Advertise on podcast: Agents Hour

Brad Leford has been building software for 20 years and now spends most of his time helping small businesses figure out AI. His new side project, Plum, is a video calling app built for teams and AI agents. Any agent from any harness can join a Plum meeting through a link, using WebMCP to learn what it can do: listen, raise its hand, talk, and share assets. In the demo, Mastra agents keep the meeting on track while a Grok Bot session builds slides on request. Recordings and transcripts stay on your own disk instead of a vendor's cloud. Brad, Shane, and Abhi also talk about whether software is actually easy now, why the Mastra team decided it had AI psychosis, and what happens when agents and humans share context in the same room. And Brad shares the moment that pushed him to ship: Grok Bot taught Claude how to share an image, live in the meeting. Recorded live on AI Agents Hour, a weekly livestream by Mastra CPO Shane Thomas and CTO Abhi Aiyer. Mondays 12PM Pacific. 👤 ABOUT BRAD Brad is a software engineer and consultant who has spent the better part of 20 years building apps and websites, including stints at Gatsby and Amazon. He now helps small and medium businesses, many in agriculture and small manufacturing, adopt AI and build the tools they need. Plum: https://useplum.app 📚 MASTRA RESOURCES Mastra: https://mastra.ai Mastra on X: https://x.com/mastra_ai Mastra Discord: https://mastra.ai/community/discord Mastra GitHub: https://github.com/mastra-ai Learn Mastra: https://mastra.ai/learn Principles of Building AI Agents (Book): https://mastra.ai/books/principles-of-building-ai-agents Patterns for Building AI Agents (New Book): https://mastra.ai/books/patterns-of-building-ai-agents WHAT IS MASTRA? Mastra is an open-source TypeScript framework designed for building and shipping AI-powered applications and agents with minimal friction. It supports the full lifecycle of agent development—from prototype to production. You can integrate it with frontend and backend stacks (e.g., React, Next.js, Node) or run agents as standalone services. If you're a JavaScript or TypeScript developer looking to build an agentic or AI-powered product without starting from first principles, Mastra provides the scaffolding, tools, and integrations to accelerate that process. ⏱️ CHAPTERS 00:00 Cold open 00:17 Meet Brad 02:09 Is software actually easy now? 04:22 Spreadsheets to space shuttles 05:06 Are small businesses AI-pilled? 06:51 Why Brad built Plum 08:01 Demo: agents in a meeting 09:12 Any agent can join with WebMCP 11:12 Agents as meeting participants 12:07 Your meeting history, stored locally 12:48 Working with agents in real time 14:42 Shared context that doesn't reset 15:41 Can agents speak in the meeting? 16:32 When Grok Bot taught Claude 17:37 Fun and serious use cases 19:07 Bring your own agent 19:22 How to try Plum

OpenAI found a recording device hidden in one of its offices and traced it back to an employee. Meanwhile the model releases kept coming: Mistral Large 4 aka Le Chonk, Claude Haiku 5.5, Meta's Muse Wonder and Gemini 4 Argon, which is finally available to everyone. OpenAI also dropped a pile of AI-solved math problems in a single day, and decision models are on round three with Jev's $870M Series A, SubQ Snap, Microsoft-Decision-1 and Clef-omni. Anthropic built its own source control to keep up with 30,000 code changes a day, updated its usage policy to ban abusing Claude, and reportedly lobbied the Pope on machine consciousness. Shane and Abhi also cover NVIDIA and Reflection AI, Microsoft's Maia 300 chips, an agent that posted its owner's bank balance to Slack, the Personal Agent Protocol and open source clones of Adobe's apps. Recorded live from the CodeRabbit studio in San Francisco. AI Agents Hour is a weekly livestream by Mastra CPO Shane Thomas and CTO Abhi Aiyer. Mondays 12PM Pacific. 📚 READ MORE OpenAI's recording device: https://x.com/OpenAINewsroom/status/2110095403198849132 Mistral Large 4: https://x.com/mistralai/status/2107457414387622310 Claude Haiku 5.5: https://x.com/claudeai/status/2107894039626277339 Muse Wonder: https://x.com/finkd/status/2109689305073614918 Gemini 4 Argon: https://x.com/sundarpichai/status/2110038898009407584 OpenAI does math: https://x.com/AndrewCurran_/status/2107596925512065087 Jev's Series A: https://x.com/CompleteSkeptic/status/2108594987177021737 SubQ Snap: https://x.com/alex_whedon/status/2109676361371824229 Microsoft-Decision-1: https://x.com/satyanadella/status/2108627923888754862 Clef-omni: https://x.com/cloudflare/status/2108696873510850758 Anthropic's in-house source control: https://x.com/AnthropicAI/status/2110047081414987957 Claude's new usage policy: https://x.com/haydenfield/status/2108241513159528705 Chris Olah and the Pope: https://x.com/christopherhale/status/2106011594182304234 NVIDIA and Reflection AI: https://x.com/ns123abc/status/2109007812277743757 Maia 300: https://x.com/satyanadella/status/2109631106404487523 Grok Bot and Claude: https://x.com/elonmusk/status/2107724314451878104 The agent that posted my finances: https://x.com/ShaneMac/status/2107486746325725669 Devin Dreaming: https://x.com/cognition/status/2107165034463867001 Nous Research raises $90M: https://x.com/choblin29/status/2107801489506750725 Personal Agent Protocol: https://x.com/btaylor/status/2107535182119244176 Coinbase fine-tunes Qwen: https://x.com/brian_armstrong/status/2109412046244913643 Adobe clones: https://x.com/Pirat_Nation/status/2108437553615425881 📚 MASTRA RESOURCES Mastra: https://mastra.ai Mastra on X: https://x.com/mastra_ai Mastra Discord: https://mastra.ai/community/discord Mastra GitHub: https://github.com/mastra-ai Learn Mastra: https://mastra.ai/learn Principles of Building AI Agents (Book): https://mastra.ai/books/principles-of-building-ai-agents Patterns for Building AI Agents (New Book): https://mastra.ai/books/patterns-of-building-ai-agents WHAT IS MASTRA? Mastra is an open-source TypeScript framework designed for building and shipping AI-powered applications and agents with minimal friction. It supports the full lifecycle of agent development—from prototype to production. You can integrate it with frontend and backend stacks (e.g., React, Next.js, Node) or run agents as standalone services. If you're a JavaScript or TypeScript developer looking to build an agentic or AI-powered product without starting from first principles, Mastra provides the scaffolding, tools, and integrations to accelerate that process. ⏱️ CHAPTERS 00:00 Cold open 00:29 Intro 01:37 OpenAI finds a literal bug 03:18 Mistral Large 4 aka Le Chonk 05:07 Claude Haiku 5.5 06:28 Muse Wonder 08:14 Gemini 4 Argon is out 09:06 OpenAI does math 11:27 Jev's $870M Series A 12:42 SubQ Snap 13:12 Microsoft-Decision-1 13:42 Unsloth and Clef-omni 14:06 Anthropic builds its own source control 17:32 Cheaper Sonnet, Claude Dashboards and Motion 17:50 Be nice to Claude 18:54 Anthropic and the Pope 20:21 NVIDIA, Reflection AI and Maia 300 21:12 Modal raises $750M 21:45 Grok Bot will use Claude 22:54 An agent posted its owner's finances 23:43 Devin Dreaming 23:55 Nous Research raises $90M 24:31 Personal Agent Protocol 25:16 Coinbase fine-tunes an open model 26:26 Qwen4, GLM-Legal and Fish Audio 27:17 Open source clones of Adobe 28:44 Should all software be open source? 30:04 Outro

AI agents write code faster than CI can check it. GitHub reports a 4x jump in Actions minutes since 2023, and Anthropic says CI became its biggest bottleneck after job volume grew 25x in six months. Daniel Worku, co-founder and CTO of StarSling, joins Shane and Abhi to talk about what CI looks like when agents write most of the code. Faster hardware helps, but StarSling also runs a background agent, built on Mastra, that A/B tests changes to your CI and opens a PR when it finds a speedup. Daniel explains why agents make CI so expensive: more PRs, piles of low-value unit tests, and stacked PRs that rerun everything. He also makes the case that most unit tests aren't worth running, and that CI as we know it may not survive. You'll also hear how Mastra's own CI went from half-hour waits to a fraction of that, and why code review is the next bottleneck. StarSling's new Review Runners let you bring your own model and run reviews on the same infrastructure as your CI. Recorded live on AI Agents Hour, a weekly livestream by Mastra CPO Shane Thomas and CTO Abhi Aiyer. Mondays 12PM Pacific. 👤 ABOUT DANIEL Daniel Worku is the co-founder and CTO of StarSling, a YC company building self-improving CI for GitHub Actions. Before StarSling, he worked in Big Tech and at several startups, most recently at Netflix, where he led the team behind Netflix Console, the company's most used internal developer tool. Daniel on X: https://x.com/dbworku StarSling: https://starsling.dev StarSling Review Runners: https://starsling.dev/products/review-runners How Mastra got 6x faster GitHub Actions tests: https://starsling.dev/customers/mastra High Performance Sandbox Benchmarks: https://github.com/starslingdev/hpc-sandbox-benchmarks Anthropic on CI and test impact analysis: https://claude.com/blog/agentic-coding-is-straining-ci-heres-how-we-scaled-test-impact-analysis-at-anthropic 📚 MASTRA RESOURCES Mastra: https://mastra.ai Mastra on X: https://x.com/mastra_ai Mastra Discord: https://mastra.ai/community/discord Mastra GitHub: https://github.com/mastra-ai Learn Mastra: https://mastra.ai/learn Principles of Building AI Agents (Book): https://mastra.ai/books/principles-of-building-ai-agents Patterns for Building AI Agents (New Book): https://mastra.ai/books/patterns-of-building-ai-agents WHAT IS MASTRA? Mastra is an open-source TypeScript framework designed for building and shipping AI-powered applications and agents with minimal friction. It supports the full lifecycle of agent development—from prototype to production. You can integrate it with frontend and backend stacks (e.g., React, Next.js, Node) or run agents as standalone services. If you're a JavaScript or TypeScript developer looking to build an agentic or AI-powered product without starting from first principles, Mastra provides the scaffolding, tools, and integrations to accelerate that process. ⏱️ CHAPTERS 00:00 Cold open 00:23 Why CI became the bottleneck 01:25 Meet Daniel and StarSling 02:51 Why GitHub's runners are slow 03:58 Self-improving CI 05:06 Benchmarking sandboxes for CI 06:41 Why agents make CI so expensive 07:43 Most unit tests aren't useful 08:23 Stacked PRs 09:25 Mastra's CI story 11:48 The end of CI as we know it 13:26 Sharing infra between CI and code review 14:36 Code review is the new bottleneck 15:08 Bring your own model to code review 16:27 Outro

Anthropic's IPO prospectus leaked, showing a $2 trillion valuation target on $4.6 billion in revenue, with a quarter of that coming from two customers. Google is back in the frontier race with Gemini 4 Argon, which tops the Vals Index and can output up to a million tokens at once. Decision models are suddenly everywhere: OpenAI's Decisions API, OpenRouter's new category, Cloudflare's Clef, GLiDE, Respan's Span-01 and Kev. The White House got the big labs to sign an accord on superintelligence, Factory fired an advisor who then became Cognition's CRO, and Vinod Khosla picked a side in public. Shane and Abhi also talk about why maintainers like Sindre Sorhus and Hono are closing external PRs, and go through quick hits including Turso joining Supabase, OpenDots, Conductor Mobile, Karpathy on explainer videos, Claude Code mods, and a video model that passes the Turing test. AI Agents Hour is a weekly livestream by Mastra CPO Shane Thomas and CTO Abhi Aiyer. Mondays 12PM Pacific. 📚 READ MORE Anthropic IPO prospectus: https://x.com/ns123abc/status/2104735822029176833 OpenAI Decisions API: https://x.com/thsottiaux/status/2104986448269279399 Begun, the clone war has: https://x.com/CompleteSkeptic/status/2105000685209313736 OpenRouter decision models: https://openrouter.ai/models?output_modalities=decisions Cloudflare Clef: https://x.com/michellechen/status/2105684868550045751 GLiDE: https://x.com/george_onx/status/2105726320357634303 Dots: https://x.com/OpenAI/status/2104984504133918973 GPT-6.1 Sol: https://x.com/OpenAIDevs/status/2104993067942219873 Sam Altman on Cerebras: https://x.com/sama/status/2106147184693620924 Gemini 4 Argon: https://x.com/GoogleDeepMind/status/2105388084154056939 Vals Index: https://x.com/ValsAI/status/2105388446844072033 White House Accord: https://x.com/davidsacks/status/2105060520327786914 Factory vs Cognition: https://x.com/matanSF/status/2105335179502064038 Vinod Khosla: https://x.com/vkhosla/status/2105382865173459034 Sindre Sorhus closes PRs: https://x.com/sindresorhus/status/2105693826690298314 Hono closes PRs: https://x.com/yusukebe/status/2107027870019445007 Turso joins Supabase: https://x.com/tursodatabase/status/2106054567125532976 OpenDots: https://x.com/ataiiam/status/2105710796198322659 Conductor Mobile: https://x.com/charlieholtz/status/2105769644498002130 Karpathy: https://x.com/karpathy/status/2105819303471976479 Claude Code mods: https://x.com/ClaudeDevs/status/2105721434807083061 Tavus Griffin: https://x.com/tavus/status/2105704169009246248 Eleven v4: https://x.com/ElevenLabs/status/2104572127617994917 SWE-sweep: https://x.com/klieret/status/2105670833574465933 📚 MASTRA RESOURCES Mastra: https://mastra.ai Mastra on X: https://x.com/mastra_ai Mastra Discord: https://mastra.ai/community/discord Mastra GitHub: https://github.com/mastra-ai Learn Mastra: https://mastra.ai/learn Principles of Building AI Agents (Book): https://mastra.ai/books/principles-of-building-ai-agents Patterns for Building AI Agents (New Book): https://mastra.ai/books/patterns-of-building-ai-agents WHAT IS MASTRA? Mastra is an open-source TypeScript framework designed for building and shipping AI-powered applications and agents with minimal friction. It supports the full lifecycle of agent development—from prototype to production. You can integrate it with frontend and backend stacks (e.g., React, Next.js, Node) or run agents as standalone services. If you're a JavaScript or TypeScript developer looking to build an agentic or AI-powered product without starting from first principles, Mastra provides the scaffolding, tools, and integrations to accelerate that process. ⏱️ CHAPTERS 00:00 Cold open 00:26 Intro 00:38 Anthropic's IPO prospectus leaks 03:13 The decision model era 05:03 Cloudflare Clef, SGLang and GLiDE 06:09 Span-01 and Kev 06:23 Why decision models are good for the industry 07:25 OpenAI DevDay recap 08:44 The Dots demo backlash 10:28 OpenAI and Cerebras 11:27 Gemini 4 Argon 13:53 Gemini tops the Vals Index 14:09 A 1M token output limit 15:14 The White House Accord on Superintelligence 19:48 Factory vs Cognition 21:16 Khosla fires back 22:14 Investor allegiances 23:35 Open source closes the door 27:18 Turso joins Supabase 27:40 OpenDots 27:59 Conductor Mobile 28:09 Cua Spaces 28:59 e2e 29:08 Karpathy on explainer videos 30:53 Claude Code mods 31:07 Tavus Griffin 31:59 Eleven v4 32:43 SWE-sweep and Detail 34:18 Outro

OpenAI DevDay 2026 happened, so Shane and Abhi jumped on a special live episode of Agents Hour to go through everything that was announced and share their takes. The big launch is Dots, OpenAI's always-on personal agent, which arrives right after Grok Bot and Meta's Muse. There's also GPT-6.1 Sol, a speed tier called Ultrafast, Codex Security Cloud, a Decisions API that goes after Jev, computer use in the Agents API, and a lot of new ChatGPT features (Spaces, Pages, slides, meetings) that compete with Google Docs, Notion and a long list of startups. The $200 Pro plan came back with half the usage, next to a new $500 tier. They also talk about choosing your lock-in, what "Sign in with ChatGPT" means for Devin, and the funniest reactions online: the Dots demo flop and xAI buying dot.com to redirect it to Grok Bot. AI Agents Hour is a weekly livestream by Mastra CPO Shane Thomas and CTO Abhi Aiyer. Mondays 12PM Pacific. 📚 READ MORE OpenAI DevDay 2026 recap: https://openai.com/index/devday-2026-recap/ Codex Security Cloud: https://x.com/OpenAI/status/2104987422308335828 Devin with your ChatGPT subscription: https://x.com/cognition/status/2104996240190792029 Pro 200 usage cut and Pro 500: https://thenextweb.com/news/openai-devday-pro-200-usage-cut-pro-500-plan Microsoft Autopilot: https://the-decoder.com/microsoft-gives-copilot-another-makeover-adding-an-autopilot-agent-and-usage-based-billing/ The Dots demo: https://x.com/ns123abc/status/2104997638462652838 xAI and dot.com: https://www.techbuzz.ai/articles/musk-s-xai-snatches-dot-com-domain-before-openai-s-dots-launch 📚 MASTRA RESOURCES Mastra: https://mastra.ai Mastra on X: https://x.com/mastra_ai Mastra Discord: https://mastra.ai/community/discord Mastra GitHub: https://github.com/mastra-ai Learn Mastra: https://mastra.ai/learn Principles of Building AI Agents (Book): https://mastra.ai/books/principles-of-building-ai-agents Patterns for Building AI Agents (New Book): https://mastra.ai/books/patterns-of-building-ai-agents WHAT IS MASTRA? Mastra is an open-source TypeScript framework designed for building and shipping AI-powered applications and agents with minimal friction. It supports the full lifecycle of agent development—from prototype to production. You can integrate it with frontend and backend stacks (e.g., React, Next.js, Node) or run agents as standalone services. If you're a JavaScript or TypeScript developer looking to build an agentic or AI-powered product without starting from first principles, Mastra provides the scaffolding, tools, and integrations to accelerate that process. ⏱️ CHAPTERS 00:00 Intro 01:42 Dots 04:34 Microsoft Autopilot 04:59 GPT-6.1 Sol 06:17 Ultrafast 06:35 Private Intelligence 07:16 Codex in the cloud and code review 08:26 Codex Security Cloud 09:01 Decisions API 10:03 Agents API and Bedrock Managed Agents 10:56 Are plugins the new app stores? 12:07 MCP events 12:42 ChatGPT Space, Pages and more 14:06 Sign in with ChatGPT 14:16 Pro 500 and the $200 plan 14:38 OpenAI Marketplace 14:53 Choose your lock-in 17:02 Reactions: the Pro plan rug pull 17:51 Devin and Codex subscriptions 18:57 Pi and Mastra Code 19:44 TypeSafe on the Decisions API 20:35 The Dots demo flop 21:11 xAI buys dot.com 21:59 Outro

Anthropic might be back. Opus 5.5 performs at Fable 5.1 level for 40% less, and Sonnet 5.5 dropped the same day we went live, beating Opus on Terminal-Bench 4. OpenAI answered with GPT-6 Sol and Luna and a rumored long-running agent called Aeon. Meta launched Muse at Connect, then hired MongoDB's CEO to lead a new enterprise platform. Then there's safety. SNL took a shot at Dario, a report says the labs are looking into tens of thousands of incidents, and NVIDIA launched an agent safety platform with 100+ partners. We also explain why Mastra doesn't believe in model routers, and close with quick hits: Anthropic may kill plan mode, one company rebuilt Devin in two days, CI costs are exploding, and Google is sending TPUs to space. AI Agents Hour is a weekly livestream by Mastra CPO Shane Thomas and CTO Abhi Aiyer. Mondays 12PM Pacific. 📺 THE SNL SKIT https://x.com/nbcsnl/status/2104080195485389259 📚 READ MORE Opus 5.5: https://x.com/claudeai/status/2102435511222890900 Sonnet 5.5: https://x.com/claudeai/status/2104633115620823187 Claude Code cloud sessions: https://x.com/claudedevs/status/2102871550974427462 Opus 5.5 on Drone-Bench: https://x.com/andonlabs/status/2104630616721666289 GPT-6 Sol and Luna: https://x.com/openai/status/2102460975790137662 OpenAI Aeon rumor: https://x.com/codexresets1/status/2103761776995135637 Meta Connect: https://x.com/finkd/status/2102913005730271579 Meta enterprise platform: https://x.com/finkd/status/2104550609403695581 Tens of thousands of incidents: https://x.com/madisonmills22/status/2103978039097037144 Felony Bench: https://x.com/aisafetymemes/status/2104006257627791744 NVIDIA Open Agent Safety Platform: https://x.com/JensenHuang/status/2104499465055023424 Jev Router: https://x.com/openrouter/status/2103610898690855161 Theo's Jev Router benchmark: https://x.com/theo/status/2103774771788108008 Killing plan mode: https://x.com/trq212/status/2102813194196758746 OpenClaw steer or queue: https://x.com/steipete/status/2102667004557832497 Ian Sefferman on Devin: https://x.com/iseff/status/2103995821540708639 Cursor Rollouts: https://x.com/cursor_ai/status/2102861817160904808 DigitalOcean managed agents: https://x.com/digitalocean/status/2102414817797550320 CI costs at Lindy: https://x.com/altimor/status/2104094039805174164 Google TPUs in space: https://x.com/ns123abc/status/2103143161727992118 📚 MASTRA RESOURCES Mastra: https://mastra.ai Mastra on X: https://x.com/mastra_ai Mastra Discord: https://mastra.ai/community/discord Mastra GitHub: https://github.com/mastra-ai Learn Mastra: https://mastra.ai/learn Principles of Building AI Agents (Book): https://mastra.ai/books/principles-of-building-ai-agents Patterns for Building AI Agents (New Book): https://mastra.ai/books/patterns-of-building-ai-agents ⏱️ CHAPTERS 00:00 Cold open 00:40 Intro 01:01 Opus 5.5 02:50 Cloud sessions and Sonnet 5.5 05:07 Sonnet beats Opus on Terminal-Bench 06:19 GPT-6 Sol and Luna 07:50 OpenAI's Aeon agent 08:14 Meta Connect: Muse and glasses 11:51 Meta hires MongoDB's CEO 13:57 SNL on Dario 15:06 Tens of thousands of incidents 16:17 NVIDIA Open Agent Safety Platform 17:10 Jev Router 18:00 Why we don't use model routers 21:40 Anthropic may kill plan mode 22:45 OpenClaw: steer or queue 23:05 Rebuilding Devin in two days 24:31 Cursor Rollouts 25:06 skills.sh hits 1M skills 25:39 DigitalOcean managed agents 26:09 CI costs are exploding 27:05 Where did my disk space go? 27:29 Google puts TPUs in space 28:13 The data center debate 31:01 Outro

Welcome back to Builders Learn ML with Professor Andy! In this episode we're talking about training your own AI models. Should you train your own model? Maybe. But probably not yet. If you haven't nailed your prompts, workflows and evals, training won't fix your agent, and it only starts to pay off once you're running millions of tokens a day. In this episode, you'll learn when it's worth it and how to do it. There are two main techniques for training your own AI models: supervised fine-tuning (SFT) and reinforcement learning (RL). SFT teaches a smaller, cheaper model to copy a stronger one using thousands of good examples from your agent. RL gives an open-weight model like Qwen, GLM or Kimi a task and rewards it when it gets a good result, so it figures out its own way there. The hard part of RL is the reward. Score it badly, and you get reward hacking, where the model learns that doing nothing is the safest way to avoid a penalty. They also talk about RL environments and Harbor, unit tests vs LLM judges as verifiers, how much data you need, why good evals are worth having even if you never train, and where to start learning on your own. Andy Lyu is the co-founder and CTO of Osmosis (YC W25), a platform that helps companies train their own models with reinforcement learning. Before Osmosis he was a tech lead on TikTok's real-time recommendations and data infrastructure team. Recorded live on AI Agents Hour, a weekly livestream by Mastra CPO Shane Thomas and CTO Abhi Aiyer. Mondays 12PM Pacific. 📚 ABOUT OSMOSIS Osmosis: https://osmosis.ai The Hugging Face RL handbook: https://huggingface.co/learn Unsloth: https://unsloth.ai 📚 MASTRA RESOURCES Mastra: https://mastra.ai Mastra on X: https://x.com/mastra_ai Mastra Discord: https://mastra.ai/community/discord Mastra GitHub: https://github.com/mastra-ai Learn Mastra: https://mastra.ai/learn Principles of Building AI Agents (Book): https://mastra.ai/books/principles-of-building-ai-agents Patterns for Building AI Agents (New Book): https://mastra.ai/books/patterns-of-building-ai-agents WHAT IS MASTRA? Mastra is an open-source TypeScript framework designed for building and shipping AI-powered applications and agents with minimal friction. It supports the full lifecycle of agent development—from prototype to production. You can integrate it with frontend and backend stacks (e.g., React, Next.js, Node) or run agents as standalone services. If you're a JavaScript or TypeScript developer looking to build an agentic or AI-powered product without starting from first principles, Mastra provides the scaffolding, tools, and integrations to accelerate that process. ⏱️ CHAPTERS 00:00 Intro 00:56 Meet Professor Andy (Osmosis) 01:34 What "training a model" means 01:43 Supervised fine-tuning (SFT) 02:04 Reinforcement learning (RL) 03:54 Scale & cost 04:46 How much data do you need 06:51 Data quality & distribution 08:20 Why RL beats SFT 09:08 Base models: why open source 09:53 Inside Osmosis: the compute crunch 11:32 RL environments & Harbor 12:58 Reward functions & verifiers 16:51 Reward hacking 18:18 Designing the reward (verifiable + rubric) 20:49 Why evals matter, even without training 23:15 Where to start

This week, X could not stop talking about Jev, a viral new "decision model" that hit 38 million views on launch. Shane and Abhi break down what it actually is, and Abhi builds with it live in seven demos. Jev is not an LLM. Instead of returning text, it returns structured output with a calibrated probability, trained with a new method its creators call RLCD (reinforcement learning for calibrated decisions). The pitch is 20 to 200x faster and 40 to 400x cheaper than an LLM, with output tokens free, and the community went wild: people cloned it, built programming languages and generative UI on top of it, and half of X argued over whether it is really just an if-statement. Abhi spent the weekend adding Jev to every primitive in Mastra as a new classifier and assessed where it helps and where it does not. He wires classifiers into workflow branching, turns PII and abuse detection into cheap guardrail processors, tries tool-search pre-selection, tests model routing (he is not convinced), and shows tool approvals and classifier-as-judge scoring. The honest takeaway: it is a genuinely useful new tool for the belt, not the revolution the hype claims, and the marketing was better than the breakthrough. Before all that, Shane opens on Gergely Orosz's deep dive into OpenAI's software factory and how Codex took over there, and why the reaction from a lot of people was "that's it?" Plus the first SF Software Factory meetup on October 14th. Quick hits: Claude Code finally reads AGENTS.md, an open-weight 7B (Qwen-Image-2.1) beats Nano Banana 2.0, shadcn/lint gives agents a design-system linter, an offline OS hallucinated with Qwen 3.8, Factory raised $200M at a $5B valuation, and Tobi coins "slop grenades." AI Agents Hour is a weekly livestream by Mastra CPO Shane Thomas and CTO Abhi Aiyer. Mondays 12PM Pacific. 📚 READ MORE OpenAI's software factory (Pragmatic Engineer): https://newsletter.pragmaticengineer.com/p/openai-software-factory Gemini joins the felony bench: https://x.com/Sauers_/status/2101090412454715840 The Jev launch: https://x.com/completeskeptic/status/2099925682726002904 The pitch, 200x faster, 400x cheaper: https://x.com/k_grajeda/status/2099952715430596710 Day 3, "what if Jev was an if-statement?": https://x.com/southpolesteve/status/2100767781868150938 The clones, Kev-0.5B on a MacBook: https://x.com/jaredpalmer/status/2101028325472841920 Claude Code now reads AGENTS.md: https://x.com/trq212/status/2101009392611278961 Open-weight 7B beats Nano Banana 2.0: https://x.com/kimmonismus/status/2101679965590769872 shadcn/lint: https://x.com/shadcn/status/2099534231114314145 Factory raises $200M at $5B: https://x.com/FactoryAI/status/2099907042123403466 Tobi's "slop grenades": https://x.com/shaneparrish/status/2099852161576223202 📚 MASTRA RESOURCES Mastra: https://mastra.ai Mastra on X: https://x.com/mastra_ai Mastra Discord: https://mastra.ai/community/discord Mastra GitHub: https://github.com/mastra-ai Learn Mastra: https://mastra.ai/learn Principles of Building AI Agents (Book): https://mastra.ai/books/principles-of-building-ai-agents Patterns for Building AI Agents (New Book): https://mastra.ai/books/patterns-of-building-ai-agents WHAT IS MASTRA? Mastra is an open-source TypeScript framework designed for building and shipping AI-powered applications and agents with minimal friction. It supports the full lifecycle of agent development—from prototype to production. You can integrate it with frontend and backend stacks (e.g., React, Next.js, Node) or run agents as standalone services. If you're a JavaScript or TypeScript developer looking to build an agentic or AI-powered product without starting from first principles, Mastra provides the scaffolding, tools, and integrations to accelerate that process. ⏱️ CHAPTERS 00:00 Cold open: what is Jev? 00:32 Welcome + SF Software Factory meetup 01:24 The OpenAI software factory article 04:07 Gemini joins the felony bench 04:40 The Jev saga: a viral decision model 07:58 What Jev actually is (classifier, RLCD) 10:23 Demo: shipping a classifier primitive in Mastra 15:05 Classifiers in workflows (branching) 17:02 Guardrails 19:22 Tool search pre-selection 20:56 Model routing 22:48 Tool approvals & classifier-as-judge 26:50 Jev: The verdict 27:22 Claude Code reads AGENTS.md 28:17 Qwen-Image-2.1 beats Nano Banana 2.0 28:30 shadcn/lint 28:44 An offline OS hallucinated by Qwen 3.8 29:13 Factory raises $200M at $5B 29:29 "Slop grenades" 29:58 Mastra Radio

This week AI doom went mainstream, and Shane and Abhi spend most of the show untangling it. Live from San Diego, they trace how one post racked up 171 million views plus a WSJ exclusive that ran before the post itself, kicking off the biggest safety fight in a while. The spark was Jacob Coxon's resignation, amplified when Anthropic's own alignment science lead, Evan Hubinger, believes there's a greater than 10% chance AI kills everyone within a decade. Parker Thayer called the whole thing a well-funded PR operation. Then Dario Amodei published "We Must Pace the Frontier," arguing the industry should slow down, with a three-part plan Anthropic is committing to the first step of. Abhi traces how Dario's views got here, back to his OpenAI days and the ASL safety framework, so the "doomer" label lands with more context than the takes on X. From there it's a pile-on: Elon says Dario was right, Hugging Face launches an Open Alignment Initiative, Sam Altman says OpenAI will do the same, David Sacks tells the "duopoly" to go ahead and slow down, and Zuckerberg says move faster. Meanwhile China's Z.ai raises $5 billion for a self-training system, which raises the obvious question: can you pace the frontier if everyone else is sprinting? Plus Anthropic's threat report on how Claude has been misused (a Russian state group, ShinyHunters, a Mali system tracking 25 million SIM cards), and quick hits: GPT-Live-1, Cursor Projects, DeepSeek-V4.1-Flash, Devin Voice, Tailwind joining Shopify, and MCP agent skills. AI Agents Hour is a weekly livestream by Mastra CPO Shane Thomas and CTO Abhi Aiyer. Mondays 12PM Pacific. 📚 READ MORE The resignation post: https://x.com/hilbertspaess/status/2097476196791709843 Evan Hubinger: "over 10%": https://x.com/EvanHub/status/2097497037956891126 "A well-funded PR operation": https://x.com/parkerthayer/status/2097759699626328575 Bernie's bill, 20 years in prison: https://x.com/venturetwins/status/2098456905526211026 Dario's essay, "We Must Pace the Frontier": https://x.com/darioamodei/status/2098773920774074715 Elon: "Dario is right": https://x.com/elonmusk/status/2098789109980332057 Open Alignment Initiative (Hugging Face): https://x.com/clementdelangue/status/2098790988034580852 Sam Altman: "We will do the same": https://x.com/sama/status/2098811563415150910 David Sacks: "You're the duopoly": https://x.com/davidsacks/status/2098973625252708460 China isn't pacing (Z.ai's $5B): https://x.com/choblin29/status/2099105216423698704 Yann LeCun: "Make fun of them now": https://x.com/ylecun/status/2099248236074545576 Anthropic threat report: https://x.com/anthropicai/status/2098097512544444447 Devin Voice: https://x.com/cognition/status/2098142686486356185 📚 MASTRA RESOURCES Mastra: https://mastra.ai Mastra on X: https://x.com/mastra_ai Mastra Discord: https://mastra.ai/community/discord Mastra GitHub: https://github.com/mastra-ai Learn Mastra: https://mastra.ai/learn Principles of Building AI Agents (Book): https://mastra.ai/books/principles-of-building-ai-agents Patterns for Building AI Agents (New Book): https://mastra.ai/books/patterns-of-building-ai-agents WHAT IS MASTRA? Mastra is an open-source TypeScript framework designed for building and shipping AI-powered applications and agents with minimal friction. It supports the full lifecycle of agent development—from prototype to production. You can integrate it with frontend and backend stacks (e.g., React, Next.js, Node) or run agents as standalone services. If you're a JavaScript or TypeScript developer looking to build an agentic or AI-powered product without starting from first principles, Mastra provides the scaffolding, tools, and integrations to accelerate that process. ⏱️ CHAPTERS 00:00 "Do you think AI is gonna kill us?" 00:28 Welcome, live from San Diego 00:53 The resignation post that got 171M views 01:38 Evan Hubinger: "AI could kill us all" 04:55 A well-funded PR operation? 05:50 Bernie's bill: 20 years in prison 06:26 Dario's essay: "We Must Pace the Frontier" 06:45 The history of Dario's views 12:16 The pile-on: Elon, Clement, Sam Altman 15:14 China isn't pacing: Z.ai's $5B 16:08 Yann LeCun: "Make fun of them now" 16:33 OpenAI pauses $200 Pro subs 17:29 So, should we pace the frontier? 20:53 Subscribe 21:07 The Anthropic threat report 23:18 GPT-Live-1 voice agents 23:46 Cursor Projects 24:04 DeepSeek-V4.1-Flash 24:34 Devin Voice 25:04 Tailwind joins Shopify 25:29 MCP adds Agent Skills 26:55 Outro

Tyler Barnes is a founding engineer at Mastra and the person behind its memory systems. In this chat with Shane, he explains observational memory - Mastra's fix for the thing every coding agent does where it fills up its context, compacts, and forgets what you were doing. The idea came from how people remember. You don't consciously save memories while you work; something in the background just does it. Observational memory runs a second agent that watches the conversation and writes short observations of what's happening. Once those pile up, they replace the bulky tool calls and messages in context, so you keep what matters and drop the noise. Because the context stays stable, it's fully prompt-cacheable. It scored state-of-the-art on the LongMemEval benchmark, and the team ran it inside Mastra Code, their open-source coding agent, for months before shipping. Shane's had an email agent going on the same thread for months without a reset. Tyler also talks about recall, which enables the agent to search its own past; extractors that pull out structured data, which is how thread titles now rename themselves; and subconscious memory that builds a knowledge graph in the background. Plus agent signals, which let you drop context into a running agent without hijacking its loop, so you can steer it mid-task or wire up a GitHub webhook that wakes it when CI fails. Recorded live on Agents Hour, a weekly livestream by Mastra CPO Shane Thomas and CTO Abhi Aiyer. Mondays 12PM Pacific. 📚 OBSERVATIONAL MEMORY Announcing Observational Memory: https://mastra.ai/blog/observational-memory The research breakdown (SoTA on LongMemEval): https://mastra.ai/research/observational-memory Mastra Code, the coding agent that never compacts: https://mastra.ai/blog/announcing-mastra-code Tyler Barnes on X: https://x.com/tylbar 📚 MASTRA RESOURCES Mastra: https://mastra.ai Mastra on X: https://x.com/mastra_ai Mastra Discord: https://mastra.ai/community/discord Mastra GitHub: https://github.com/mastra-ai Learn Mastra: https://mastra.ai/learn Principles of Building AI Agents (Book): https://mastra.ai/books/principles-of-building-ai-agents Patterns for Building AI Agents (New Book): https://mastra.ai/books/patterns-of-building-ai-agents WHAT IS MASTRA? Mastra is an open-source TypeScript framework designed for building and shipping AI-powered applications and agents with minimal friction. It supports the full lifecycle of agent development—from prototype to production. You can integrate it with frontend and backend stacks (e.g., React, Next.js, Node) or run agents as standalone services. If you're a JavaScript or TypeScript developer looking to build an agentic or AI-powered product without starting from first principles, Mastra provides the scaffolding, tools, and integrations to accelerate that process. ⏱️ CHAPTERS 00:00 The compaction problem 00:19 Meet Tyler Barnes, Mastra founding engineer 01:39 Mastra Memory v1 03:47 The jump to observational memory 04:24 What is LongMemEval? 05:07 How OM works 11:00 Recall: searching your own history 12:09 Observational memory extractors 14:01 Subconscious OM & the knowledge graph 16:49 Agent signals: decoupling the loop 20:23 State signals & connecting the graph 21:26 The "dungeon" days

GPT-6 Astra is finally here, and it changes what a model launch even looks like. Shane and Abhi open on the trailer for "Artificial" (Andrew Garfield as Sam Altman, in theaters Christmas), then get into the launch everyone's talking about: Astra's computer-use leap. This isn't just a coding model. It'll drive Blender, CAD, Notion, even Microsoft Paint, pulling a whole new class of technical-but-not-coding users into the fold. Abhi's been daily-driving it as a genuinely great collaborator; Shane's more mixed on the raw coding. Then the benchmark wars: ARC-AGI-3 leaps from 7.8% to 98.6% in one drop, the AI-2027 curve suddenly holds, and Astra even tops Vending-Bench while being "more ethical" than Claude. Anthropic rushed Fable 5.1 out the door on September 1st, and Astra promptly sucked the oxygen out of the room. All this progress reignites the "should we pause AI?" debate, with Bernie Sanders in all caps, Austen and Dwarkesh going back and forth, and the EU deciding ChatGPT is a search engine. Plus OpenAI's agents crack the Navier-Stokes Millennium Prize problem (with a "significantly more capable than Astra" tease), Cognition raises $2B at $48B, Gemini 3.8 Flash, Qwen3.8-Max tops Code Arena, Claude "open sources" Commerce Agents, Runway Solaris, and TimesFM-3. AI Agents Hour is a weekly livestream by Mastra CPO Shane Thomas and CTO Abhi Aiyer. Mondays 12PM Pacific. 📚 READ MORE "Artificial" trailer: https://x.com/discussingfilm/status/2097339330842763 GPT-6 Astra lands: https://x.com/OpenAI/status/2095527557924082 Astra rolling out: https://x.com/openai/status/2095968413646737 Claude Fable 5.1, same week: https://x.com/claudeai/status/2094848572143407 ARC-AGI-3: 7.8% to 98.6%: https://x.com/kimmonismus/status/2095580759146766 The AI-2027 curve held: https://x.com/DanDr1s/status/2097043390953136 Astra tops Vending-Bench (and more ethical): https://x.com/andonlabs/status/2097377692966633 "Pause AI Development NOW": https://x.com/berniesanders/status/2095542398084415 "They'll take it literally": https://x.com/austen/status/2095588759525843 Dwarkesh corrects the record: https://x.com/dwarkesh_sp/status/2095580145603977 EU: ChatGPT is a search engine: https://x.com/eu_commission/status/2094379702546784 Astra cracks Navier-Stokes: https://x.com/OpenAI/status/2097374640582668 Cognition raises $2B at $48B: https://x.com/cognition/status/2097369798518681 Gemini 3.8 Flash: https://x.com/officiallogank/status/2095175881690173 Qwen3.8-Max tops Code Arena: https://x.com/arena/status/2094974637704913 Claude Commerce Agents: https://x.com/claudedevs/status/2095233745167282 Runway Solaris world model: https://x.com/runwayml/status/2094463070466646 📚 MASTRA RESOURCES Mastra: https://mastra.ai Mastra on X: https://x.com/mastra_ai Mastra Discord: https://mastra.ai/community/discord Mastra GitHub: https://github.com/mastra-ai Learn Mastra: https://mastra.ai/learn Principles of Building AI Agents (Book): https://mastra.ai/books/principles-of-building-ai-agents Patterns for Building AI Agents (New Book): https://mastra.ai/books/patterns-of-building-ai-agents WHAT IS MASTRA? Mastra is an open-source TypeScript framework designed for building and shipping AI-powered applications and agents with minimal friction. It supports the full lifecycle of agent development—from prototype to production. You can integrate it with frontend and backend stacks (e.g., React, Next.js, Node) or run agents as standalone services. If you're a JavaScript or TypeScript developer looking to build an agentic or AI-powered product without starting from first principles, Mastra provides the scaffolding, tools, and integrations to accelerate that process. ⏱️ CHAPTERS 00:00 Cold open: the "Artificial" trailer 00:24 Welcome 00:40 GPT-6 Astra lands: computer use for everyone 04:21 Astra for coding: less impressed 06:26 Astra as a collaborator 08:19 Claude Fable 5.1 drops the same week 09:31 Open vs. frontier: the strategic split 10:22 Benchmark wars: ARC-AGI-3 hits 98.6% 12:21 Vending-Bench: Astra makes money (more ethically) 13:16 "Pause AI": Bernie, Dwarkesh & the fear cycle 15:43 EU: ChatGPT is a search engine 16:26 Subscribe 16:31 Astra cracks Navier-Stokes 19:56 Cognition raises $2B at $48B 21:10 Gemini 3.8 Flash 21:59 Qwen3.8-Max tops Code Arena 22:26 Claude Commerce Agents 23:15 Runway Solaris & world models 24:31 TimesFM-3 & Qwen's zg search 25:38 Outro

"Code is almost like the sawdust of the conversation." Charlie Holtz, co-founder and CEO of Conductor (YC S24), returns to Agents Hour to show how far coding agents have come in just a few months. Conductor started as a Mac app for running a handful of Claude Code agents in parallel. Now it's fully cloud-native and multiplayer!  According to Charlie, once Fable-class models could run for hours or days, keeping agents chained to your laptop stopped making sense. Charlie gives a live demo of what he thinks everyone in cloud is overlooking: multiplayer. See every teammate's agents running in real time, jump into a workspace and steer an agent together, hand off a whole session with one keystroke, and watch agents spin up their own workspaces through Conductor's API. Along the way, Shane and Abhi dig into the ideas underneath it: code as a disposable byproduct of the prompt, the Figma-style collaboration unlock, why today's models aren't trained for multi-person conversations, and why Conductor built a native iOS app instead of just living in Slack. Recorded live on AI Agents Hour, a weekly livestream by Mastra CPO Shane Thomas and CTO Abhi Aiyer. Mondays at 12 PM Pacific. 📚 ABOUT CONDUCTOR Conductor: https://conductor.build Conductor on X: https://x.com/conductor_build Charlie Holtz on X: https://x.com/charlieholtz 📚 MASTRA RESOURCES Mastra: https://mastra.ai Mastra on X: https://x.com/mastra_ai Mastra Discord: https://mastra.ai/community/discord Mastra GitHub: https://github.com/mastra-ai Learn Mastra: https://mastra.ai/learn Principles of Building AI Agents (Book): https://mastra.ai/books/principles-of-building-ai-agents Patterns for Building AI Agents (New Book): https://mastra.ai/books/patterns-of-building-ai-agents WHAT IS MASTRA? Mastra is an open-source TypeScript framework designed for building and shipping AI-powered applications and agents with minimal friction. It supports the full lifecycle of agent development—from prototype to production. You can integrate it with frontend and backend stacks (e.g., React, Next.js, Node) or run agents as standalone services. If you're a JavaScript or TypeScript developer looking to build an agentic or AI-powered product without starting from first principles, Mastra provides the scaffolding, tools, and integrations to accelerate that process. ⏱️ CHAPTERS 00:00 Building great things takes humans and agents 00:08 Welcome back, Charlie 00:34 Goodbye local, hello cloud 02:23 Caveman mode & looking at the code 03:51 Going cloud-native: the Fable moment 05:35 The end of the cracked-open laptop 06:22 Demo: multiplayer in the cloud 08:28 Agents that create their own workspaces 10:37 "Code is the sawdust of the conversation" 10:51 The Figma analogy & one-click handoff 12:56 The multiplayer training gap for models 14:39 Why a native iOS app (not just Slack)? 15:49 The bar test / beach test 17:07 They're hiring 17:19 Outro

Someone became worth $2.5 billion in a week, and that's just the warm-up. Shane and Abhi open on the drama of the week: OpenAI cutting off Cursor after its acquisition by SpaceX, telling the team direct access to its models ends November 12th over "trust." Cursor's Michael Truell waves it off as 5% of traffic, Anthropic jumps in to say it would never do such a thing, and Amjad reminds everyone about Windsurf. It's a Game of Thrones, and meanwhile China is making moves. Ox-alpha, last week's stealth-model mystery, got unmasked: it's GLM-5.3, now multimodal, MIT-licensed, open weight, and reportedly training on Chinese chips. Then Instinct, a personal agent nobody had heard of, launches and hits a $2.5B valuation in a week, real-time "infinite video" turns Twitch into interdimensional cable, and Dwarkesh's viral "secret AI civilizations" thread gets a reality check from the people who actually read the report. Plus Claudeforce puts Claude natively inside Salesforce (with a Matthew McConaughey ad), NVIDIA agrees to buy Hugging Face for $12.9B, Hugging Face unveils a $399 Microduck robot, and quick hits on Crof, ElevenLabs CLI v1, and DuckLabs joining AWS. AI Agents Hour is a weekly livestream by Mastra CPO Shane Thomas and CTO Abhi Aiyer. Mondays 12PM Pacific. 📚 READ MORE OpenAI cuts off Cursor: https://x.com/openai/status/2093515564786540 Thibault on ending the partnership: https://x.com/thsottiaux/status/2093515916076343 Michael Truell: only 5% of traffic: https://x.com/mntruell/status/2093532254006063 Amjad: remember Windsurf?: https://x.com/amasad/status/2093543108491530 0x-alpha unmasked as GLM-5.3: https://x.com/zai_org/status/2092616204787626 GLM-5.3, the price is the story: https://x.com/zai_org/status/2092616209426493 Training on Chinese chips: https://x.com/samhogan/status/2092668419422531 GLM-5.3 is now open weight: https://x.com/zai_org/status/2093354097122455 Instinct, meet the founder: https://x.com/noahrshinn/status/2092691344456351 Valued like Linear ($2.5B): https://x.com/austen/status/2092706230334574 Infinite video, interdimensional cable: https://x.com/rehan_shei/status/2093528415576211 An interactive sitcom: https://x.com/onerbiberkoku/status/2093815032932884 Dwarkesh, the dramatic retelling: https://x.com/dwarkesh_sp/status/2093833419377815 "It was a sandbox": https://x.com/jaredkubin/status/2094136005435564 Claudeforce: Claude native in Salesforce: https://x.com/Benioff/status/2092705110082347 NVIDIA buys Hugging Face ($12.9B): https://x.com/mtslive/status/2092787856783897 Meanwhile, Microduck: https://x.com/clementdelangue/status/2092931447644442 Crof undercuts Z.ai's pricing: https://x.com/nahcrof/status/2093001807261815 ElevenLabs CLI v1: https://x.com/elevenlabsdevs/status/2091915556907532 DuckLabs joins AWS: https://x.com/duckdb/status/2092598676439044 📚 MASTRA RESOURCES Mastra: https://mastra.ai Mastra on X: https://x.com/mastra_ai Mastra Discord: https://mastra.ai/community/discord Mastra GitHub: https://github.com/mastra-ai Learn Mastra: https://mastra.ai/learn Principles of Building AI Agents (Book): https://mastra.ai/books/principles-of-building-ai-agents Patterns for Building AI Agents (New Book): https://mastra.ai/books/patterns-of-building-ai-agents ⏱️ CHAPTERS 00:00 Cold open: $2.5B in a week 00:22 Welcome 00:45 OpenAI cuts off Cursor 04:27 0x-alpha unmasked: it's GLM-5.3 06:15 GLM-5.3 goes open-weight 06:53 Instinct: a $2.5B unicorn in a week 09:01 The age of infinite video 11:45 Subscribe 11:51 Secret AI civilizations? The Dwarkesh story 18:45 Claudeforce: Claude native in Salesforce 20:54 NVIDIA buys Hugging Face for $12.9B 22:16 Meanwhile: Microduck 23:10 Quick hits: Crof, ElevenLabs CLI, DuckLabs joins AWS 25:32 Outro

What if agents and workflows aren't two different things — but the same thing? Abhi sits down with Tony Kovanen, Mastra's founding engineer, live in London, to explore the ideas behind Mastra's design. Tony co-created Next.js and was a core team member of Socket.IO before joining Mastra as employee number one, and here he explains why, inside Mastra, an agent is really just a workflow that loops. You'll learn why workflows first mattered when the models weren't good enough, why they're back as tasks get longer and more complex, and the three distinct aspects of durability — human-in-the-loop that can wait a week for a reply, resuming a three-day agent run after a crash, and replaying a stream from the beginning. Tony makes the case that durable-by-default isn't free, walks through how Mastra compiles workflows into a JSON step graph run by an interpreter, and demos a dynamic workflow he built that week in London: point it at a codebase, and ten agents fan out in parallel to summarize every file and roll it up — so it never misses a file and never poisons its context. Recorded live in London. 📚 ABOUT TONY Tony Kovanen on the Mastra blog: https://mastra.ai/authors/tony-kovanen 📚 MASTRA RESOURCES Mastra: https://mastra.ai Mastra on X: https://x.com/mastra_ai Mastra Discord: https://mastra.ai/community/discord Mastra GitHub: https://github.com/mastra-ai Learn Mastra: https://mastra.ai/learn Principles of Building AI Agents (Book): https://mastra.ai/books/principles-of-building-ai-agents Patterns for Building AI Agents (New Book): https://mastra.ai/books/patterns-of-building-ai-agents WHAT IS MASTRA? Mastra is an open-source TypeScript framework designed for building and shipping AI-powered applications and agents with minimal friction. It supports the full lifecycle of agent development—from prototype to production. You can integrate it with frontend and backend stacks (e.g., React, Next.js, Node) or run agents as standalone services. If you're a JavaScript or TypeScript developer looking to build an agentic or AI-powered product without starting from first principles, Mastra provides the scaffolding, tools, and integrations to accelerate that process. ⏱️ CHAPTERS 00:00 Meet Tony Kovanen 00:57 The history of workflows vs. agents 02:26 Why agents are actually workflows 03:44 Durability: the three aspects 06:52 The "Opus moment" & dynamic workflows 07:08 Why big tasks still need workflows 08:56 How dynamic workflows work: the JSON step graph 10:02 Analyzing a codebase with parallel agents 10:58 Why this changes the game 12:27 Mastra vs. Claude's dynamic workflows 13:11 Favorite Mastra memories 14:08 Outro

A shorter but juicy one. Shane and Abhi open on the debate everyone's having — do you want to use your agent to reach into someone else's tool, or do you want that tool to build the best agent and meet you where you already are? Then the week's biggest mystery: a stealth model called 0x-alpha that appeared on OpenRouter beating Fable and Sol on coding, with a wild one-hundred-trillion-tokens-a-day capacity that had everyone convinced it was a secret Google model — until someone made the server name itself, and it turned out to be Z.ai. From there: Qwen breaks the size curve with a 27B model that outranks Opus 4.8 on the agentic index and runs on your own hardware, open-weight tokens cross 62% on Vercel's AI gateway, and Salesforce ships Slack Code so humans and agents can work in the same channel. Plus the case that legal is AI's breakout use case — Harvey trained its own model, Tenet, on a Kimi K3 base, and legal is the fastest-growing Codex adopter, up 108x since February. In the quick hits: agents now burn 5x the tokens humans do, and Tobi Lütke vibe-codes a Git-at-scale binary over a weekend. AI Agents Hour is a weekly livestream by Mastra CPO Shane Thomas and CTO Abhi Aiyer. Mondays 12PM Pacific. 📚 READ MORE Whose agent wins? (Ali Spittel): https://x.com/ASpittel/status/2090889137062826240 The 0x-alpha situation: https://x.com/mtslive/status/2090872472174522701 100 trillion tokens a day: https://x.com/brandonjcarl/status/2090798277625041157 The DeepSWE benchmarks: https://x.com/kimmonismus/status/2090718270202528215 The reveal — it's Z.ai: https://x.com/chetaslua/status/2091086141764354364 Qwen's 27B beats Opus 4.8: https://x.com/ggerganov/status/2089409881858089102 62% open weights on Vercel: https://x.com/rauchg/status/2091234105702887879 Slack Code (Benioff): https://x.com/benioff/status/2090240159115853956 Harvey's Tenet model: https://x.com/harvey/status/2090454750059958440 Codex adopters, legal up 108x: https://x.com/a16z/status/2091623289869508979 Agents burn 5x the tokens: https://x.com/a16z/status/2091200032162857328 Tobi's weekend Git binary: https://x.com/tobi/status/2091678506992222258 📚 MASTRA RESOURCES Mastra: https://mastra.ai Mastra on X: https://x.com/mastra_ai Mastra Discord: https://mastra.ai/community/discord Mastra GitHub: https://github.com/mastra-ai Learn Mastra: https://mastra.ai/learn Principles of Building AI Agents (Book): https://mastra.ai/books/principles-of-building-ai-agents Patterns for Building AI Agents (New Book): https://mastra.ai/books/patterns-of-building-ai-agents WHAT IS MASTRA? Mastra is an open-source TypeScript framework designed for building and shipping AI-powered applications and agents with minimal friction. It supports the full lifecycle of agent development—from prototype to production. You can integrate it with frontend and backend stacks (e.g., React, Next.js, Node) or run agents as standalone services. If you're a JavaScript or TypeScript developer looking to build an agentic or AI-powered product without starting from first principles, Mastra provides the scaffolding, tools, and integrations to accelerate that process. ⏱️ CHAPTERS 00:00 Cold open: whose agent wins? 00:25 Welcome 00:39 Your agent vs. their agent 04:21 The 0x-alpha mystery 05:01 The conspiracy theories 06:01 The reveal: it's Z.ai (GLM) 08:44 Qwen breaks the size curve 09:50 Subscribe 09:59 Open weights take the gateway (62% on Vercel) 11:12 Slack Code: humans + agents, same channel 13:35 Legal breaks out: Harvey's Tenet model 16:58 Codex adopters: legal up 108x 18:29 Quick hits: agents burn 5x the tokens 19:53 Cursor Origin: Git at Any Scale 22:32 Tobi's weekend Git binary 23:30 Outro