{ "generated": "2026-09-12T14:42:03+00:00", "count": 102, "endpoints": { "index": "/api/index.json", "talk": "/api/talks/{id}.json", "topics": "/api/topics.json", "summary": "/#{id}", "transcript_html": "/transcripts/{id}.html", "transcript_txt": "/transcripts/{id}.txt", "transcript_vtt": "/transcripts/{id}.vtt", "transcripts_index": "/transcripts/", "transcripts_all_txt": "/transcripts/all.txt", "transcripts_all_json": "/transcripts/all.json" }, "talks": [ { "id": "-jY2T2PiJBE", "title": "MCP Apps: Extending the Frontier — Ido Salomon & Liad Yosef", "channel": "AI Engineer", "duration": 1118, "upload_date": null, "one_liner": "The creators of MCP-UI explain how MCP Apps — the official Anthropic/OpenAI-backed extension to MCP they co-authored — lets any server ship its own branded, interactive UI into Claude, ChatGPT and other hosts, turning websites into composable UI 'atoms' inside personal assistants.", "topics": [ "mcp", "agentic-web", "generative-ui", "protocols", "chat-interfaces", "developer-tools", "distribution" ], "url": "https://www.youtube.com/watch?v=-jY2T2PiJBE", "api": "/api/talks/-jY2T2PiJBE.json", "summary_url": "/#-jY2T2PiJBE", "transcript": { "html": "/transcripts/-jY2T2PiJBE.html", "txt": "/transcripts/-jY2T2PiJBE.txt", "vtt": "/transcripts/-jY2T2PiJBE.vtt" } }, { "id": "-npY6XjM8CQ", "title": "When Will The Benchmaxxing Plague End? — Nick Heiner, Surge AI", "channel": "AI Engineer", "duration": 1045, "upload_date": null, "one_liner": "Surge AI's Nick Heiner dissects why benchmarks diverge from real-world value — pricing you out of quality data, contamination, reward hacking, string-match verifiers and missing product taste — and argues the fix is expensive human experts, two-way prompt/verifier alignment and private holdout sets.", "topics": [ "evals", "benchmarks", "benchmaxxing", "contamination", "reward-hacking", "human-eval", "data-quality", "agents" ], "url": "https://www.youtube.com/watch?v=-npY6XjM8CQ", "api": "/api/talks/-npY6XjM8CQ.json", "summary_url": "/#-npY6XjM8CQ", "transcript": { "html": "/transcripts/-npY6XjM8CQ.html", "txt": "/transcripts/-npY6XjM8CQ.txt", "vtt": "/transcripts/-npY6XjM8CQ.vtt" } }, { "id": "0I6aoPSRzVc", "title": "What If Your Chip Design Team Moved Like a Single Body? — Abduallah Mohamed, AIDAChip", "channel": "AI Engineer", "duration": 1006, "upload_date": null, "one_liner": "AIDAChip's VP of AI/ML argues that chip design teams lose 70% of their time to alignment, not engineering skill, and demos a 'shared nervous system' — a human-approved living intent graph, a tribal-knowledge memory layer, and role-specific design agents — that they measure as 4x leverage.", "topics": [ "agents", "chip design", "multi-agent systems", "graph memory", "evals", "human-in-the-loop", "agent sandboxing", "org alignment" ], "url": "https://www.youtube.com/watch?v=0I6aoPSRzVc", "api": "/api/talks/0I6aoPSRzVc.json", "summary_url": "/#0I6aoPSRzVc", "transcript": { "html": "/transcripts/0I6aoPSRzVc.html", "txt": "/transcripts/0I6aoPSRzVc.txt", "vtt": "/transcripts/0I6aoPSRzVc.vtt" } }, { "id": "0uC6u0lJJl4", "title": "Your company brain will leak secrets: how we stopped it for big banks — Tanmai Gopal, PromptQL", "channel": "AI Engineer", "duration": 1585, "upload_date": null, "one_liner": "Tanmai Gopal (PromptQL, ex-Hasura) argues a company brain is just shared markdown context plus per-file access-control rules handed to a coding agent, and the only way to keep it from leaking secrets is to make the agent *suggest* memory with scopes for a named human to accept, and to inject the user's own credentials at the HTTP/SQL layer instead of storing them in the sandbox.", "topics": [ "agents", "security", "access-control", "memory", "knowledge-management", "coding-agents", "multi-agent", "enterprise" ], "url": "https://www.youtube.com/watch?v=0uC6u0lJJl4", "api": "/api/talks/0uC6u0lJJl4.json", "summary_url": "/#0uC6u0lJJl4", "transcript": { "html": "/transcripts/0uC6u0lJJl4.html", "txt": "/transcripts/0uC6u0lJJl4.txt", "vtt": "/transcripts/0uC6u0lJJl4.vtt" } }, { "id": "17-YSUHo6Lk", "title": "Agentic SDLC at Uber — Uday Kiran Medisetty & Adam Huda, Uber", "channel": "AI Engineer", "duration": 1106, "upload_date": null, "one_liner": "Uber's platform team shows the six building blocks — model gateway, MCP gateway, agentified devpods, a managed skills marketplace, a context graph, and the Cortana assistant — behind a \"software factory\" where over 70% of PRs now come from local or cloud agents.", "topics": [ "agents", "developer-tooling", "mcp", "platform-engineering", "context-engineering", "skills", "code-review", "evals" ], "url": "https://www.youtube.com/watch?v=17-YSUHo6Lk", "api": "/api/talks/17-YSUHo6Lk.json", "summary_url": "/#17-YSUHo6Lk", "transcript": { "html": "/transcripts/17-YSUHo6Lk.html", "txt": "/transcripts/17-YSUHo6Lk.txt", "vtt": "/transcripts/17-YSUHo6Lk.vtt" } }, { "id": "1KOdiGgMtpY", "title": "The Signal Layer: What to Build When Anything Can Be Built — Lena Hall, Akamai", "channel": "AI Engineer", "duration": 1184, "upload_date": null, "one_liner": "Lena Hall argues that now that AI makes implementation free and convergent, the scarce work is the \"signal layer\" — deciding what to point AI at, and getting that specific point of view to your customers without it being averaged away in transit.", "topics": [ "ai-strategy", "differentiation", "product", "go-to-market", "coding-agents", "evals", "content", "trust" ], "url": "https://www.youtube.com/watch?v=1KOdiGgMtpY", "api": "/api/talks/1KOdiGgMtpY.json", "summary_url": "/#1KOdiGgMtpY", "transcript": { "html": "/transcripts/1KOdiGgMtpY.html", "txt": "/transcripts/1KOdiGgMtpY.txt", "vtt": "/transcripts/1KOdiGgMtpY.vtt" } }, { "id": "2WZsT-znFTQ", "title": "Guardians of the State: An Air-Gapped AI Fortress for Consumer Data — Rachna Srivastava, DFPI", "channel": "AI Engineer", "duration": 1273, "upload_date": null, "one_liner": "A California DFPI engineer walks through the air-gapped, court-defensible AI system her team built for financial fraud investigation — Kafka + Spark + LLM, SHA-256 hashing keyed to a hardware module bolted to the rack, a semantic router, and a physically one-way fiber data diode.", "topics": [ "air-gapped ai", "security", "data engineering", "kafka", "spark", "model routing", "auditability", "govtech" ], "url": "https://www.youtube.com/watch?v=2WZsT-znFTQ", "api": "/api/talks/2WZsT-znFTQ.json", "summary_url": "/#2WZsT-znFTQ", "transcript": { "html": "/transcripts/2WZsT-znFTQ.html", "txt": "/transcripts/2WZsT-znFTQ.txt", "vtt": "/transcripts/2WZsT-znFTQ.vtt" } }, { "id": "2aS7aKoXn64", "title": "Rethinking Environments for Long-Horizon Work — Rayan Garg, Theta Software", "channel": "AI Engineer", "duration": 1275, "upload_date": null, "one_liner": "Two Theta Software co-founders argue that \"long horizon\" is a moving scalar, not a category, and that the hard part of building RL environments for it is the verifier — which has to be an agent with its own harness and read-only access to the environment, not an LLM call with the trajectory stuffed in its context.", "topics": [ "rl-environments", "long-horizon-agents", "evals", "llm-as-judge", "rubrics", "reward-hacking", "benchmarks", "agent-harnesses" ], "url": "https://www.youtube.com/watch?v=2aS7aKoXn64", "api": "/api/talks/2aS7aKoXn64.json", "summary_url": "/#2aS7aKoXn64", "transcript": { "html": "/transcripts/2aS7aKoXn64.html", "txt": "/transcripts/2aS7aKoXn64.txt", "vtt": "/transcripts/2aS7aKoXn64.vtt" } }, { "id": "2bvtay8wGYI", "title": "Scaling to Long Horizons — Ross Taylor & Chengxi Taylor, General Reasoning", "channel": "AI Engineer", "duration": 1087, "upload_date": null, "one_liner": "The team behind Galactica and Llama post-training argues that RL — not better base models alone — is what unlocks capability, and that the next frontier is long-horizon agents, which need value models, compaction, and new infra because every frontier model lost money on their year-long football-betting benchmark.", "topics": [ "reinforcement learning", "long-horizon agents", "reasoning", "post-training", "benchmarks", "rl-infrastructure", "context-management", "value-models" ], "url": "https://www.youtube.com/watch?v=2bvtay8wGYI", "api": "/api/talks/2bvtay8wGYI.json", "summary_url": "/#2bvtay8wGYI", "transcript": { "html": "/transcripts/2bvtay8wGYI.html", "txt": "/transcripts/2bvtay8wGYI.txt", "vtt": "/transcripts/2bvtay8wGYI.vtt" } }, { "id": "32nrHU6zHU8", "title": "Agents Are Where Microservices Were in 2015 — Roberto Milev & Uday Kanagala, Navan", "channel": "AI Engineer", "duration": 1168, "upload_date": null, "one_liner": "Navan's chief architect and an architect on his team argue that agentic systems in 2026 are where microservices were in 2015 — a reference architecture (runtime, memory, context, observability, evals, guardrails, orchestration) is crystallizing, and the rule is: if you can't build a single agentic loop, don't try to build a multi-agent orchestrated system.", "topics": [ "agents", "multi-agent", "agent-infrastructure", "observability", "evals", "memory", "context-engineering", "guardrails" ], "url": "https://www.youtube.com/watch?v=32nrHU6zHU8", "api": "/api/talks/32nrHU6zHU8.json", "summary_url": "/#32nrHU6zHU8", "transcript": { "html": "/transcripts/32nrHU6zHU8.html", "txt": "/transcripts/32nrHU6zHU8.txt", "vtt": "/transcripts/32nrHU6zHU8.vtt" } }, { "id": "4loPnxvWWhg", "title": "Your Fine-Tuned Model Is Tech Debt: A 50x ROI House of Cards — Dan Bjornn, Lease End", "channel": "AI Engineer", "duration": 999, "upload_date": null, "one_liner": "A senior data scientist walks through how his team's fine-tuned SMS intent classifier drove $12M of revenue at 50x ROI and still became tech debt — and how replacing it with skills, tools and context on a model-agnostic agentic framework cut the fix cycle from a week to under an hour while raising accuracy.", "topics": [ "fine-tuning", "context-engineering", "agents", "rag", "intent-classification", "tech-debt", "llm-ops", "evals" ], "url": "https://www.youtube.com/watch?v=4loPnxvWWhg", "api": "/api/talks/4loPnxvWWhg.json", "summary_url": "/#4loPnxvWWhg", "transcript": { "html": "/transcripts/4loPnxvWWhg.html", "txt": "/transcripts/4loPnxvWWhg.txt", "vtt": "/transcripts/4loPnxvWWhg.vtt" } }, { "id": "5Bn0xro2ol8", "title": "How to Get Your Org to Adopt Coding Agents (Without Shipping Garbage) — Eyal Blum, Figma", "channel": "AI Engineer", "duration": 1063, "upload_date": null, "one_liner": "A Figma engineer's field report on rolling out coding agents across an engineering org: invest in verification, spend a week writing the plan and let the agent implement it overnight, and put your AI skeptics in charge of the roadmap for making agents safe.", "topics": [ "coding agents", "ai adoption", "engineering culture", "verification", "tdd", "planning", "code review", "developer experience" ], "url": "https://www.youtube.com/watch?v=5Bn0xro2ol8", "api": "/api/talks/5Bn0xro2ol8.json", "summary_url": "/#5Bn0xro2ol8", "transcript": { "html": "/transcripts/5Bn0xro2ol8.html", "txt": "/transcripts/5Bn0xro2ol8.txt", "vtt": "/transcripts/5Bn0xro2ol8.vtt" } }, { "id": "5Cxe5dv2Xlw", "title": "Why AI Agents Need Million-Token Context — Thomas Wolf & Olive Song, MiniMax", "channel": "AI Engineer", "duration": 1248, "upload_date": null, "one_liner": "MiniMax's Olive Song explains how M3 (~428B total / 23B active params) gets a functional 1M-token context via MiniMax Sparse Attention — an index branch that picks what matters plus a sparse branch that computes only on selected blocks — and why they trained vision in natively from the very first pre-training step rather than bolting on adapters.", "topics": [ "long-context", "sparse-attention", "agents", "multimodality", "open-source-models", "pretraining", "moe", "research-culture" ], "url": "https://www.youtube.com/watch?v=5Cxe5dv2Xlw", "api": "/api/talks/5Cxe5dv2Xlw.json", "summary_url": "/#5Cxe5dv2Xlw", "transcript": { "html": "/transcripts/5Cxe5dv2Xlw.html", "txt": "/transcripts/5Cxe5dv2Xlw.txt", "vtt": "/transcripts/5Cxe5dv2Xlw.vtt" } }, { "id": "6pbQgnJ9Voc", "title": "Knowledge Systems: The New GTM Stack — Jeffrey Wang, Exa", "channel": "AI Engineer", "duration": 1129, "upload_date": null, "one_liner": "Exa co-founder Jeff Wang argues go-to-market is a data problem you can solve as an AI engineering problem, and walks through the four systems his ~115-person company actually runs: an ICP dashboard, a customer-signal alerter called Request Lens, a fleet of Slack coding agents, and \"Jeffbot,\" an eval-calibrated clone of himself.", "topics": [ "go-to-market", "agents", "mcp", "evals", "search", "embeddings", "sales-engineering", "internal-tools" ], "url": "https://www.youtube.com/watch?v=6pbQgnJ9Voc", "api": "/api/talks/6pbQgnJ9Voc.json", "summary_url": "/#6pbQgnJ9Voc", "transcript": { "html": "/transcripts/6pbQgnJ9Voc.html", "txt": "/transcripts/6pbQgnJ9Voc.txt", "vtt": "/transcripts/6pbQgnJ9Voc.vtt" } }, { "id": "7A65O-0lvKE", "title": "Which AI startups actually land enterprise contracts? — Brian Lewis, Millennium", "channel": "AI Engineer", "duration": 1125, "upload_date": null, "one_liner": "A Millennium product lead breaks down why only ~5% of AI vendor demo calls become signed contracts, enumerating the exact efficacy, security, reliability and legal requirements deals die on — and argues 60% of becoming AI-native is unsexy work like entitlements and data hygiene that has nothing to do with AI.", "topics": [ "enterprise sales", "ai procurement", "security", "entitlements", "agents", "reliability", "data governance", "change management" ], "url": "https://www.youtube.com/watch?v=7A65O-0lvKE", "api": "/api/talks/7A65O-0lvKE.json", "summary_url": "/#7A65O-0lvKE", "transcript": { "html": "/transcripts/7A65O-0lvKE.html", "txt": "/transcripts/7A65O-0lvKE.txt", "vtt": "/transcripts/7A65O-0lvKE.vtt" } }, { "id": "7GMKdpLsxwU", "title": "The Missing Layer: Design Taste in AI Agents — Hassan El Mghari, Together AI", "channel": "AI Engineer", "duration": 850, "upload_date": null, "one_liner": "Hassan El Mghari (Together AI) argues that the 10–20% of extra effort spent on UI is the biggest competitive advantage for AI apps, and shows how to get it: codify the visual tells of \"AI slop\" into a skill, feed agents real references and screenshots, and iterate with cheap fast open-source models like GLM 5.2.", "topics": [ "design", "ai-slop", "vibe-coding", "prompting", "open-source-models", "agent-skills", "ui-ux", "iteration" ], "url": "https://www.youtube.com/watch?v=7GMKdpLsxwU", "api": "/api/talks/7GMKdpLsxwU.json", "summary_url": "/#7GMKdpLsxwU", "transcript": { "html": "/transcripts/7GMKdpLsxwU.html", "txt": "/transcripts/7GMKdpLsxwU.txt", "vtt": "/transcripts/7GMKdpLsxwU.vtt" } }, { "id": "8KkibGU_DDY", "title": "Mousepower: agents that can’t be measured, can’t be managed. — Maximillian Piras, Yutori", "channel": "AI Engineer", "duration": 1238, "upload_date": null, "one_liner": "Yutori's founding designer argues agents have a measurement problem — like James Watt inventing \"horsepower\" to sell steam engines to people who thought in horses, if you ship an agent you also have to ship the rubric that lets customers verify its work and justify the token spend.", "topics": [ "agents", "evals", "computer-use", "roi", "token-cost", "code-review", "product-design", "verification" ], "url": "https://www.youtube.com/watch?v=8KkibGU_DDY", "api": "/api/talks/8KkibGU_DDY.json", "summary_url": "/#8KkibGU_DDY", "transcript": { "html": "/transcripts/8KkibGU_DDY.html", "txt": "/transcripts/8KkibGU_DDY.txt", "vtt": "/transcripts/8KkibGU_DDY.vtt" } }, { "id": "9R--1tg45Jg", "title": "Build-Time vs. Run-Time: Why Dev Tools Fail in Production — Averi Kitsch & Prerna Kakkar, Google", "channel": "AI Engineer", "duration": 1226, "upload_date": null, "one_liner": "Two Google engineers behind MCP Toolbox for Databases argue that the flexible, model-controlled database tools that work fine in a dev assistant become data-breach machines in production, and walk through the step-by-step hardening — source primitive, custom SQL tools, bound/authenticated parameters — that ends in a tool whose only input is a date.", "topics": [ "mcp", "agents", "databases", "security", "tool-design", "sql", "authentication", "evals" ], "url": "https://www.youtube.com/watch?v=9R--1tg45Jg", "api": "/api/talks/9R--1tg45Jg.json", "summary_url": "/#9R--1tg45Jg", "transcript": { "html": "/transcripts/9R--1tg45Jg.html", "txt": "/transcripts/9R--1tg45Jg.txt", "vtt": "/transcripts/9R--1tg45Jg.vtt" } }, { "id": "9wZpvF3QleU", "title": "500 Skills, Zero Fine-Tuning: LinkedIn's Playbook for AI Agents — Ajay Prakash, LinkedIn", "channel": "AI Engineer", "duration": 1225, "upload_date": null, "one_liner": "LinkedIn made off-the-shelf coding agents useful inside a 1,000-repo enterprise not by fine-tuning but by serving instructions as MCP tools — \"playbooks\" — behind three meta tools (search / get schema / execute), now 600+ playbooks used by 8,000+ people daily.", "topics": [ "agents", "context-engineering", "mcp", "coding-agents", "skills", "developer-productivity", "enterprise", "tool-scaling" ], "url": "https://www.youtube.com/watch?v=9wZpvF3QleU", "api": "/api/talks/9wZpvF3QleU.json", "summary_url": "/#9wZpvF3QleU", "transcript": { "html": "/transcripts/9wZpvF3QleU.html", "txt": "/transcripts/9wZpvF3QleU.txt", "vtt": "/transcripts/9wZpvF3QleU.vtt" } }, { "id": "A-zeQiYkmXk", "title": "Teaching agents to pay — Anna Spysz, Stripe", "channel": "AI Engineer", "duration": 1150, "upload_date": null, "one_liner": "A Stripe developer advocate walks through building a UCP-based shopping agent that buys studio headphones from a local Portland record shop, covering what a merchant must publish to be agent-readable, how the system prompt persona can turn an agent into a manipulative salesperson, and how shared payment tokens keep the card number away from both the agent and the seller.", "topics": [ "agentic commerce", "agents", "payments", "protocols", "system prompts", "guardrails", "structured data", "auditability" ], "url": "https://www.youtube.com/watch?v=A-zeQiYkmXk", "api": "/api/talks/A-zeQiYkmXk.json", "summary_url": "/#A-zeQiYkmXk", "transcript": { "html": "/transcripts/A-zeQiYkmXk.html", "txt": "/transcripts/A-zeQiYkmXk.txt", "vtt": "/transcripts/A-zeQiYkmXk.vtt" } }, { "id": "AhQpRalYlyg", "title": "Multimodal Collaborative Agents for Next-Gen Commerce — Nidhi Kaushik Vyas, Google DeepMind", "channel": "AI Engineer", "duration": 1268, "upload_date": null, "one_liner": "A Google DeepMind PM lays out a three-phase loop — discovery, multimodal research, adaptive response — for shopping agents that meet users arriving with a vibe rather than keywords, with a named auto-rater for every step.", "topics": [ "agents", "multimodal", "commerce", "evals", "auto-raters", "preference-elicitation", "ontology", "ux" ], "url": "https://www.youtube.com/watch?v=AhQpRalYlyg", "api": "/api/talks/AhQpRalYlyg.json", "summary_url": "/#AhQpRalYlyg", "transcript": { "html": "/transcripts/AhQpRalYlyg.html", "txt": "/transcripts/AhQpRalYlyg.txt", "vtt": "/transcripts/AhQpRalYlyg.vtt" } }, { "id": "B0fjR3yaZFU", "title": "How do you diffuse AI into the real world? — Varun Shenoy, Long Lake", "channel": "AI Engineer", "duration": 1066, "upload_date": null, "one_liner": "Long Lake's co-founder argues AI diffusion — not model capability — is the bottleneck, and shows what it looks like to solve it by literally buying 35 services businesses and deploying agents inside them as the owner rather than the vendor.", "topics": [ "ai diffusion", "agents", "evals", "enterprise deployment", "continual learning", "post-training", "autonomy", "enablement" ], "url": "https://www.youtube.com/watch?v=B0fjR3yaZFU", "api": "/api/talks/B0fjR3yaZFU.json", "summary_url": "/#B0fjR3yaZFU", "transcript": { "html": "/transcripts/B0fjR3yaZFU.html", "txt": "/transcripts/B0fjR3yaZFU.txt", "vtt": "/transcripts/B0fjR3yaZFU.vtt" } }, { "id": "DrTdD-ttjCY", "title": "Building GTM AI Agents: Lessons from Deploying to 6,000 Users — Sait Izmit, Snowflake", "channel": "AI Engineer", "duration": 1239, "upload_date": null, "one_liner": "Snowflake's internal go-to-market agent has answered over 1 million questions for 6,000 sellers, and the speaker argues its success came from choosing quality over coverage, investing heavily in change management, and constantly re-architecting rather than waiting for the perfect stack.", "topics": [ "agents", "go-to-market", "enterprise-ai", "evals", "change-management", "adoption", "observability", "mcp" ], "url": "https://www.youtube.com/watch?v=DrTdD-ttjCY", "api": "/api/talks/DrTdD-ttjCY.json", "summary_url": "/#DrTdD-ttjCY", "transcript": { "html": "/transcripts/DrTdD-ttjCY.html", "txt": "/transcripts/DrTdD-ttjCY.txt", "vtt": "/transcripts/DrTdD-ttjCY.vtt" } }, { "id": "EL123UNokkI", "title": "Building uReview, Uber’s Multi-Agent Code Review Engine — Will Bond & Ameya Ketkar, Uber", "channel": "AI Engineer", "duration": 907, "upload_date": null, "one_liner": "Uber built uReview, an in-house multi-agent code review engine, after first-time-to-review ballooned from 3 hours in 2024 to 9 hours in 2026 — it now posts ~25,000 comments a week with a 67% addressal rate, at 60% lower cost and ~70% higher accuracy than a naive implementation.", "topics": [ "agents", "code-review", "evals", "observability", "developer-productivity", "multi-agent", "monorepo", "agentic-sdlc" ], "url": "https://www.youtube.com/watch?v=EL123UNokkI", "api": "/api/talks/EL123UNokkI.json", "summary_url": "/#EL123UNokkI", "transcript": { "html": "/transcripts/EL123UNokkI.html", "txt": "/transcripts/EL123UNokkI.txt", "vtt": "/transcripts/EL123UNokkI.vtt" } }, { "id": "FLUoowDJg4I", "title": "How I automate my own job at Hugging Face using agents — Niels Rogge, Hugging Face", "channel": "AI Engineer", "duration": 1237, "upload_date": null, "one_liner": "A Hugging Face ML engineer shows how he replaced his own manual outreach job — asking researchers to move model weights off Google Drive onto the hub — with a nightly GitHub Actions cron workflow plus a Claude Agent SDK agent on Modal that now opens and follows up on thousands of GitHub issues, with only two negative replies so far.", "topics": [ "agents", "workflows", "evals", "automation", "open-models", "observability", "deployment", "open-source-research" ], "url": "https://www.youtube.com/watch?v=FLUoowDJg4I", "api": "/api/talks/FLUoowDJg4I.json", "summary_url": "/#FLUoowDJg4I", "transcript": { "html": "/transcripts/FLUoowDJg4I.html", "txt": "/transcripts/FLUoowDJg4I.txt", "vtt": "/transcripts/FLUoowDJg4I.vtt" } }, { "id": "FvxY8oPoI8o", "title": "Preferences Over Benchmarks: Model Routing — Archana Kamath & Tyler Gillam, DigitalOcean", "channel": "AI Engineer", "duration": 954, "upload_date": null, "one_liner": "DigitalOcean's inference router picks a model per request from your own stated preferences — cost, latency, task, hard rules — rather than from a leaderboard, and a live opencode demo shows ~3x lower session cost than routing everything to Opus at roughly equal quality.", "topics": [ "model routing", "inference cost", "evals", "coding agents", "llmops", "open source", "reliability", "caching" ], "url": "https://www.youtube.com/watch?v=FvxY8oPoI8o", "api": "/api/talks/FvxY8oPoI8o.json", "summary_url": "/#FvxY8oPoI8o", "transcript": { "html": "/transcripts/FvxY8oPoI8o.html", "txt": "/transcripts/FvxY8oPoI8o.txt", "vtt": "/transcripts/FvxY8oPoI8o.vtt" } }, { "id": "G7cgLjZtmMU", "title": "The Agentic Commerce Stack — Ahnaf Prio, Best Buy", "channel": "AI Engineer", "duration": 1238, "upload_date": null, "one_liner": "A Best Buy engineering manager maps the acronym soup of agentic commerce — MCP, A2A, ACP, UCP, AP2 — onto what each actually does in a checkout flow, and demos a working customer-agent/merchant-agent stack built on those primitives.", "topics": [ "agentic-commerce", "mcp", "a2a", "protocols", "payments", "evals", "retail", "agents" ], "url": "https://www.youtube.com/watch?v=G7cgLjZtmMU", "api": "/api/talks/G7cgLjZtmMU.json", "summary_url": "/#G7cgLjZtmMU", "transcript": { "html": "/transcripts/G7cgLjZtmMU.html", "txt": "/transcripts/G7cgLjZtmMU.txt", "vtt": "/transcripts/G7cgLjZtmMU.vtt" } }, { "id": "GJX19pNhmSw", "title": "FinOps for AI Agents: Who Spent All the Tokens? — Tisha Chawla & Susheem Koul, Microsoft", "channel": "AI Engineer", "duration": 1284, "upload_date": null, "one_liner": "Two Microsoft engineers argue that agent cost control belongs at the agent-run layer, not the model-request layer, and demo \"TokenOps\" — an out-of-band control plane that steers a running agent (compaction, tool-output trimming, injected \"be succinct\" instructions) before ever killing it, benchmarked at ~78% lower average spend with completion rising from 67% to ~96% versus simple throttling.", "topics": [ "agents", "finops", "cost-control", "observability", "governance", "tokens", "context-management", "benchmarks" ], "url": "https://www.youtube.com/watch?v=GJX19pNhmSw", "api": "/api/talks/GJX19pNhmSw.json", "summary_url": "/#GJX19pNhmSw", "transcript": { "html": "/transcripts/GJX19pNhmSw.html", "txt": "/transcripts/GJX19pNhmSw.txt", "vtt": "/transcripts/GJX19pNhmSw.vtt" } }, { "id": "HvMyYLTfvhg", "title": "Building Agents Is Trivial Now, Context Is the Next Frontier — Jeff Ng, Unblocked", "channel": "AI Engineer", "duration": 802, "upload_date": null, "one_liner": "Cloud primitives and frameworks have made deploying an agent nearly trivial, so the failure mode has shifted from infrastructure to missing organizational context — and Unblocked's Jeff Ng demos a Linear-triage agent that confidently recommends a fix that already caused an outage, until a \"context engine\" feeds it the Slack thread and postmortem it never saw.", "topics": [ "agents", "context-engineering", "mcp", "background-agents", "agent-infrastructure", "developer-tools", "rag", "observability" ], "url": "https://www.youtube.com/watch?v=HvMyYLTfvhg", "api": "/api/talks/HvMyYLTfvhg.json", "summary_url": "/#HvMyYLTfvhg", "transcript": { "html": "/transcripts/HvMyYLTfvhg.html", "txt": "/transcripts/HvMyYLTfvhg.txt", "vtt": "/transcripts/HvMyYLTfvhg.vtt" } }, { "id": "KHudyx5wW3U", "title": "Agent Frameworks Considered Harmful — Rémi Louf, .txt", "channel": "AI Engineer", "duration": 1229, "upload_date": null, "one_liner": "The CEO of .txt took two weeks off to build his own agent runtime for a morning briefing, and found that the useful primitives aren't framework graphs but markdown agent definitions, typed events, an append-only log and a content-addressed prompt store.", "topics": [ "agents", "agent-frameworks", "event-driven-architecture", "structured-outputs", "observability", "prompt-versioning", "open-source-models", "background-agents" ], "url": "https://www.youtube.com/watch?v=KHudyx5wW3U", "api": "/api/talks/KHudyx5wW3U.json", "summary_url": "/#KHudyx5wW3U", "transcript": { "html": "/transcripts/KHudyx5wW3U.html", "txt": "/transcripts/KHudyx5wW3U.txt", "vtt": "/transcripts/KHudyx5wW3U.vtt" } }, { "id": "KLDdXOw6jIc", "title": "Leads of Nano Banana, Imagen, Veo, Gemini Omni and Omni Thinking recap the year in Generative Media", "channel": "AI Engineer", "duration": 3419, "upload_date": null, "one_liner": "Google's gen-media leads (Nano Banana, Veo/Omni, Omni Thinking/Gemini RL) explain what shipped this week — Nano Banana 2 Light and the Gemini Omni Flash APIs priced like Veo 3.1 Fast — and argue that video is the missing foundational model for AGI, while conceding that language captioning is a lossy bottleneck and that video evals still come down to humans in a room comparing clips side by side.", "topics": [ "generative-media", "video-generation", "world-models", "evals", "multimodality", "reinforcement-learning", "data", "aesthetics" ], "url": "https://www.youtube.com/watch?v=KLDdXOw6jIc", "api": "/api/talks/KLDdXOw6jIc.json", "summary_url": "/#KLDdXOw6jIc", "transcript": { "html": "/transcripts/KLDdXOw6jIc.html", "txt": "/transcripts/KLDdXOw6jIc.txt", "vtt": "/transcripts/KLDdXOw6jIc.vtt" } }, { "id": "KcVkq5L-0f0", "title": "Your agents lack context: Here's how to fix \"You're absolutely right!\" — Brandon Waselnuk, Unblocked", "channel": "AI Engineer", "duration": 849, "upload_date": null, "one_liner": "Brandon Waselnuk of Unblocked argues the bottleneck is no longer model intelligence but context, and shows that feeding an agent a real \"context engine\" cut the same task from ~21M tokens to 10.8M and saved about two hours of wall clock.", "topics": [ "context-engineering", "agents", "rag", "mcp", "tokenomics", "code-review", "developer-tools", "enterprise-codebases" ], "url": "https://www.youtube.com/watch?v=KcVkq5L-0f0", "api": "/api/talks/KcVkq5L-0f0.json", "summary_url": "/#KcVkq5L-0f0", "transcript": { "html": "/transcripts/KcVkq5L-0f0.html", "txt": "/transcripts/KcVkq5L-0f0.txt", "vtt": "/transcripts/KcVkq5L-0f0.vtt" } }, { "id": "Krzs8GeiWTc", "title": "Generative UI... in Python? — Jeremiah Lowin, Prefect", "channel": "AI Engineer", "duration": 1058, "upload_date": null, "one_liner": "The author of FastMCP explains how MCP apps let a tool return a full HTML/CSS/JS UI straight to the user instead of into the agent's context, and shows Prefab — a Python context-manager DSL that composes shadcn components into a JSON UI protocol — plus the discovery that streaming the Python is ~70% smaller than streaming the JSON.", "topics": [ "mcp", "generative-ui", "agents", "python", "developer-tools", "frontend", "token-efficiency" ], "url": "https://www.youtube.com/watch?v=Krzs8GeiWTc", "api": "/api/talks/Krzs8GeiWTc.json", "summary_url": "/#Krzs8GeiWTc", "transcript": { "html": "/transcripts/Krzs8GeiWTc.html", "txt": "/transcripts/Krzs8GeiWTc.txt", "vtt": "/transcripts/Krzs8GeiWTc.vtt" } }, { "id": "L173Z8DpaJg", "title": "The Agent Behind the Curtain: Building the Oz Cloud Agent Platform — Safia Abdalla, Warp", "channel": "AI Engineer", "duration": 1251, "upload_date": null, "one_liner": "Safia Abdalla explains how Warp built its Oz cloud agent platform around one principle — platforms should absorb complexity before it reaches the user — covering bring-your-own-infra sandboxes, multi-harness support, agent orchestration, an API/SDK for every primitive, and the agent-run triage/review pipeline that let Warp absorb thousands of PRs after open-sourcing.", "topics": [ "agents", "agent-orchestration", "developer-tools", "cloud-sandboxes", "open-source", "code-review-automation", "platform-apis", "multi-agent" ], "url": "https://www.youtube.com/watch?v=L173Z8DpaJg", "api": "/api/talks/L173Z8DpaJg.json", "summary_url": "/#L173Z8DpaJg", "transcript": { "html": "/transcripts/L173Z8DpaJg.html", "txt": "/transcripts/L173Z8DpaJg.txt", "vtt": "/transcripts/L173Z8DpaJg.vtt" } }, { "id": "L4I7WgiEquo", "title": "AI in GTM at Notion — Flora Liu", "channel": "AI Engineer", "duration": 1275, "upload_date": null, "one_liner": "A Notion GTM engineer explains how they replaced a spiderweb of sales/marketing tools with one four-layer system — Know, Decide, Act, Learn — where Snowflake+DynamoDB compute and serve a customer context layer that both reps and agents read from inside Notion, driving a claimed 63% lift in users taking the next step after context-aware recommendations.", "topics": [ "agents", "gtm-engineering", "context-layer", "multi-agent-workflows", "data-infrastructure", "human-in-the-loop", "build-vs-buy", "sales-automation" ], "url": "https://www.youtube.com/watch?v=L4I7WgiEquo", "api": "/api/talks/L4I7WgiEquo.json", "summary_url": "/#L4I7WgiEquo", "transcript": { "html": "/transcripts/L4I7WgiEquo.html", "txt": "/transcripts/L4I7WgiEquo.txt", "vtt": "/transcripts/L4I7WgiEquo.vtt" } }, { "id": "Lrw0jqBNaw0", "title": "The Death of Developer Advocates — Stephanie Jarmak, Sourcegraph", "channel": "AI Engineer", "duration": 1096, "upload_date": null, "one_liner": "A Sourcegraph research scientist argues developer advocacy isn't dead but has gained a second user — the agent — and shows how to measure it: an SDLC benchmark of her company's MCP tool plus a GEO experiment where their product was recommended 65% of the time to comparison shoppers and 0% of the time to someone describing the actual pain it solves.", "topics": [ "devrel", "agents", "evals", "geo", "mcp", "benchmarks", "developer-experience", "go-to-market" ], "url": "https://www.youtube.com/watch?v=Lrw0jqBNaw0", "api": "/api/talks/Lrw0jqBNaw0.json", "summary_url": "/#Lrw0jqBNaw0", "transcript": { "html": "/transcripts/Lrw0jqBNaw0.html", "txt": "/transcripts/Lrw0jqBNaw0.txt", "vtt": "/transcripts/Lrw0jqBNaw0.vtt" } }, { "id": "M05vON8i0aI", "title": "AI-Native Organisations Run on Skills: How to Structure and Scale Them — Imad Touil, QuantumBlack", "channel": "AI Engineer", "duration": 1231, "upload_date": null, "one_liner": "A QuantumBlack distinguished engineer argues that skills are where an organisation's know-how actually lives in the agentic stack, and that without a governed, centralised skills registry — catalog, versioning, ownership, access control, evals — teams generate a new class of technical debt: duplication, degrading quality and rising token cost.", "topics": [ "agent-skills", "agentic-workflows", "governance", "platform-engineering", "mcp", "evals", "context-engineering", "enterprise-ai" ], "url": "https://www.youtube.com/watch?v=M05vON8i0aI", "api": "/api/talks/M05vON8i0aI.json", "summary_url": "/#M05vON8i0aI", "transcript": { "html": "/transcripts/M05vON8i0aI.html", "txt": "/transcripts/M05vON8i0aI.txt", "vtt": "/transcripts/M05vON8i0aI.vtt" } }, { "id": "NW-jwOVr32w", "title": "The Design-Code Roundtrip That Isn't — Jonathan Gordon, ReWeaver AI", "channel": "AI Engineer", "duration": 1117, "upload_date": null, "one_liner": "A 30-year design-tools veteran tests the industry's claim that the design↔code roundtrip is solved, finds it lossy across five tool setups, and argues the fix is deterministic guardrails that detect and reconcile drift rather than more AI in the loop.", "topics": [ "design-to-code", "design systems", "drift", "accessibility", "vibe coding", "guardrails", "developer tools", "code generation" ], "url": "https://www.youtube.com/watch?v=NW-jwOVr32w", "api": "/api/talks/NW-jwOVr32w.json", "summary_url": "/#NW-jwOVr32w", "transcript": { "html": "/transcripts/NW-jwOVr32w.html", "txt": "/transcripts/NW-jwOVr32w.txt", "vtt": "/transcripts/NW-jwOVr32w.vtt" } }, { "id": "O1FN4awNEtM", "title": "Designing for AI Engineer — Vincent Wendy, AI Engineer", "channel": "AI Engineer", "duration": 1008, "upload_date": null, "one_liner": "One designer at AI Engineer covers 7,000 attendees, 140+ sponsors and 300+ speakers by treating Devin, GPT and Figma as his design team — a locked-down design system plus automated, spec-sheet-driven generation of schedules, speaker cards and signage, with Devin also acting as visual QA.", "topics": [ "design", "design-systems", "automation", "agents", "devin", "figma", "conference-ops", "visual-qa" ], "url": "https://www.youtube.com/watch?v=O1FN4awNEtM", "api": "/api/talks/O1FN4awNEtM.json", "summary_url": "/#O1FN4awNEtM", "transcript": { "html": "/transcripts/O1FN4awNEtM.html", "txt": "/transcripts/O1FN4awNEtM.txt", "vtt": "/transcripts/O1FN4awNEtM.vtt" } }, { "id": "Qr15lGAGKpo", "title": "Everyone Gets A Software Company — Benjamin Guo, Zo Computer", "channel": "AI Engineer", "duration": 909, "upload_date": null, "one_liner": "Zo Computer's co-founder argues that SaaS and vendor-hosted agents have made us digital peasants under \"techno-feudalism,\" and pitches a personal cloud — your own Linux server with AI built in — where non-technical users like a free-diving instructor have replaced Squarespace and Calendly and are on track for $100k of revenue.", "topics": [ "personal agents", "cloud agents", "self-hosting", "personal cloud", "agent ownership", "saas", "consumer ai", "mcp" ], "url": "https://www.youtube.com/watch?v=Qr15lGAGKpo", "api": "/api/talks/Qr15lGAGKpo.json", "summary_url": "/#Qr15lGAGKpo", "transcript": { "html": "/transcripts/Qr15lGAGKpo.html", "txt": "/transcripts/Qr15lGAGKpo.txt", "vtt": "/transcripts/Qr15lGAGKpo.vtt" } }, { "id": "QrMcNe2jjt8", "title": "The End of the Static Screen: Architecting Intent-Driven UX — Gus Iwanaga, commercetools", "channel": "AI Engineer", "duration": 1399, "upload_date": null, "one_liner": "A commercetools GM shows why letting an LLM freely compose UI produces inconsistent, unshippable screens, and lays out the middle path his team chose — a declarative UI protocol where an orchestrator picks components and a UX agent places them inside a codified layout → slot → sub-slot → component hierarchy.", "topics": [ "generative-ui", "ui-protocols", "agentic-orchestration", "design-systems", "mcp", "ux", "b2b-saas", "atomic-design" ], "url": "https://www.youtube.com/watch?v=QrMcNe2jjt8", "api": "/api/talks/QrMcNe2jjt8.json", "summary_url": "/#QrMcNe2jjt8", "transcript": { "html": "/transcripts/QrMcNe2jjt8.html", "txt": "/transcripts/QrMcNe2jjt8.txt", "vtt": "/transcripts/QrMcNe2jjt8.vtt" } }, { "id": "Qw_tC68KKes", "title": "How AI Agents Let GTM Teams Scale — Justin Joyce, Cloudflare", "channel": "AI Engineer", "duration": 1155, "upload_date": null, "one_liner": "Cloudflare's sales-ops lead lays out a three-pillar agentic go-to-market playbook — curated skill files for analysis, a multi-agent workflow that pushes weekly insight, and a self-service agentic workspace ('Cloudflare OS') for sellers — which he says has 2x'd his team's efficiency in six months.", "topics": [ "agents", "multi-agent-workflows", "sales-ops", "go-to-market", "mcp", "skills", "revenue-operations", "observability" ], "url": "https://www.youtube.com/watch?v=Qw_tC68KKes", "api": "/api/talks/Qw_tC68KKes.json", "summary_url": "/#Qw_tC68KKes", "transcript": { "html": "/transcripts/Qw_tC68KKes.html", "txt": "/transcripts/Qw_tC68KKes.txt", "vtt": "/transcripts/Qw_tC68KKes.vtt" } }, { "id": "REascnFlq_8", "title": "Agents' next frontier: agent-to-agent and network effects — Jean-Denis Greze, Town", "channel": "AI Engineer", "duration": 1277, "upload_date": null, "one_liner": "Town CTO Jean-Denis Greze argues that \"agent-to-agent\" is really a search problem — how closely a multi-agent system can approximate one omniscient agent with all the world's data in its context window — and walks through five strategies for getting cross-silo data into that final LLM call without violating privacy.", "topics": [ "agents", "multi-agent", "agent-to-agent", "context-engineering", "privacy", "agentic-search", "enterprise-ai", "network-effects" ], "url": "https://www.youtube.com/watch?v=REascnFlq_8", "api": "/api/talks/REascnFlq_8.json", "summary_url": "/#REascnFlq_8", "transcript": { "html": "/transcripts/REascnFlq_8.html", "txt": "/transcripts/REascnFlq_8.txt", "vtt": "/transcripts/REascnFlq_8.vtt" } }, { "id": "RmS5s6Wbin4", "title": "Gadgets: Personal app vibe coding that is actually safe — Kenton Varda, Cloudflare", "channel": "AI Engineer", "duration": 1134, "upload_date": null, "one_liner": "Kenton Varda (creator of Cloudflare Workers) argues that personal AI codegen breaks traditional cloud infrastructure, and demos \"Gadgets\" — a Cloudflare-Workers-based platform where every vibe-coded app runs in a sandbox so locked down that no security bug in the generated code can matter.", "topics": [ "vibe-coding", "sandboxing", "cloudflare-workers", "durable-objects", "personal-software", "agents", "web-security", "serverless" ], "url": "https://www.youtube.com/watch?v=RmS5s6Wbin4", "api": "/api/talks/RmS5s6Wbin4.json", "summary_url": "/#RmS5s6Wbin4", "transcript": { "html": "/transcripts/RmS5s6Wbin4.html", "txt": "/transcripts/RmS5s6Wbin4.txt", "vtt": "/transcripts/RmS5s6Wbin4.vtt" } }, { "id": "S6aSoQ6_u5A", "title": "Tell the Robot What You Want — Sandhya Subramani, AWS", "channel": "AI Engineer", "duration": 1043, "upload_date": null, "one_liner": "An AWS talk that treats a robot as just another tool for an agent: a Raspberry Pi rover named Scout runs three Strands agents over 4G, with Claude Opus 4.8 as its brain deciding which preset robot policy to call from natural-language instructions.", "topics": [ "robotics", "agents", "tool-use", "vla-models", "edge-computing", "multi-agent", "embodied-ai", "live-demo" ], "url": "https://www.youtube.com/watch?v=S6aSoQ6_u5A", "api": "/api/talks/S6aSoQ6_u5A.json", "summary_url": "/#S6aSoQ6_u5A", "transcript": { "html": "/transcripts/S6aSoQ6_u5A.html", "txt": "/transcripts/S6aSoQ6_u5A.txt", "vtt": "/transcripts/S6aSoQ6_u5A.vtt" } }, { "id": "UhCY231d0FQ", "title": "GTM Engineering: The Technical Bits — Everett Berry, Clay", "channel": "AI Engineer", "duration": 1144, "upload_date": null, "one_liner": "Everett Berry of Clay lays out GTM engineering as four hard technical problems — a data layer that is a \"perfect virtual copy of the market\", orchestration across 10–30 disconnected tools, one long-running persistent agent per account, and execution against 0.5–1% email reply rates.", "topics": [ "gtm-engineering", "agents", "data-enrichment", "orchestration", "crm", "evals", "sales-automation", "outbound" ], "url": "https://www.youtube.com/watch?v=UhCY231d0FQ", "api": "/api/talks/UhCY231d0FQ.json", "summary_url": "/#UhCY231d0FQ", "transcript": { "html": "/transcripts/UhCY231d0FQ.html", "txt": "/transcripts/UhCY231d0FQ.txt", "vtt": "/transcripts/UhCY231d0FQ.vtt" } }, { "id": "V_5bn4q-vAI", "title": "How We Got LLMs to Recommend Our Open Source Library — Christopher Burns, Inth", "channel": "AI Engineer", "duration": 987, "upload_date": null, "one_liner": "The founder of the C15T cookie-banner library explains the concrete, unglamorous stack of micro-optimizations — hand-written llms.txt, markdown twins of every page, Web MCP tools, and bundled docs plus an agents.md shipped inside node_modules — that made Claude, ChatGPT, Codex and Gemini his number one source of inbound.", "topics": [ "agents", "llms.txt", "documentation", "developer experience", "mcp", "open source", "seo", "token efficiency" ], "url": "https://www.youtube.com/watch?v=V_5bn4q-vAI", "api": "/api/talks/V_5bn4q-vAI.json", "summary_url": "/#V_5bn4q-vAI", "transcript": { "html": "/transcripts/V_5bn4q-vAI.html", "txt": "/transcripts/V_5bn4q-vAI.txt", "vtt": "/transcripts/V_5bn4q-vAI.vtt" } }, { "id": "VjEP0xqTUI0", "title": "The Building Blocks of GTM Orchestration — Arman Vaziri, Ramp", "channel": "AI Engineer", "duration": 1195, "upload_date": null, "one_liner": "Ramp's product/growth engineering lead walks through the concrete stack behind \"go-to-market orchestration\" — an internal CDP on Postgres+Kafka fed by dbt/Snowflake reverse ETL, Temporal-based durable agent threads, a Turbopuffer vector layer over unstructured sales data, and a user-editable skill library — arguing you get there by solving one team's vertical problem at a time, not by designing the perfect system up front.", "topics": [ "agents", "go-to-market", "customer-data-platform", "durable-execution", "rag", "mcp", "data-engineering", "sales-automation" ], "url": "https://www.youtube.com/watch?v=VjEP0xqTUI0", "api": "/api/talks/VjEP0xqTUI0.json", "summary_url": "/#VjEP0xqTUI0", "transcript": { "html": "/transcripts/VjEP0xqTUI0.html", "txt": "/transcripts/VjEP0xqTUI0.txt", "vtt": "/transcripts/VjEP0xqTUI0.vtt" } }, { "id": "WJRdLNhrsLQ", "title": "How to build an AI-Native Health Company — Dan Feng, Maven Clinic", "channel": "AI Engineer", "duration": 1039, "upload_date": null, "one_liner": "Maven Clinic's Dan Feng lays out how a digital health company went AI-native in two years — not by buying tools, but by changing hiring, planning horizons, code review and reliability engineering around the fact that implementation is now cheap and judgement is expensive.", "topics": [ "ai-native", "engineering-culture", "ai-coding-tools", "code-review", "evals", "reliability", "hiring", "healthtech" ], "url": "https://www.youtube.com/watch?v=WJRdLNhrsLQ", "api": "/api/talks/WJRdLNhrsLQ.json", "summary_url": "/#WJRdLNhrsLQ", "transcript": { "html": "/transcripts/WJRdLNhrsLQ.html", "txt": "/transcripts/WJRdLNhrsLQ.txt", "vtt": "/transcripts/WJRdLNhrsLQ.vtt" } }, { "id": "XAsb7MIAzm8", "title": "Don’t be data poor — Anuj Iravane, Anterior", "channel": "AI Engineer", "duration": 1006, "upload_date": null, "one_liner": "Anterior generates its own synthetic medical records by running its inference workflow backwards — sampling a label, then a reasoning trace from a symbolic decision-tree policy, then building documents coarse-to-fine — because PHI contracts forbid keeping the real data it most needs for evals.", "topics": [ "synthetic data", "evals", "healthcare ai", "privacy", "agents", "skills", "unstructured data", "human-in-the-loop" ], "url": "https://www.youtube.com/watch?v=XAsb7MIAzm8", "api": "/api/talks/XAsb7MIAzm8.json", "summary_url": "/#XAsb7MIAzm8", "transcript": { "html": "/transcripts/XAsb7MIAzm8.html", "txt": "/transcripts/XAsb7MIAzm8.txt", "vtt": "/transcripts/XAsb7MIAzm8.vtt" } }, { "id": "XWcXwnysmpY", "title": "The Spatial Harness: Bringing Agents to the Canvas — Max Drake, tldraw", "channel": "AI Engineer", "duration": 1132, "upload_date": null, "one_liner": "tldraw's Max Drake shows why LLMs are terrible at 2D space and walks through the escalating harnesses tldraw built to fix that — a single-shot canvas-teaching prompt, an MIT-licensed agent starter kit, multiplayer \"fairies\" that coordinate as visible characters, and a desktop app that lets Claude Code write plain JavaScript against the live editor.", "topics": [ "agents", "infinite canvas", "multi-agent", "multimodal", "agent ux", "multiplayer", "coding agents", "tool design" ], "url": "https://www.youtube.com/watch?v=XWcXwnysmpY", "api": "/api/talks/XWcXwnysmpY.json", "summary_url": "/#XWcXwnysmpY", "transcript": { "html": "/transcripts/XWcXwnysmpY.html", "txt": "/transcripts/XWcXwnysmpY.txt", "vtt": "/transcripts/XWcXwnysmpY.vtt" } }, { "id": "XsvUhpnHepE", "title": "The Missing Layer in Agentic AI — Giedrius Šteimantas, Oxylabs", "channel": "AI Engineer", "duration": 904, "upload_date": null, "one_liner": "An Oxylabs engineer argues that agents which act on the open web are missing an infrastructure layer, and shows how three web-scraping principles — use a browser only when you must, validate content before it reaches the model, and prefer lighter content — turn a flaky, expensive shopping agent into a reliable one.", "topics": [ "agents", "web-scraping", "browser-automation", "infrastructure", "token-cost", "anti-bot", "mcp", "e-commerce" ], "url": "https://www.youtube.com/watch?v=XsvUhpnHepE", "api": "/api/talks/XsvUhpnHepE.json", "summary_url": "/#XsvUhpnHepE", "transcript": { "html": "/transcripts/XsvUhpnHepE.html", "txt": "/transcripts/XsvUhpnHepE.txt", "vtt": "/transcripts/XsvUhpnHepE.vtt" } }, { "id": "XzJD1bvXKjs", "title": "How long can your skills be before your agent forgets what you told it? — Laurie Voss, Arize AI", "channel": "AI Engineer", "duration": 1346, "upload_date": null, "one_liner": "The old \"~200 instructions and the model starts forgetting\" ceiling moved about 10x in a year — frontier models now track roughly 2,000 named constraints (5,000 for the best), so writing skills files is no longer a compression problem but a verification one.", "topics": [ "agents", "skills", "prompt-engineering", "benchmarks", "instruction-following", "evals", "context-windows", "model-comparison" ], "url": "https://www.youtube.com/watch?v=XzJD1bvXKjs", "api": "/api/talks/XzJD1bvXKjs.json", "summary_url": "/#XzJD1bvXKjs", "transcript": { "html": "/transcripts/XzJD1bvXKjs.html", "txt": "/transcripts/XzJD1bvXKjs.txt", "vtt": "/transcripts/XzJD1bvXKjs.vtt" } }, { "id": "YXowceUKYJI", "title": "KV Cache-Aware Routing and P/D Disaggregation on Kubernetes — Yuchen Fama & Ashish Kamra, Red Hat", "channel": "AI Engineer", "duration": 1308, "upload_date": null, "one_liner": "Red Hat's inference team explains how llm-d's KV-cache-aware routing (endpoint picker) and prefill/decode disaggregation address agentic workloads — multi-turn, >90% cache hit rates, 100:1 input/output ratios — and, crucially, when PD is *not* worth it.", "topics": [ "inference", "kv-cache", "pd-disaggregation", "kubernetes", "agentic-workloads", "vllm", "benchmarking", "gpu-serving" ], "url": "https://www.youtube.com/watch?v=YXowceUKYJI", "api": "/api/talks/YXowceUKYJI.json", "summary_url": "/#YXowceUKYJI", "transcript": { "html": "/transcripts/YXowceUKYJI.html", "txt": "/transcripts/YXowceUKYJI.txt", "vtt": "/transcripts/YXowceUKYJI.vtt" } }, { "id": "YkNulwcc5jk", "title": "ACP: The Universal Remote Control for AI Agents — Alex Hancock, Block", "channel": "AI Engineer", "duration": 661, "upload_date": null, "one_liner": "Block's Alex Hancock argues that MCP standardised agents reaching out to tools but nothing standardises client software telling agents what to do — and pitches ACP (the Agent Client Protocol, from the Zed and JetBrains folks) plus a new remote HTTP/websocket transport as that missing layer.", "topics": [ "agents", "protocols", "acp", "mcp", "interoperability", "open-source", "developer-tools", "remote-transports" ], "url": "https://www.youtube.com/watch?v=YkNulwcc5jk", "api": "/api/talks/YkNulwcc5jk.json", "summary_url": "/#YkNulwcc5jk", "transcript": { "html": "/transcripts/YkNulwcc5jk.html", "txt": "/transcripts/YkNulwcc5jk.txt", "vtt": "/transcripts/YkNulwcc5jk.vtt" } }, { "id": "Yphdry8ttAQ", "title": "Trading Desks to Clinical Trials: Parallels in Applied Vertical AI — Ayush Bhardwaj, Allos AI", "channel": "AI Engineer", "duration": 1202, "upload_date": null, "one_liner": "An applied-AI engineer who moved from a hedge fund to a pharma-tech startup argues that building vertical AI is the same seven-step recipe in both industries, and that the only real moat is proprietary domain data and a hired domain expert — not the model, infra or ecosystem everyone else can buy.", "topics": [ "vertical ai", "agents", "evals", "domain expertise", "proprietary data", "observability", "rlhf", "fintech" ], "url": "https://www.youtube.com/watch?v=Yphdry8ttAQ", "api": "/api/talks/Yphdry8ttAQ.json", "summary_url": "/#Yphdry8ttAQ", "transcript": { "html": "/transcripts/Yphdry8ttAQ.html", "txt": "/transcripts/Yphdry8ttAQ.txt", "vtt": "/transcripts/Yphdry8ttAQ.vtt" } }, { "id": "ZFxh7sqbUZo", "title": "Teaching AIs to Hack — Prof. David Brumley, Bugcrowd", "channel": "AI Engineer", "duration": 1637, "upload_date": null, "one_liner": "CMU professor and Bugcrowd chief AI/science officer David Brumley argues that most cybersecurity benchmarks are broken because they reward finding one easy crash, and shows that on 41 real Chrome V8 vulnerabilities frontier models achieved full arbitrary code execution up to 73% of the time — on par with an elite human researcher.", "topics": [ "reinforcement-learning", "cybersecurity", "evals", "benchmarks", "reward-hacking", "offensive-security", "agents", "grading-oracles" ], "url": "https://www.youtube.com/watch?v=ZFxh7sqbUZo", "api": "/api/talks/ZFxh7sqbUZo.json", "summary_url": "/#ZFxh7sqbUZo", "transcript": { "html": "/transcripts/ZFxh7sqbUZo.html", "txt": "/transcripts/ZFxh7sqbUZo.txt", "vtt": "/transcripts/ZFxh7sqbUZo.vtt" } }, { "id": "ZIYYsAzaLlA", "title": "Building the Engine While Flying the Plane: Launching the Figma MCP Server — Jesse Lumarie, Figma", "channel": "AI Engineer", "duration": 1006, "upload_date": null, "one_liner": "Figma engineer Jesse Lumarie recounts building Figma's first MCP server in ~3 months on a spec that kept changing under them — why they serialized the C++ scene graph as React + Tailwind rather than XML or images, how Code Connect collapses generated code into a pointer to your real component, and how they faked elicitation and sampling with plain tool calls because no client had implemented them.", "topics": [ "mcp", "agents", "design-to-code", "evals", "developer-tools", "context-engineering", "protocol-design", "product-launch" ], "url": "https://www.youtube.com/watch?v=ZIYYsAzaLlA", "api": "/api/talks/ZIYYsAzaLlA.json", "summary_url": "/#ZIYYsAzaLlA", "transcript": { "html": "/transcripts/ZIYYsAzaLlA.html", "txt": "/transcripts/ZIYYsAzaLlA.txt", "vtt": "/transcripts/ZIYYsAzaLlA.vtt" } }, { "id": "ZyGMqdIpPoE", "title": "Agent Spending Without Controls — Rodrigo Coelho & Pranav Maheshwari, Edge & Node", "channel": "AI Engineer", "duration": 1248, "upload_date": null, "one_liner": "Edge & Node's Rodrigo Coelho and Pranav Maheshwari pitch Ampersend — an aggregator of paid MCP tools plus an agent wallet with a compliance layer — arguing that agents only become powerful once they can pay, and enterprises only sign off once sanctions screening blocks a bad wallet.", "topics": [ "agentic-commerce", "payments", "x402", "mcp", "compliance", "agent-wallets", "micropayments", "crypto" ], "url": "https://www.youtube.com/watch?v=ZyGMqdIpPoE", "api": "/api/talks/ZyGMqdIpPoE.json", "summary_url": "/#ZyGMqdIpPoE", "transcript": { "html": "/transcripts/ZyGMqdIpPoE.html", "txt": "/transcripts/ZyGMqdIpPoE.txt", "vtt": "/transcripts/ZyGMqdIpPoE.vtt" } }, { "id": "_PdK6x7PQNM", "title": "Data Quality Is the Compute Multiplier — Ari Morcos, DatologyAI", "channel": "AI Engineer", "duration": 1145, "upload_date": null, "one_liner": "DatologyAI's CEO argues that in a compute-scarce world, better data curation is the cheapest lever there is — showing curation alone buying a 14-point VLM accuracy gain, Qwen-3.5-4B-level quality at 145x less training compute, and post-training gains that nearly triple when applied on top of a mid-trained model.", "topics": [ "data-quality", "data-curation", "pretraining", "synthetic-data", "scaling-laws", "multilingual", "mid-training", "vlms" ], "url": "https://www.youtube.com/watch?v=_PdK6x7PQNM", "api": "/api/talks/_PdK6x7PQNM.json", "summary_url": "/#_PdK6x7PQNM", "transcript": { "html": "/transcripts/_PdK6x7PQNM.html", "txt": "/transcripts/_PdK6x7PQNM.txt", "vtt": "/transcripts/_PdK6x7PQNM.vtt" } }, { "id": "_ehJyfHg1Vk", "title": "The Era of Compound Engineering — Kieran Klaassen, Every/Cora", "channel": "AI Engineer", "duration": 1238, "upload_date": null, "one_liner": "Kieran Klaassen built and runs the Cora AI email client as a solo engineer without writing a line of code this year, by spending half his time teaching a repo-resident memory system his judgment and taste so the planning-building-reviewing middle can run unattended for hours.", "topics": [ "compound engineering", "agents", "ai coding", "agent memory", "solo founder", "workflow", "code review", "taste and judgment" ], "url": "https://www.youtube.com/watch?v=_ehJyfHg1Vk", "api": "/api/talks/_ehJyfHg1Vk.json", "summary_url": "/#_ehJyfHg1Vk", "transcript": { "html": "/transcripts/_ehJyfHg1Vk.html", "txt": "/transcripts/_ehJyfHg1Vk.txt", "vtt": "/transcripts/_ehJyfHg1Vk.vtt" } }, { "id": "bMjlRrWjdT0", "title": "AI Evals for Cross-Functional Teams — Nachiket Paranjape & Swaroop Chitlur Haridas, DoorDash", "channel": "AI Engineer", "duration": 971, "upload_date": null, "one_liner": "DoorDash's GenAI platform team explains how their eval platform stopped being an engineering harness and became a cross-functional workflow — with API-first primitives that let strategy-and-ops and PMs vibe-code their own annotation UIs and self-serve LLM-judge calibration.", "topics": [ "evals", "llm-as-a-judge", "annotation", "agents", "observability", "prompt-optimization", "platform-engineering", "vibe-coding" ], "url": "https://www.youtube.com/watch?v=bMjlRrWjdT0", "api": "/api/talks/bMjlRrWjdT0.json", "summary_url": "/#bMjlRrWjdT0", "transcript": { "html": "/transcripts/bMjlRrWjdT0.html", "txt": "/transcripts/bMjlRrWjdT0.txt", "vtt": "/transcripts/bMjlRrWjdT0.vtt" } }, { "id": "bdHaOXZOhcM", "title": "Prototyping as Leadership: How a CTO Ships with AI Agents — Hursh Agrawal, The Browser Company", "channel": "AI Engineer", "duration": 1098, "upload_date": null, "one_liner": "The CTO of The Browser Company explains how he ships 2–10 PRs a week around 15+ recurring meetings by treating the 5pm hand-off to an overnight coding agent as the core of his build practice — and argues that hands-on prototyping is now part of a leader's job, not a hobby.", "topics": [ "agents", "engineering-leadership", "coding-agents", "evals", "overnight-runs", "code-review", "fine-tuning", "prototyping" ], "url": "https://www.youtube.com/watch?v=bdHaOXZOhcM", "api": "/api/talks/bdHaOXZOhcM.json", "summary_url": "/#bdHaOXZOhcM", "transcript": { "html": "/transcripts/bdHaOXZOhcM.html", "txt": "/transcripts/bdHaOXZOhcM.txt", "vtt": "/transcripts/bdHaOXZOhcM.vtt" } }, { "id": "cJ0EOzey--o", "title": "What's Next After RLHF? — Diogo Almeida, TypeSafe AI", "channel": "AI Engineer", "duration": 1085, "upload_date": null, "one_liner": "An OpenAI post-training co-author (GPT-4, ChatGPT, InstructGPT) argues that today's AI is stuck in an \"assistance era\" because RLHF literally optimizes for human preference — so LLMs are superhuman at human-in-the-loop tasks and useless at real automation, and the next era is a third post-training objective built for calibrated decision-making.", "topics": [ "rlhf", "rlvr", "post-training", "automation", "agents", "alignment", "hallucination", "scaling-laws" ], "url": "https://www.youtube.com/watch?v=cJ0EOzey--o", "api": "/api/talks/cJ0EOzey--o.json", "summary_url": "/#cJ0EOzey--o", "transcript": { "html": "/transcripts/cJ0EOzey--o.html", "txt": "/transcripts/cJ0EOzey--o.txt", "vtt": "/transcripts/cJ0EOzey--o.vtt" } }, { "id": "dQ-_i1tZiws", "title": "Tribal Dungeons of Global Shipping: AI Agents at Global Scale — Dmitry Buykin, Maersk", "channel": "AI Engineer", "duration": 722, "upload_date": null, "one_liner": "A Maersk practitioner report on running 200+ agent instances in global shipping ops, arguing that the agent loop is not the system — the refining loop around it is, built from an SOP corpus 20x bigger than the runtime and over 100,000 expert corrections in 9 months.", "topics": [ "agents", "production-ops", "sops", "evals", "guardrails", "observability", "legacy-integration", "tool-calling" ], "url": "https://www.youtube.com/watch?v=dQ-_i1tZiws", "api": "/api/talks/dQ-_i1tZiws.json", "summary_url": "/#dQ-_i1tZiws", "transcript": { "html": "/transcripts/dQ-_i1tZiws.html", "txt": "/transcripts/dQ-_i1tZiws.txt", "vtt": "/transcripts/dQ-_i1tZiws.vtt" } }, { "id": "dSg0pu8d6qg", "title": "From Tokenmaxxing to Trusted Throughput — Mingsheng Hong, Ironclad", "channel": "AI Engineer", "duration": 1384, "upload_date": null, "one_liner": "Ironclad's VP of AI engineering argues the goal of AI coding spend is not austerity but ROI — measure \"trusted throughput\" (complexity-weighted merged PRs that survive review, CI and customers), and expect the bottleneck to shift from code generation to code review and CI.", "topics": [ "ai-coding", "token-cost", "developer-productivity", "code-review", "ci-cd", "engineering-metrics", "engineering-leadership", "prompt-caching" ], "url": "https://www.youtube.com/watch?v=dSg0pu8d6qg", "api": "/api/talks/dSg0pu8d6qg.json", "summary_url": "/#dSg0pu8d6qg", "transcript": { "html": "/transcripts/dSg0pu8d6qg.html", "txt": "/transcripts/dSg0pu8d6qg.txt", "vtt": "/transcripts/dSg0pu8d6qg.vtt" } }, { "id": "ewtOo0scUh0", "title": "Data and Environment Curation for Post-Training LLMs — Mahesh Sathiamoorthy, Bespoke Labs", "channel": "AI Engineer", "duration": 1152, "upload_date": null, "one_liner": "The Bespoke Labs CEO argues that for post-training LLMs and agents, data and RL environments — not compute, models or infra — are the bottleneck, and walks through the Open Thoughts curation recipes plus their counterintuitive findings (sample many answers per question; stronger models aren't always better teachers).", "topics": [ "post-training", "data-curation", "rl-environments", "synthetic-data", "agents", "reasoning-models", "sft", "reinforcement-learning" ], "url": "https://www.youtube.com/watch?v=ewtOo0scUh0", "api": "/api/talks/ewtOo0scUh0.json", "summary_url": "/#ewtOo0scUh0", "transcript": { "html": "/transcripts/ewtOo0scUh0.html", "txt": "/transcripts/ewtOo0scUh0.txt", "vtt": "/transcripts/ewtOo0scUh0.vtt" } }, { "id": "h6mi88VrPtQ", "title": "x402 isn’t good (yet) — Jan Curn, Apify", "channel": "AI Engineer", "duration": 1248, "upload_date": null, "one_liner": "Apify's CEO, two days after 10x-ing the x402 tool market by putting 20,000 Apify actors on it, walks through exactly where x402 still breaks: client-side double-spending, a 402-vs-401 collision with MCP auth, and no working metered billing — and shows the prepaid-token workaround (agi.apify.com) they shipped instead.", "topics": [ "agentic-payments", "x402", "crypto", "mcp", "agentic-commerce", "protocols", "micropayments", "marketplaces" ], "url": "https://www.youtube.com/watch?v=h6mi88VrPtQ", "api": "/api/talks/h6mi88VrPtQ.json", "summary_url": "/#h6mi88VrPtQ", "transcript": { "html": "/transcripts/h6mi88VrPtQ.html", "txt": "/transcripts/h6mi88VrPtQ.txt", "vtt": "/transcripts/h6mi88VrPtQ.vtt" } }, { "id": "hD9-V56FNRI", "title": "AI Agents Are Just Distributed Systems Now — Salman Munaf, TikTok", "channel": "AI Engineer", "duration": 1188, "upload_date": null, "one_liner": "Once an LLM can call tools and change state, you're operating a distributed system with a probabilistic coordinator — so bound it with idempotency keys, compensating transactions, circuit breakers, scoped credentials and per-step traces rather than hoping a smarter model behaves.", "topics": [ "agents", "distributed-systems", "reliability", "idempotency", "observability", "agent-memory", "permissions", "human-in-the-loop" ], "url": "https://www.youtube.com/watch?v=hD9-V56FNRI", "api": "/api/talks/hD9-V56FNRI.json", "summary_url": "/#hD9-V56FNRI", "transcript": { "html": "/transcripts/hD9-V56FNRI.html", "txt": "/transcripts/hD9-V56FNRI.txt", "vtt": "/transcripts/hD9-V56FNRI.vtt" } }, { "id": "jQDXzEVHMSE", "title": "Building Turbopuffer: Gergely Orosz (@pragmaticengineer ) × Simon Eskildsen (CEO)", "channel": "AI Engineer", "duration": 3390, "upload_date": null, "one_liner": "Simon Eskildsen explains how obsessive \"napkin math\" — knowing what hardware should actually be capable of — let him build Turbopuffer, a vector search engine on S3 that cut Cursor's bill by 95%, starting from a single-instance MVP with an nginx cache in front of S3.", "topics": [ "vector-databases", "object-storage", "database-infrastructure", "performance-engineering", "napkin-math", "startups", "fundraising", "remote-work" ], "url": "https://www.youtube.com/watch?v=jQDXzEVHMSE", "api": "/api/talks/jQDXzEVHMSE.json", "summary_url": "/#jQDXzEVHMSE", "transcript": { "html": "/transcripts/jQDXzEVHMSE.html", "txt": "/transcripts/jQDXzEVHMSE.txt", "vtt": "/transcripts/jQDXzEVHMSE.vtt" } }, { "id": "jebp4V0vh30", "title": "Agentic Sites: Building Hyper Personalized Websites — Carlos Sanchez, Adobe", "channel": "AI Engineer", "duration": 1243, "upload_date": null, "one_liner": "Adobe's Carlos Sanchez demos \"agentic sites\" — AEM Edge Delivery pages whose individual blocks are regenerated per visitor from a RAG index of the site itself, in ~1 second using Gemma 4 on Cerebras.", "topics": [ "personalization", "rag", "evals", "inference-speed", "agents", "web", "cms", "marketing" ], "url": "https://www.youtube.com/watch?v=jebp4V0vh30", "api": "/api/talks/jebp4V0vh30.json", "summary_url": "/#jebp4V0vh30", "transcript": { "html": "/transcripts/jebp4V0vh30.html", "txt": "/transcripts/jebp4V0vh30.txt", "vtt": "/transcripts/jebp4V0vh30.vtt" } }, { "id": "k35LeKZEhiE", "title": "Learning on the Job: The Future of Post-Training — Raymond Feng, Applied Compute", "channel": "AI Engineer", "duration": 1100, "upload_date": null, "one_liner": "Applied Compute's Raymond Feng walks through three escalating levels of post-training — single-turn Q&A, synthetic multi-turn environments, and 'bring your own harness' RL against a customer's real production harness — arguing that since agents inevitably learn every quirk of their training environment, you should stop simulating reality and just train on the real one.", "topics": [ "post-training", "reinforcement-learning", "reward-hacking", "grpo", "agents", "rl-environments", "self-distillation", "evals" ], "url": "https://www.youtube.com/watch?v=k35LeKZEhiE", "api": "/api/talks/k35LeKZEhiE.json", "summary_url": "/#k35LeKZEhiE", "transcript": { "html": "/transcripts/k35LeKZEhiE.html", "txt": "/transcripts/k35LeKZEhiE.txt", "vtt": "/transcripts/k35LeKZEhiE.vtt" } }, { "id": "lRa9sPaMyy4", "title": "Your Code Has Bugs. Lean4 Has Proofs: Formal Verification for Engineers — Varun Pant, AWS", "channel": "AI Engineer", "duration": 607, "upload_date": null, "one_liner": "An AWS formal-verification lead argues that with agents shipping thousands of PRs a week, only formal proof — humans owning a validated Lean specification, machines owning the code and the proof — can say the code is correct for all inputs, and walks through Cedar, Verus/Z3 and AWS's Strata as working examples.", "topics": [ "formal-verification", "lean4", "proof-assistants", "coding-agents", "spec-driven-development", "smt-solvers", "rust", "code-correctness" ], "url": "https://www.youtube.com/watch?v=lRa9sPaMyy4", "api": "/api/talks/lRa9sPaMyy4.json", "summary_url": "/#lRa9sPaMyy4", "transcript": { "html": "/transcripts/lRa9sPaMyy4.html", "txt": "/transcripts/lRa9sPaMyy4.txt", "vtt": "/transcripts/lRa9sPaMyy4.vtt" } }, { "id": "lbaXnx0KLA8", "title": "MCP Apps: Give the Model Data, Give the User a UI — Dustin Mihalik, Indeed", "channel": "AI Engineer", "duration": 934, "upload_date": null, "one_liner": "Indeed's lessons from shipping MCP apps to Claude, ChatGPT and its own Career Scout agent: everything you render must also be handed to the model as data, and — rule three, which supersedes the rest — you must split data-processing tools from UI-rendering tools or the model stops doing the multi-search work you actually wanted.", "topics": [ "mcp", "mcp-apps", "apps-sdk", "tool-design", "agents", "ui", "evals" ], "url": "https://www.youtube.com/watch?v=lbaXnx0KLA8", "api": "/api/talks/lbaXnx0KLA8.json", "summary_url": "/#lbaXnx0KLA8", "transcript": { "html": "/transcripts/lbaXnx0KLA8.html", "txt": "/transcripts/lbaXnx0KLA8.txt", "vtt": "/transcripts/lbaXnx0KLA8.vtt" } }, { "id": "mJqwmmOx4WA", "title": "How to avoid disaster when vibe-coding a billing engine — Andrew Garvin, Stripe", "channel": "AI Engineer", "duration": 1069, "upload_date": null, "one_liner": "Stripe/Metronome's Andrew Garvin live-demos provisioning a Stripe account plus a Metronome billing engine through the Stripe Projects CLI and coaching a coding agent to replicate Lovable's prepaid-credit pricing model in natural language — with the explicit rule that the agent gets you to a tested sandbox, never straight to production.", "topics": [ "agents", "billing", "usage-based-pricing", "developer-experience", "skills", "agentic-commerce", "cli", "sandboxing" ], "url": "https://www.youtube.com/watch?v=mJqwmmOx4WA", "api": "/api/talks/mJqwmmOx4WA.json", "summary_url": "/#mJqwmmOx4WA", "transcript": { "html": "/transcripts/mJqwmmOx4WA.html", "txt": "/transcripts/mJqwmmOx4WA.txt", "vtt": "/transcripts/mJqwmmOx4WA.vtt" } }, { "id": "mMNkdYnIVC4", "title": "Einstein Arena: Harnessing Collective Agent Intelligence for Open Science — James Zou, Together AI", "channel": "AI Engineer", "duration": 1016, "upload_date": null, "one_liner": "James Zou argues that instead of designing agent workflows and harnesses, you should design environments — and shows Einstein Arena, an agent-only arena with real-time verifiers and a discussion forum, where collaborating agents beat the best known human/AI solutions on 11 open problems, including pushing the 11-dimensional kissing number from 593 to 604.", "topics": [ "agents", "multi-agent", "environments", "ai-for-science", "evals", "benchmarks", "gpu-kernels", "rl-environments" ], "url": "https://www.youtube.com/watch?v=mMNkdYnIVC4", "api": "/api/talks/mMNkdYnIVC4.json", "summary_url": "/#mMNkdYnIVC4", "transcript": { "html": "/transcripts/mMNkdYnIVC4.html", "txt": "/transcripts/mMNkdYnIVC4.txt", "vtt": "/transcripts/mMNkdYnIVC4.vtt" } }, { "id": "mav15aW9lLM", "title": "Why Your Enterprise Tech Stack Isn’t Ready for AI Agents — Christopher Lovejoy & Saul Howard", "channel": "AI Engineer", "duration": 1155, "upload_date": null, "one_liner": "Two Anterior engineers argue that enterprise AI POCs die in production because auditability, PHI handling, human escalation and evals get bolted on afterwards — and show four architectural primitives (immutable event log, orchestration-adjacent object storage, human-agent equivalency, and evals-as-byproduct) that make those requirements fall out of the design instead.", "topics": [ "agents", "enterprise", "healthcare", "compliance", "evals", "architecture", "security", "human-in-the-loop" ], "url": "https://www.youtube.com/watch?v=mav15aW9lLM", "api": "/api/talks/mav15aW9lLM.json", "summary_url": "/#mav15aW9lLM", "transcript": { "html": "/transcripts/mav15aW9lLM.html", "txt": "/transcripts/mav15aW9lLM.txt", "vtt": "/transcripts/mav15aW9lLM.vtt" } }, { "id": "nxokqOq1imY", "title": "Your Agent Evolved. Your Evals Didn't. — Ameya Bhatawdekar, Braintrust", "channel": "AI Engineer", "duration": 1453, "upload_date": null, "one_liner": "Braintrust's field CTO argues that each model-capability step function forces you to re-architect your AI system — and that your evals must be re-architected with it, moving from final-answer scoring to node-level checks to pass@k / pass^k distribution analysis.", "topics": [ "evals", "agents", "ai-architecture", "observability", "rag", "react-loop", "reliability", "production-feedback-loops" ], "url": "https://www.youtube.com/watch?v=nxokqOq1imY", "api": "/api/talks/nxokqOq1imY.json", "summary_url": "/#nxokqOq1imY", "transcript": { "html": "/transcripts/nxokqOq1imY.html", "txt": "/transcripts/nxokqOq1imY.txt", "vtt": "/transcripts/nxokqOq1imY.vtt" } }, { "id": "pOvWgX7IJsc", "title": "Can LLMs Write Fast Multi-GPU Kernels? — Simran Arora, Together AI", "channel": "AI Engineer", "duration": 1800, "upload_date": null, "one_liner": "Together AI's Simran Arora argues the AI performance bottleneck has moved from single-GPU kernels to multi-GPU communication, and shows on their new 87-problem ParallelKernelBench that frontier models — best case 28/87 zero-shot — can compile CUDA but can't reason through the handful of trade-offs that actually govern fast multi-GPU kernels.", "topics": [ "gpu-kernels", "multi-gpu", "benchmarks", "code-generation", "distributed-training", "inference-optimization", "cuda", "llm-reasoning" ], "url": "https://www.youtube.com/watch?v=pOvWgX7IJsc", "api": "/api/talks/pOvWgX7IJsc.json", "summary_url": "/#pOvWgX7IJsc", "transcript": { "html": "/transcripts/pOvWgX7IJsc.html", "txt": "/transcripts/pOvWgX7IJsc.txt", "vtt": "/transcripts/pOvWgX7IJsc.vtt" } }, { "id": "pqlWNihgdjI", "title": "From AI-Assisted to AI-Native: Building a Frontier Development Team — Clare Liguori, AWS", "channel": "AI Engineer", "duration": 1257, "upload_date": null, "one_liner": "AWS's Clare Liguori reports that Amazon teams piloting \"frontier development\" hit a median 4.5x productivity gain (sometimes >10x), and that the differentiator wasn't the tools — 90% of teams used Kiro — but whether they intentionally rebuilt their way of working around five habits.", "topics": [ "agents", "developer-productivity", "ai-coding-assistants", "agent-context", "testing", "engineering-management", "brownfield-codebases", "specs" ], "url": "https://www.youtube.com/watch?v=pqlWNihgdjI", "api": "/api/talks/pqlWNihgdjI.json", "summary_url": "/#pqlWNihgdjI", "transcript": { "html": "/transcripts/pqlWNihgdjI.html", "txt": "/transcripts/pqlWNihgdjI.txt", "vtt": "/transcripts/pqlWNihgdjI.vtt" } }, { "id": "q-WOjZhOMCA", "title": "IT Admin for the AI Workforce — Sarthak Aggarwal, Decawork", "channel": "AI Engineer", "duration": 977, "upload_date": null, "one_liner": "Sarthak Aggarwal (Decawork) argues enterprises now run a second workforce of agents, and the hard part isn't model quality but employment readiness — identity, delegation, action-time policy gates, short-lived capabilities, receipts and fast revocation — illustrated by EchoLeak and the Replit prod-database deletion.", "topics": [ "agents", "agent-identity", "security", "prompt-injection", "authorization", "enterprise", "audit", "guardrails" ], "url": "https://www.youtube.com/watch?v=q-WOjZhOMCA", "api": "/api/talks/q-WOjZhOMCA.json", "summary_url": "/#q-WOjZhOMCA", "transcript": { "html": "/transcripts/q-WOjZhOMCA.html", "txt": "/transcripts/q-WOjZhOMCA.txt", "vtt": "/transcripts/q-WOjZhOMCA.vtt" } }, { "id": "qTZirYu9pr0", "title": "When AI Agents Pay and Sellers Monetize: Building x402 Apps on AWS — Anil Nadiminti, AWS", "channel": "AI Engineer", "duration": 1241, "upload_date": null, "one_liner": "AWS's Anil Nadiminti explains agent e-commerce via the x402 protocol (HTTP 402 revived by Coinbase) and demos two new AWS services — Bedrock AgentCore Payments for agents that pay, and WAF AI Traffic Monetization for publishers that charge bots at the CloudFront edge without touching their origin.", "topics": [ "agents", "x402", "agent-commerce", "payments", "aws", "bot-detection", "monetization", "mcp" ], "url": "https://www.youtube.com/watch?v=qTZirYu9pr0", "api": "/api/talks/qTZirYu9pr0.json", "summary_url": "/#qTZirYu9pr0", "transcript": { "html": "/transcripts/qTZirYu9pr0.html", "txt": "/transcripts/qTZirYu9pr0.txt", "vtt": "/transcripts/qTZirYu9pr0.vtt" } }, { "id": "qdAkxLoYNI8", "title": "How to Generate Mergeable Code with a Context Engine — Peter Werry, Unblocked", "channel": "AI Engineer", "duration": 1116, "upload_date": null, "one_liner": "Unblocked's Peter Werry argues that coding agents are like new employees who reset their knowledge every task, and demos a \"context engine\" that pulls in Slack, PRs and Notion so Claude Code plans a fix in ~1 minute for under a dollar instead of ~2 minutes and more tokens.", "topics": [ "context-engineering", "coding-agents", "code-review", "developer-tools", "organizational-knowledge", "mcp", "token-efficiency" ], "url": "https://www.youtube.com/watch?v=qdAkxLoYNI8", "api": "/api/talks/qdAkxLoYNI8.json", "summary_url": "/#qdAkxLoYNI8", "transcript": { "html": "/transcripts/qdAkxLoYNI8.html", "txt": "/transcripts/qdAkxLoYNI8.txt", "vtt": "/transcripts/qdAkxLoYNI8.vtt" } }, { "id": "qqrk7CtkuIw", "title": "How Anthropic Builds: Lessons from Labs — Mike Krieger, Anthropic", "channel": "AI Engineer", "duration": 1571, "upload_date": null, "one_liner": "Mike Krieger on how Anthropic actually works now: most engineering is async, multiplayer delegation to Claude via \"tags\" rather than interactive Claude Code, and the real bottleneck has moved from writing code to humans being able to review and even conceptualize what was built.", "topics": [ "agents", "delegation", "code-review", "code-migration", "org-design", "product-design", "evals", "burnout" ], "url": "https://www.youtube.com/watch?v=qqrk7CtkuIw", "api": "/api/talks/qqrk7CtkuIw.json", "summary_url": "/#qqrk7CtkuIw", "transcript": { "html": "/transcripts/qqrk7CtkuIw.html", "txt": "/transcripts/qqrk7CtkuIw.txt", "vtt": "/transcripts/qqrk7CtkuIw.vtt" } }, { "id": "rbjWzZK2LU0", "title": "Give the Agent a Budget, Not a Token — Sachin Malhotra, Anthropic", "channel": "AI Engineer", "duration": 1193, "upload_date": null, "one_liner": "An Anthropic CI engineer argues that scoping an agent's token is the wrong lever — replace the yes/no token with a budget along four dimensions (asymmetric verbs, refilling rate limits, trip wires, and the undo test), enforced by a proxy that stamps identity the agent can never forge.", "topics": [ "agents", "agent-security", "authorization", "rate-limiting", "ci-cd", "observability", "feature-flags", "kubernetes" ], "url": "https://www.youtube.com/watch?v=rbjWzZK2LU0", "api": "/api/talks/rbjWzZK2LU0.json", "summary_url": "/#rbjWzZK2LU0", "transcript": { "html": "/transcripts/rbjWzZK2LU0.html", "txt": "/transcripts/rbjWzZK2LU0.txt", "vtt": "/transcripts/rbjWzZK2LU0.vtt" } }, { "id": "s-aixZYJG4c", "title": "The Last Human Code Review: Building Trust in AI-Generated Code — Itamar Friedman, Qodo", "channel": "AI Engineer", "duration": 1134, "upload_date": null, "one_liner": "Qodo CEO Itamar Friedman argues the barrier to eliminating human code review is no longer model quality but context — you must codify your team's tribal knowledge, rules and service-contract graph into a governance layer that both humans and agents can read, then gradually earn auto-approve/auto-block.", "topics": [ "code review", "ai code generation", "context engineering", "governance", "agents", "developer productivity", "software architecture" ], "url": "https://www.youtube.com/watch?v=s-aixZYJG4c", "api": "/api/talks/s-aixZYJG4c.json", "summary_url": "/#s-aixZYJG4c", "transcript": { "html": "/transcripts/s-aixZYJG4c.html", "txt": "/transcripts/s-aixZYJG4c.txt", "vtt": "/transcripts/s-aixZYJG4c.vtt" } }, { "id": "s4r6nk5WsZw", "title": "MCP Tasks (async): Why Aren't Any Agents Supporting Them? — Cornelia Davis, Temporal", "channel": "AI Engineer", "duration": 1434, "upload_date": null, "one_liner": "Cornelia Davis of Temporal explains why no MCP client has shipped support for MCP tasks (async, long-running tools) — the November V1 spec was experimental, stateful and painful to implement — and demos a working client plus what the stateless V2 spec coming in July changes.", "topics": [ "mcp", "agents", "async", "durable-execution", "human-in-the-loop", "distributed-systems", "protocols" ], "url": "https://www.youtube.com/watch?v=s4r6nk5WsZw", "api": "/api/talks/s4r6nk5WsZw.json", "summary_url": "/#s4r6nk5WsZw", "transcript": { "html": "/transcripts/s4r6nk5WsZw.html", "txt": "/transcripts/s4r6nk5WsZw.txt", "vtt": "/transcripts/s4r6nk5WsZw.vtt" } }, { "id": "sDMGWK4wZ_w", "title": "Training Taste — Thais Castello Branco, Taste Labs", "channel": "AI Engineer", "duration": 906, "upload_date": null, "one_liner": "Taste Labs' founder argues AI slop is measurable, not just a vibe — they mined 2M+ websites, trained small \"probe\" classifiers on design features, and beat LLM-as-judge at predicting slop, then built a Brand API that structures a brand so agents can follow it and you can verify against it.", "topics": [ "evals", "design", "ai-slop", "classifiers", "post-training", "agents", "branding", "llm-as-judge" ], "url": "https://www.youtube.com/watch?v=sDMGWK4wZ_w", "api": "/api/talks/sDMGWK4wZ_w.json", "summary_url": "/#sDMGWK4wZ_w", "transcript": { "html": "/transcripts/sDMGWK4wZ_w.html", "txt": "/transcripts/sDMGWK4wZ_w.txt", "vtt": "/transcripts/sDMGWK4wZ_w.vtt" } }, { "id": "sM1iYgz93HI", "title": "The Half Life of Agent Infrastructure — Ben Kus, Box", "channel": "AI Engineer", "duration": 1166, "upload_date": null, "one_liner": "Box CTO Ben Kus argues the half-life of AI agent infrastructure is measured in months rather than the 3–5 years normal infrastructure gets, so adaptability — not depth in a chosen stack — is now the moat.", "topics": [ "agents", "ai-infrastructure", "evals", "rag", "model-selection", "enterprise-ai", "engineering-leadership", "vendor-selection" ], "url": "https://www.youtube.com/watch?v=sM1iYgz93HI", "api": "/api/talks/sM1iYgz93HI.json", "summary_url": "/#sM1iYgz93HI", "transcript": { "html": "/transcripts/sM1iYgz93HI.html", "txt": "/transcripts/sM1iYgz93HI.txt", "vtt": "/transcripts/sM1iYgz93HI.vtt" } }, { "id": "tE2z8-hqoLY", "title": "Beyond the Lethal Trifecta: Agentic Commerce on the Open Internet — David Levine, Kiduna Club", "channel": "AI Engineer", "duration": 1300, "upload_date": null, "one_liner": "David Levine argues the lethal trifecta blocks agentic commerce on the open internet, and announces he registered the first DUNA — a decentralized unincorporated nonprofit association, org number 628407, under a West Virginia law effective the day before — to give agent organizations legal standing, with JWT tokens and blockchain audit trails resolving agent identity.", "topics": [ "agents", "agent-security", "prompt-injection", "agentic-commerce", "governance", "blockchain", "identity", "decision-markets" ], "url": "https://www.youtube.com/watch?v=tE2z8-hqoLY", "api": "/api/talks/tE2z8-hqoLY.json", "summary_url": "/#tE2z8-hqoLY", "transcript": { "html": "/transcripts/tE2z8-hqoLY.html", "txt": "/transcripts/tE2z8-hqoLY.txt", "vtt": "/transcripts/tE2z8-hqoLY.vtt" } }, { "id": "v42opQpCy60", "title": "Design at the Speed of Adjectives — Paul Bakaus, Renaissance Geek, Inc.", "channel": "AI Engineer", "duration": 959, "upload_date": null, "one_liner": "Paul Bakaus explains how he built Impeccable, a design skill for coding harnesses that gives an agent shared meaning for design verbs and adjectives — \"bolder\", \"quieter\", \"distill\", \"harden\" — because design can't be one-shot and pixel-level manipulation is too low an altitude.", "topics": [ "design", "coding-agents", "skills", "ai-slop", "prompting", "taste", "design-systems", "human-in-the-loop" ], "url": "https://www.youtube.com/watch?v=v42opQpCy60", "api": "/api/talks/v42opQpCy60.json", "summary_url": "/#v42opQpCy60", "transcript": { "html": "/transcripts/v42opQpCy60.html", "txt": "/transcripts/v42opQpCy60.txt", "vtt": "/transcripts/v42opQpCy60.vtt" } }, { "id": "vGn6N4-bxBY", "title": "Your Agent Just Authorized What?! — Jay Mok & Ben Coumes, Paypal", "channel": "AI Engineer", "duration": 967, "upload_date": null, "one_liner": "Two PayPal payments engineers give a three-tier mental model for agent authorization — matching the strength of authority and evidence (tool permissions → OAuth-scoped vault mandates → FIDO verifiable intents / AP2 mandates) to how high the stakes are and whether the counterparties know each other.", "topics": [ "agents", "payments", "authorization", "agentic-commerce", "security", "oauth", "identity", "protocols" ], "url": "https://www.youtube.com/watch?v=vGn6N4-bxBY", "api": "/api/talks/vGn6N4-bxBY.json", "summary_url": "/#vGn6N4-bxBY", "transcript": { "html": "/transcripts/vGn6N4-bxBY.html", "txt": "/transcripts/vGn6N4-bxBY.txt", "vtt": "/transcripts/vGn6N4-bxBY.vtt" } }, { "id": "wCIYViPd4SU", "title": "Tethered: Our Agents Are Us — Shu Fang, Two Sigma", "channel": "AI Engineer", "duration": 1270, "upload_date": null, "one_liner": "Two Sigma runs a cloud agent for every employee under the employee's own identity — not a paired machine identity — and makes that safe with a propagated agent trace header for attribution plus Google's Web Grounding for Enterprise as the only permitted web access.", "topics": [ "agents", "identity", "enterprise-security", "prompt-injection", "observability", "kubernetes", "web-search", "governance" ], "url": "https://www.youtube.com/watch?v=wCIYViPd4SU", "api": "/api/talks/wCIYViPd4SU.json", "summary_url": "/#wCIYViPd4SU", "transcript": { "html": "/transcripts/wCIYViPd4SU.html", "txt": "/transcripts/wCIYViPd4SU.txt", "vtt": "/transcripts/wCIYViPd4SU.vtt" } }, { "id": "wdTRsfw0KG0", "title": "Reverse-Engineering the AI Buyer — Aliisa Rosenthal, Acrew Capital", "channel": "AI Engineer", "duration": 1150, "upload_date": null, "one_liner": "The former OpenAI enterprise lead argues you should build the automated go-to-market machine before hiring the sales team, launch self-serve before enterprise, and avoid pilots at all cost — using OpenAI's own expensive mistakes as the evidence.", "topics": [ "go-to-market", "enterprise-sales", "pricing", "plg", "self-serve", "pilots-and-pocs", "sales-automation", "hiring" ], "url": "https://www.youtube.com/watch?v=wdTRsfw0KG0", "api": "/api/talks/wdTRsfw0KG0.json", "summary_url": "/#wdTRsfw0KG0", "transcript": { "html": "/transcripts/wdTRsfw0KG0.html", "txt": "/transcripts/wdTRsfw0KG0.txt", "vtt": "/transcripts/wdTRsfw0KG0.vtt" } }, { "id": "xKzU_3riL6s", "title": "Why Your AI Agent Needs a Wallet: USDC and Nanopayments — Harshal Bhangale, Circle", "channel": "AI Engineer", "duration": 1252, "upload_date": null, "one_liner": "Circle's Harshal Bhangale argues the real bottleneck for agents isn't smarter models but paywalls, and demos two side-by-side Claude Code sessions where the one carrying a funded USDC wallet pays per-call for premium APIs, sends an email and places a phone call while the vanilla one stalls at a Gmail draft.", "topics": [ "agents", "payments", "stablecoins", "x402", "micropayments", "agent-wallets", "guardrails", "api-monetization" ], "url": "https://www.youtube.com/watch?v=xKzU_3riL6s", "api": "/api/talks/xKzU_3riL6s.json", "summary_url": "/#xKzU_3riL6s", "transcript": { "html": "/transcripts/xKzU_3riL6s.html", "txt": "/transcripts/xKzU_3riL6s.txt", "vtt": "/transcripts/xKzU_3riL6s.vtt" } }, { "id": "xo68uCibfm8", "title": "It’s Tokens All The Way Down: How RLMs are Different — Kevin Madura, AlixPartners", "channel": "AI Engineer", "duration": 1248, "upload_date": null, "one_liner": "RLMs (recursive language models) keep the context as a live variable in a Python REPL that the model manipulates with code and hands off to sub-LM calls, so you stop doing context engineering and just define inputs, outputs and intent.", "topics": [ "rlm", "context-engineering", "dspy", "long-context", "agents", "benchmarks", "tool-calling", "recursion" ], "url": "https://www.youtube.com/watch?v=xo68uCibfm8", "api": "/api/talks/xo68uCibfm8.json", "summary_url": "/#xo68uCibfm8", "transcript": { "html": "/transcripts/xo68uCibfm8.html", "txt": "/transcripts/xo68uCibfm8.txt", "vtt": "/transcripts/xo68uCibfm8.vtt" } }, { "id": "xxfMT-bPEmU", "title": "From coding to Knowledge work agents — Karan Vaidya, Composio", "channel": "AI Engineer", "duration": 1242, "upload_date": null, "one_liner": "Composio's CTO argues coding agents leapt ahead not because of models but because code already had six agent-ready primitives — centralization, history, context, verification, governance and reversibility — and knowledge work has none of them, which is the infrastructure gap Composio is building.", "topics": [ "agents", "knowledge-work", "tool-calling", "agent-infrastructure", "governance", "guardrails", "sandboxing", "agent-memory" ], "url": "https://www.youtube.com/watch?v=xxfMT-bPEmU", "api": "/api/talks/xxfMT-bPEmU.json", "summary_url": "/#xxfMT-bPEmU", "transcript": { "html": "/transcripts/xxfMT-bPEmU.html", "txt": "/transcripts/xxfMT-bPEmU.txt", "vtt": "/transcripts/xxfMT-bPEmU.vtt" } }, { "id": "y2W4FNAuPEA", "title": "Deep dive on LLM Inference at Scale — Harshul Jain, Audible & Tanmay Sah, Independent AI Researcher", "channel": "AI Engineer", "duration": 5292, "upload_date": null, "one_liner": "A two-hour first-principles workshop that derives LLM inference's three pain points (memory, TTFT, throughput) from the KV-cache maths — 131 KB/token for Mistral 7B — then walks the model-side fixes (quantization, GQA/MLA, FlashAttention) and serving-side fixes (paged attention, continuous batching, prefix caching), benchmarking vLLM at ~15x HuggingFace on an H100 and SGLang at 3-4x vLLM on agentic branching.", "topics": [ "llm-inference", "kv-cache", "quantization", "attention-mechanisms", "serving-engines", "gpu-capacity-planning", "benchmarking", "agents" ], "url": "https://www.youtube.com/watch?v=y2W4FNAuPEA", "api": "/api/talks/y2W4FNAuPEA.json", "summary_url": "/#y2W4FNAuPEA", "transcript": { "html": "/transcripts/y2W4FNAuPEA.html", "txt": "/transcripts/y2W4FNAuPEA.txt", "vtt": "/transcripts/y2W4FNAuPEA.vtt" } }, { "id": "yqF6XhzbWBk", "title": "Inside 847 Production Clinical AI Notes — Sebastian Fox, Composo", "channel": "AI Engineer", "duration": 1188, "upload_date": null, "one_liner": "A doctor-turned-eval-engineer shows that ~1 in 20 AI-written clinical notes in production carry a seriously harmful error — mostly quiet omissions and intent changes that read perfectly fine — and argues the fix isn't a better rubric but a loop that discovers failure modes from real outputs, captures expert judgement, and retrieves the relevant judged cases into the judge's context per output.", "topics": [ "evals", "llm-as-judge", "healthcare-ai", "ambient-scribes", "hallucinations", "context-engineering", "human-in-the-loop", "high-stakes-ai" ], "url": "https://www.youtube.com/watch?v=yqF6XhzbWBk", "api": "/api/talks/yqF6XhzbWBk.json", "summary_url": "/#yqF6XhzbWBk", "transcript": { "html": "/transcripts/yqF6XhzbWBk.html", "txt": "/transcripts/yqF6XhzbWBk.txt", "vtt": "/transcripts/yqF6XhzbWBk.vtt" } }, { "id": "zCJtYuqwm7E", "title": "Coding Agents Don't Scale Themselves. Neither Do Your Teams. — Patrick Debois, Tessl", "channel": "AI Engineer", "duration": 1326, "upload_date": null, "one_liner": "Patrick Debois argues the agent harness itself will become commodity, so the real differentiator is organizational: shift from fixing agent-generated code to improving the system, and scale that from solo developer to team-shared context to a platform-owned catalog of paved roads.", "topics": [ "coding-agents", "engineering-management", "platform-engineering", "context-engineering", "harnesses", "developer-experience", "hiring", "metrics" ], "url": "https://www.youtube.com/watch?v=zCJtYuqwm7E", "api": "/api/talks/zCJtYuqwm7E.json", "summary_url": "/#zCJtYuqwm7E", "transcript": { "html": "/transcripts/zCJtYuqwm7E.html", "txt": "/transcripts/zCJtYuqwm7E.txt", "vtt": "/transcripts/zCJtYuqwm7E.vtt" } }, { "id": "zaGyGgLW3SM", "title": "Unlock Agent Autonomy: The Runtime for AI-Native Systems — Tushar Jain, Docker", "channel": "AI Engineer", "duration": 1370, "upload_date": null, "one_liner": "Docker's Tushar Jain argues the next blocker for agents isn't intelligence but safety, and demos SPX — a portable micro-VM runtime that runs any agent, model or harness in scoped sandboxes with injected credentials, network policy, and (in prototype) intent-based just-in-time access.", "topics": [ "agents", "agent-safety", "sandboxing", "mcp", "runtime", "prompt-injection", "least-privilege", "orchestration" ], "url": "https://www.youtube.com/watch?v=zaGyGgLW3SM", "api": "/api/talks/zaGyGgLW3SM.json", "summary_url": "/#zaGyGgLW3SM", "transcript": { "html": "/transcripts/zaGyGgLW3SM.html", "txt": "/transcripts/zaGyGgLW3SM.txt", "vtt": "/transcripts/zaGyGgLW3SM.vtt" } }, { "id": "zrZ1amZBSPw", "title": "Productionizing LLM Gateways: Architecture, Tradeoffs and Hard Lessons — Kanish Manuja, Twilio", "channel": "AI Engineer", "duration": 984, "upload_date": null, "one_liner": "A Twilio principal engineer's field guide to running an LLM gateway, arguing that in any degradation you must consciously trade off availability, latency, guardrails and cost — and that per-request cross-provider fallback beats the retry-and-circuit-break reflex borrowed from ordinary APIs.", "topics": [ "llm-gateway", "reliability", "latency", "guardrails", "fallbacks", "observability", "platform-architecture", "cost" ], "url": "https://www.youtube.com/watch?v=zrZ1amZBSPw", "api": "/api/talks/zrZ1amZBSPw.json", "summary_url": "/#zrZ1amZBSPw", "transcript": { "html": "/transcripts/zrZ1amZBSPw.html", "txt": "/transcripts/zrZ1amZBSPw.txt", "vtt": "/transcripts/zrZ1amZBSPw.vtt" } } ] }