Agents Hour

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 MOREOpenAI's software factory (Pragmatic Engineer): https://newsletter.pragmaticengineer.com/p/openai-software-factoryGemini joins the felony bench: https://x.com/Sauers_/status/2101090412454715840The Jev launch: https://x.com/completeskeptic/status/2099925682726002904The pitch, 200x faster, 400x cheaper: https://x.com/k_grajeda/status/2099952715430596710Day 3, "what if Jev was an if-statement?": https://x.com/southpolesteve/status/2100767781868150938The clones, Kev-0.5B on a MacBook: https://x.com/jaredpalmer/status/2101028325472841920Claude Code now reads AGENTS.md: https://x.com/trq212/status/2101009392611278961Open-weight 7B beats Nano Banana 2.0: https://x.com/kimmonismus/status/2101679965590769872shadcn/lint: https://x.com/shadcn/status/2099534231114314145Factory raises $200M at $5B: https://x.com/FactoryAI/status/2099907042123403466Tobi's "slop grenades": https://x.com/shaneparrish/status/2099852161576223202
📚 MASTRA RESOURCESMastra: https://mastra.aiMastra on X: https://x.com/mastra_aiMastra Discord: https://mastra.ai/community/discordMastra GitHub: https://github.com/mastra-aiLearn Mastra: https://mastra.ai/learnPrinciples of Building AI Agents (Book): https://mastra.ai/books/principles-of-building-ai-agentsPatterns 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.
⏱️ CHAPTERS00:00 Cold open: what is Jev?00:32 Welcome + SF Software Factory meetup01:24 The OpenAI software factory article04:07 Gemini joins the felony bench04:40 The Jev saga: a viral decision model07:58 What Jev actually is (classifier, RLCD)10:23 Demo: shipping a classifier primitive in Mastra15:05 Classifiers in workflows (branching)17:02 Guardrails19:22 Tool search pre-selection20:56 Model routing22:48 Tool approvals & classifier-as-judge26:50 Jev: The verdict27:22 Claude Code reads AGENTS.md28:17 Qwen-Image-2.1 beats Nano Banana 2.028:30 shadcn/lint28:44 An offline OS hallucinated by Qwen 3.829:13 Factory raises $200M at $5B29:29 "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 MOREThe resignation post: https://x.com/hilbertspaess/status/2097476196791709843Evan Hubinger: "over 10%": https://x.com/EvanHub/status/2097497037956891126"A well-funded PR operation": https://x.com/parkerthayer/status/2097759699626328575Bernie's bill, 20 years in prison: https://x.com/venturetwins/status/2098456905526211026Dario's essay, "We Must Pace the Frontier": https://x.com/darioamodei/status/2098773920774074715Elon: "Dario is right": https://x.com/elonmusk/status/2098789109980332057Open Alignment Initiative (Hugging Face): https://x.com/clementdelangue/status/2098790988034580852Sam Altman: "We will do the same": https://x.com/sama/status/2098811563415150910David Sacks: "You're the duopoly": https://x.com/davidsacks/status/2098973625252708460China isn't pacing (Z.ai's $5B): https://x.com/choblin29/status/2099105216423698704Yann LeCun: "Make fun of them now": https://x.com/ylecun/status/2099248236074545576Anthropic threat report: https://x.com/anthropicai/status/2098097512544444447Devin Voice: https://x.com/cognition/status/2098142686486356185
📚 MASTRA RESOURCESMastra: https://mastra.aiMastra on X: https://x.com/mastra_aiMastra Discord: https://mastra.ai/community/discordMastra GitHub: https://github.com/mastra-aiLearn Mastra: https://mastra.ai/learnPrinciples of Building AI Agents (Book): https://mastra.ai/books/principles-of-building-ai-agentsPatterns 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.
⏱️ CHAPTERS00:00 "Do you think AI is gonna kill us?"00:28 Welcome, live from San Diego00:53 The resignation post that got 171M views01:38 Evan Hubinger: "AI could kill us all"04:55 A well-funded PR operation?05:50 Bernie's bill: 20 years in prison06:26 Dario's essay: "We Must Pace the Frontier"06:45 The history of Dario's views12:16 The pile-on: Elon, Clement, Sam Altman15:14 China isn't pacing: Z.ai's $5B16:08 Yann LeCun: "Make fun of them now"16:33 OpenAI pauses $200 Pro subs17:29 So, should we pace the frontier?20:53 Subscribe21:07 The Anthropic threat report23:18 GPT-Live-1 voice agents23:46 Cursor Projects24:04 DeepSeek-V4.1-Flash24:34 Devin Voice25:04 Tailwind joins Shopify25:29 MCP adds Agent Skills26:55 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 MEMORYAnnouncing Observational Memory: https://mastra.ai/blog/observational-memoryThe research breakdown (SoTA on LongMemEval): https://mastra.ai/research/observational-memoryMastra Code, the coding agent that never compacts: https://mastra.ai/blog/announcing-mastra-codeTyler Barnes on X: https://x.com/tylbar
📚 MASTRA RESOURCESMastra: https://mastra.aiMastra on X: https://x.com/mastra_aiMastra Discord: https://mastra.ai/community/discordMastra GitHub: https://github.com/mastra-aiLearn Mastra: https://mastra.ai/learnPrinciples of Building AI Agents (Book): https://mastra.ai/books/principles-of-building-ai-agentsPatterns 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.
⏱️ CHAPTERS00:00 The compaction problem00:19 Meet Tyler Barnes, Mastra founding engineer01:39 Mastra Memory v103:47 The jump to observational memory04:24 What is LongMemEval?05:07 How OM works11:00 Recall: searching your own history12:09 Observational memory extractors14:01 Subconscious OM & the knowledge graph16:49 Agent signals: decoupling the loop20:23 State signals & connecting the graph21:26 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/2097339330842763GPT-6 Astra lands: https://x.com/OpenAI/status/2095527557924082Astra rolling out: https://x.com/openai/status/2095968413646737Claude Fable 5.1, same week: https://x.com/claudeai/status/2094848572143407ARC-AGI-3: 7.8% to 98.6%: https://x.com/kimmonismus/status/2095580759146766The AI-2027 curve held: https://x.com/DanDr1s/status/2097043390953136Astra 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/2095588759525843Dwarkesh corrects the record: https://x.com/dwarkesh_sp/status/2095580145603977EU: ChatGPT is a search engine: https://x.com/eu_commission/status/2094379702546784Astra cracks Navier-Stokes: https://x.com/OpenAI/status/2097374640582668Cognition raises $2B at $48B: https://x.com/cognition/status/2097369798518681Gemini 3.8 Flash: https://x.com/officiallogank/status/2095175881690173Qwen3.8-Max tops Code Arena: https://x.com/arena/status/2094974637704913Claude Commerce Agents: https://x.com/claudedevs/status/2095233745167282Runway Solaris world model: https://x.com/runwayml/status/2094463070466646
📚 MASTRA RESOURCESMastra: https://mastra.aiMastra on X: https://x.com/mastra_aiMastra Discord: https://mastra.ai/community/discordMastra GitHub: https://github.com/mastra-aiLearn Mastra: https://mastra.ai/learnPrinciples of Building AI Agents (Book): https://mastra.ai/books/principles-of-building-ai-agentsPatterns 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.
⏱️ CHAPTERS00:00 Cold open: the "Artificial" trailer00:24 Welcome00:40 GPT-6 Astra lands: computer use for everyone04:21 Astra for coding: less impressed06:26 Astra as a collaborator08:19 Claude Fable 5.1 drops the same week09:31 Open vs. frontier: the strategic split10:22 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 cycle15:43 EU: ChatGPT is a search engine16:26 Subscribe16:31 Astra cracks Navier-Stokes19:56 Cognition raises $2B at $48B21:10 Gemini 3.8 Flash21:59 Qwen3.8-Max tops Code Arena22:26 Claude Commerce Agents23:15 Runway Solaris & world models24:31 TimesFM-3 & Qwen's zg search25:38 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 CONDUCTORConductor: https://conductor.buildConductor on X: https://x.com/conductor_buildCharlie Holtz on X: https://x.com/charlieholtz
📚 MASTRA RESOURCESMastra: https://mastra.aiMastra on X: https://x.com/mastra_aiMastra Discord: https://mastra.ai/community/discordMastra GitHub: https://github.com/mastra-aiLearn Mastra: https://mastra.ai/learnPrinciples of Building AI Agents (Book): https://mastra.ai/books/principles-of-building-ai-agentsPatterns 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.
⏱️ CHAPTERS00:00 Building great things takes humans and agents00:08 Welcome back, Charlie00:34 Goodbye local, hello cloud02:23 Caveman mode & looking at the code03:51 Going cloud-native: the Fable moment05:35 The end of the cracked-open laptop06:22 Demo: multiplayer in the cloud08:28 Agents that create their own workspaces10:37 "Code is the sawdust of the conversation"10:51 The Figma analogy & one-click handoff12:56 The multiplayer training gap for models14:39 Why a native iOS app (not just Slack)?15:49 The bar test / beach test17:07 They're hiring17:19 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 MOREOpenAI cuts off Cursor: https://x.com/openai/status/2093515564786540Thibault on ending the partnership: https://x.com/thsottiaux/status/2093515916076343Michael Truell: only 5% of traffic: https://x.com/mntruell/status/2093532254006063Amjad: remember Windsurf?: https://x.com/amasad/status/20935431084915300x-alpha unmasked as GLM-5.3: https://x.com/zai_org/status/2092616204787626GLM-5.3, the price is the story: https://x.com/zai_org/status/2092616209426493Training on Chinese chips: https://x.com/samhogan/status/2092668419422531GLM-5.3 is now open weight: https://x.com/zai_org/status/2093354097122455Instinct, meet the founder: https://x.com/noahrshinn/status/2092691344456351Valued like Linear ($2.5B): https://x.com/austen/status/2092706230334574Infinite video, interdimensional cable: https://x.com/rehan_shei/status/2093528415576211An interactive sitcom: https://x.com/onerbiberkoku/status/2093815032932884Dwarkesh, the dramatic retelling: https://x.com/dwarkesh_sp/status/2093833419377815"It was a sandbox": https://x.com/jaredkubin/status/2094136005435564Claudeforce: Claude native in Salesforce: https://x.com/Benioff/status/2092705110082347NVIDIA buys Hugging Face ($12.9B): https://x.com/mtslive/status/2092787856783897Meanwhile, Microduck: https://x.com/clementdelangue/status/2092931447644442Crof undercuts Z.ai's pricing: https://x.com/nahcrof/status/2093001807261815ElevenLabs CLI v1: https://x.com/elevenlabsdevs/status/2091915556907532DuckLabs joins AWS: https://x.com/duckdb/status/2092598676439044
📚 MASTRA RESOURCESMastra: https://mastra.aiMastra on X: https://x.com/mastra_aiMastra Discord: https://mastra.ai/community/discordMastra GitHub: https://github.com/mastra-aiLearn Mastra: https://mastra.ai/learnPrinciples of Building AI Agents (Book): https://mastra.ai/books/principles-of-building-ai-agentsPatterns for Building AI Agents (New Book): https://mastra.ai/books/patterns-of-building-ai-agents
⏱️ CHAPTERS00:00 Cold open: $2.5B in a week00:22 Welcome00:45 OpenAI cuts off Cursor04:27 0x-alpha unmasked: it's GLM-5.306:15 GLM-5.3 goes open-weight06:53 Instinct: a $2.5B unicorn in a week09:01 The age of infinite video11:45 Subscribe11:51 Secret AI civilizations? The Dwarkesh story18:45 Claudeforce: Claude native in Salesforce20:54 NVIDIA buys Hugging Face for $12.9B22:16 Meanwhile: Microduck23:10 Quick hits: Crof, ElevenLabs CLI, DuckLabs joins AWS25:32 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 TONYTony Kovanen on the Mastra blog: https://mastra.ai/authors/tony-kovanen
📚 MASTRA RESOURCESMastra: https://mastra.aiMastra on X: https://x.com/mastra_aiMastra Discord: https://mastra.ai/community/discordMastra GitHub: https://github.com/mastra-aiLearn Mastra: https://mastra.ai/learnPrinciples of Building AI Agents (Book): https://mastra.ai/books/principles-of-building-ai-agentsPatterns 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.
⏱️ CHAPTERS00:00 Meet Tony Kovanen00:57 The history of workflows vs. agents02:26 Why agents are actually workflows03:44 Durability: the three aspects06:52 The "Opus moment" & dynamic workflows07:08 Why big tasks still need workflows08:56 How dynamic workflows work: the JSON step graph10:02 Analyzing a codebase with parallel agents10:58 Why this changes the game12:27 Mastra vs. Claude's dynamic workflows13:11 Favorite Mastra memories14:08 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 MOREWhose agent wins? (Ali Spittel): https://x.com/ASpittel/status/2090889137062826240The 0x-alpha situation: https://x.com/mtslive/status/2090872472174522701100 trillion tokens a day: https://x.com/brandonjcarl/status/2090798277625041157The DeepSWE benchmarks: https://x.com/kimmonismus/status/2090718270202528215The reveal — it's Z.ai: https://x.com/chetaslua/status/2091086141764354364Qwen's 27B beats Opus 4.8: https://x.com/ggerganov/status/208940988185808910262% open weights on Vercel: https://x.com/rauchg/status/2091234105702887879Slack Code (Benioff): https://x.com/benioff/status/2090240159115853956Harvey's Tenet model: https://x.com/harvey/status/2090454750059958440Codex adopters, legal up 108x: https://x.com/a16z/status/2091623289869508979Agents burn 5x the tokens: https://x.com/a16z/status/2091200032162857328Tobi's weekend Git binary: https://x.com/tobi/status/2091678506992222258
📚 MASTRA RESOURCESMastra: https://mastra.aiMastra on X: https://x.com/mastra_aiMastra Discord: https://mastra.ai/community/discordMastra GitHub: https://github.com/mastra-aiLearn Mastra: https://mastra.ai/learnPrinciples of Building AI Agents (Book): https://mastra.ai/books/principles-of-building-ai-agentsPatterns 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.
⏱️ CHAPTERS00:00 Cold open: whose agent wins?00:25 Welcome00:39 Your agent vs. their agent04:21 The 0x-alpha mystery05:01 The conspiracy theories06:01 The reveal: it's Z.ai (GLM)08:44 Qwen breaks the size curve09:50 Subscribe09:59 Open weights take the gateway (62% on Vercel)11:12 Slack Code: humans + agents, same channel13:35 Legal breaks out: Harvey's Tenet model16:58 Codex adopters: legal up 108x18:29 Quick hits: agents burn 5x the tokens19:53 Cursor Origin: Git at Any Scale22:32 Tobi's weekend Git binary23:30 Outro

What does it actually take to run AI agents reliably in production? Hendrix Liu, co-founder of Respan (formerly Keywords AI, YC W24), joins Shane and Abhi to break it down.
Respan is a one-stop LLM engineering platform — an AI gateway, observability, evals, and prompt optimization in one place — used by teams like AlphaSense, Retell AI, DataCurve, and Mem0. Hendrix shares the three failure modes every agent team runs into (silent failures, reliability outages, and runaway cost), and the techniques to catch each one: fallback routing across 1,000+ models when a provider goes down, online evals that flag hallucinations before a customer does, and spend limits at the per-key, per-model, and per-customer level.
You'll also hear the counterintuitive origin story — Respan started as a model router in 2023, years before routing was cool, then pivoted to observability when nobody wanted another black box — plus a live demo of their Scratch-style evaluators, an honest take on build vs. buy for the LLM stack, and why most teams chasing an eval "certification" are really just after a compliance sticker.
Recorded live on AI Agents Hour, a weekly livestream by Mastra CPO Shane Thomas and CTO Abhi Aiyer. Mondays 12PM Pacific.
📚 ABOUT RESPANRespan: https://respan.aiRespan on X: https://x.com/RespanAIHendrix Liu on X: https://x.com/HendrixLiu29208Hendrix Liu on LinkedIn: https://www.linkedin.com/in/hendrix-liu-7a015822bRespan integrates with Mastra — teams already run Mastra agents through Respan today.
📚 MASTRA RESOURCESMastra: https://mastra.aiMastra on X: https://x.com/mastra_aiMastra Discord: https://mastra.ai/community/discordMastra GitHub: https://github.com/mastra-aiLearn Mastra: https://mastra.ai/learnPrinciples of Building AI Agents (Book): https://mastra.ai/books/principles-of-building-ai-agentsPatterns 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.
⏱️ CHAPTERS00:00 What to fix first00:24 Welcome — Hendrix from Respan00:57 What is Respan?01:38 The gateway: their first product03:41 The journey: gateway to observability to evals04:40 Bootstrapping to the tier-one list06:09 Three failure modes: silent, reliability, cost07:16 Techniques: fallbacks & online evals08:25 Build vs. buy for the LLM stack10:00 Demo: the gateway, limits & tracing11:18 Scratch-style evaluators13:11 Evals 101: how to actually get good14:22 The compliance trap15:12 The Mastra integration15:27 Outro

Money is moving, models are dropping, and GitHub's status page looks like a Christmas tree. Shane and Abhi open on the week's most-shared joke — the SF founder who realized his best friend was "emotionally attached to a cron job" — then get into Anthropic watermarking every bit of Claude's output to comply with the EU AI Act, and the reasoning-leak vulnerability that let researchers pull hidden thinking tokens out of frontier models.
Then a wave of new models: Grok 4.6 lands right in the conversation with GPT-5.6 and Fable (and Elon is already teasing 4.7), GLM 5.3 pushes near-frontier for cyber defense, and Qwen ships an open-weights 27B you can actually run on your own hardware. On the money side: Stripe reportedly acquiring OpenRouter for $7B, Dynatrace buying Arize, CodeRabbit's $143M Series C (with an all-time-great Silicon Valley parody video), and Lovable raising $400M at $13.3B. Plus DeepSeek's new harness, Sol running ultra-fast on Cerebras, and the code-hosting land grab as Cursor Origin and Netlify both become Git hosts while GitHub keeps going down.
AI Agents Hour is a weekly livestream by Mastra CPO Shane Thomas and CTO Abhi Aiyer. Mondays 12PM Pacific.
📚 READ MOREThe cron job breakup: https://x.com/tech__unicorn/status/2086936880197566757Anthropic watermarks AI output: https://x.com/ns123abc/status/2086922991921664307Hidden reasoning leak: https://x.com/kotekjedi_ml/status/2087147042888114428Grok 4.6: https://x.com/spacexai/status/2087562800982077492Grok 4.7 teaser (Elon): https://x.com/elonmusk/status/2087604711767896527GLM-5.3: https://x.com/zai_org/status/2088132965922476159Qwen3.8-27B open weights: https://x.com/Alibaba_Qwen/status/2088280182356611304Stripe to acquire OpenRouter ($7B): https://x.com/business/status/2089077253778915636Dynatrace acquires Arize: https://x.com/aparnadhinak/status/2087844420922364148CodeRabbit's $143M Series C: https://x.com/coderabbitai/status/2087525329132814524Lovable raises $400M at $13.3B: https://x.com/lovable/status/2087479640952836349DeepSeek Harness v0.1: https://x.com/deepseek_ai/status/2087887408440164663Sol ultra-fast on Cerebras: https://x.com/cerebras/status/2087948820906950719Cursor Origin: https://x.com/cursor_ai/status/2089399057659596847Netlify is now a Git host: https://x.com/biilmann/status/2089392941408399452Prompt injection in court filings: https://x.com/MTSlive/status/2088042921027330263MCP surpasses the app in Linear: https://x.com/jorilallo/status/2087277823631204591
📚 MASTRA RESOURCESMastra: https://mastra.aiMastra on X: https://x.com/mastra_aiMastra Discord: https://mastra.ai/community/discordMastra GitHub: https://github.com/mastra-aiLearn Mastra: https://mastra.ai/learnPrinciples of Building AI Agents (Book): https://mastra.ai/books/principles-of-building-ai-agentsPatterns 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.
⏱️ CHAPTERS00:00 Cold open: GitHub's Christmas-tree status page00:29 Welcome01:17 Emotionally attached to a cron job02:24 Anthropic watermarks AI output05:06 The hidden-reasoning leak06:39 New models: Grok 4.6 (and a 4.7 teaser)08:48 GLM 5.309:56 Qwen3.8-27B & open weights11:53 Subscribe12:09 Stripe acquires OpenRouter for $7B12:46 Why is OpenRouter worth $7B?15:31 Dynatrace acquires Arize16:49 CodeRabbit's $143M Series C19:04 Lovable raises $400M at $13.3B20:01 Harnesses: DeepSeek & Sol on Cerebras20:49 What's going on at GitHub?24:13 The code-hosting land grab: Cursor Origin & Netlify26:02 Quick hits: Ramp Index, OpenVuln, courtroom prompt injection, MCP in Linear28:12 Outro