Show Notes
Evan Marshall, CTO of Ito, joins Agents Hour to argue that the bottleneck of code development has moved to QA — and the tools to automate it don't exist yet. Ito is a code review tool that runs your code. It intercepts every PR, spins up the impacted user flows in an isolated sandbox, and posts videos, screenshots, and run logs back to the GitHub timeline as proof. The team is fourteen people, mostly engineers. Evan has been a professional programmer for fifteen years and previously worked at Demox Labs and Rev. With model gains flattening after Opus 4.5, the harness around the model is where value gets created. Evan shares details of Ito's "carriage" — a workflow of swarmed agents inside deterministic boundaries, designed so the system benefits from agents getting smarter without compounding probabilistic errors. He explains why bigger organizations aren't hitting the 10x code velocity the X timeline promises, and what the validation layer needs to look like before they can. 🔗 EVAN MARSHALLhttps://x.com/CoralReliefhttps://www.linkedin.com/in/evan-marshall-66598053/ 📁 ITOhttps://www.ito.ai 📚 MASTRA RESOURCEShttps://mastra.aihttps://x.com/mastra_aihttps://mastra.ai/community/discordhttps://github.com/mastra-aihttps://mastra.ai/coursehttps://mastra.ai/books/principles-of-building-ai-agentshttps://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. 0:00 Cold open: It's the harness0:26 Meet Evan and Ito1:30 Unit tests vs the integration layer2:11 From scraping to QA2:59 What's a harness?3:42 What's a carriage?5:51 Sandboxes and task decomposition7:16 Claude Code, Opus, and Terminal Bench9:01 Live demo: code reviews that run your code13:57 The enterprise gap15:08 Audience Q: Playwright integration16:30 How to try Ito
More from 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 BRADBrad 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 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 open00:17 Meet Brad02:09 Is software actually easy now?04:22 Spreadsheets to space shuttles05:06 Are small businesses AI-pilled?06:51 Why Brad built Plum08:01 Demo: agents in a meeting09:12 Any agent can join with WebMCP11:12 Agents as meeting participants12:07 Your meeting history, stored locally12:48 Working with agents in real time14:42 Shared context that doesn't reset15:41 Can agents speak in the meeting?16:32 When Grok Bot taught Claude17:37 Fun and serious use cases19:07 Bring your own agent19:22 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 MOREOpenAI's recording device: https://x.com/OpenAINewsroom/status/2110095403198849132Mistral Large 4: https://x.com/mistralai/status/2107457414387622310Claude Haiku 5.5: https://x.com/claudeai/status/2107894039626277339Muse Wonder: https://x.com/finkd/status/2109689305073614918Gemini 4 Argon: https://x.com/sundarpichai/status/2110038898009407584OpenAI does math: https://x.com/AndrewCurran_/status/2107596925512065087Jev's Series A: https://x.com/CompleteSkeptic/status/2108594987177021737SubQ Snap: https://x.com/alex_whedon/status/2109676361371824229Microsoft-Decision-1: https://x.com/satyanadella/status/2108627923888754862Clef-omni: https://x.com/cloudflare/status/2108696873510850758Anthropic's in-house source control: https://x.com/AnthropicAI/status/2110047081414987957Claude's new usage policy: https://x.com/haydenfield/status/2108241513159528705Chris Olah and the Pope: https://x.com/christopherhale/status/2106011594182304234NVIDIA and Reflection AI: https://x.com/ns123abc/status/2109007812277743757Maia 300: https://x.com/satyanadella/status/2109631106404487523Grok Bot and Claude: https://x.com/elonmusk/status/2107724314451878104The agent that posted my finances: https://x.com/ShaneMac/status/2107486746325725669Devin Dreaming: https://x.com/cognition/status/2107165034463867001Nous Research raises $90M: https://x.com/choblin29/status/2107801489506750725Personal Agent Protocol: https://x.com/btaylor/status/2107535182119244176Coinbase fine-tunes Qwen: https://x.com/brian_armstrong/status/2109412046244913643Adobe clones: https://x.com/Pirat_Nation/status/2108437553615425881 📚 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 open00:29 Intro01:37 OpenAI finds a literal bug03:18 Mistral Large 4 aka Le Chonk05:07 Claude Haiku 5.506:28 Muse Wonder08:14 Gemini 4 Argon is out09:06 OpenAI does math11:27 Jev's $870M Series A12:42 SubQ Snap13:12 Microsoft-Decision-113:42 Unsloth and Clef-omni14:06 Anthropic builds its own source control17:32 Cheaper Sonnet, Claude Dashboards and Motion17:50 Be n
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 DANIELDaniel 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/dbworkuStarSling: https://starsling.devStarSling Review Runners: https://starsling.dev/products/review-runnersHow Mastra got 6x faster GitHub Actions tests: https://starsling.dev/customers/mastraHigh Performance Sandbox Benchmarks: https://github.com/starslingdev/hpc-sandbox-benchmarksAnthropic 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 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 open00:23 Why CI became the bottleneck01:25 Meet Daniel and StarSling02:51 Why GitHub's runners are slow03:58 Self-improving CI05:06 Benchmarking sandboxes for CI06:41 Why agents make CI so expensive07:43 Most unit tests aren't useful08:23 Stacked PRs09:25 Mastra's CI story11:48 The end of CI as we know it13:26 Sharing infra between CI and code review14:36 Code review is the new bottleneck15:08 Bring your own model to code review16:27 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 MOREAnthropic IPO prospectus: https://x.com/ns123abc/status/2104735822029176833OpenAI Decisions API: https://x.com/thsottiaux/status/2104986448269279399Begun, the clone war has: https://x.com/CompleteSkeptic/status/2105000685209313736OpenRouter decision models: https://openrouter.ai/models?output_modalities=decisionsCloudflare Clef: https://x.com/michellechen/status/2105684868550045751GLiDE: https://x.com/george_onx/status/2105726320357634303Dots: https://x.com/OpenAI/status/2104984504133918973GPT-6.1 Sol: https://x.com/OpenAIDevs/status/2104993067942219873Sam Altman on Cerebras: https://x.com/sama/status/2106147184693620924Gemini 4 Argon: https://x.com/GoogleDeepMind/status/2105388084154056939Vals Index: https://x.com/ValsAI/status/2105388446844072033White House Accord: https://x.com/davidsacks/status/2105060520327786914Factory vs Cognition: https://x.com/matanSF/status/2105335179502064038Vinod Khosla: https://x.com/vkhosla/status/2105382865173459034Sindre Sorhus closes PRs: https://x.com/sindresorhus/status/2105693826690298314Hono closes PRs: https://x.com/yusukebe/status/2107027870019445007Turso joins Supabase: https://x.com/tursodatabase/status/2106054567125532976OpenDots: https://x.com/ataiiam/status/2105710796198322659Conductor Mobile: https://x.com/charlieholtz/status/2105769644498002130Karpathy: https://x.com/karpathy/status/2105819303471976479Claude Code mods: https://x.com/ClaudeDevs/status/2105721434807083061Tavus Griffin: https://x.com/tavus/status/2105704169009246248Eleven v4: https://x.com/ElevenLabs/status/2104572127617994917SWE-sweep: https://x.com/klieret/status/2105670833574465933 📚 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 open00:26 Intro00:38 Anthropic's IPO prospectus leaks03:13 The decision model era05:03 Cloudflare Clef, SGLang and GLiDE06:09 Span-01 and Kev06:23 Why decision models are good for the industry07:25 OpenAI DevDay recap08:44 The Dots demo backlash10:28 OpenAI and Cerebras11:27 Gemini 4 Argon13:53 Gemini tops the Vals Index14:09 A 1M token output limit15:14 T
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 MOREOpenAI DevDay 2026 recap: https://openai.com/index/devday-2026-recap/Codex Security Cloud: https://x.com/OpenAI/status/2104987422308335828Devin with your ChatGPT subscription: https://x.com/cognition/status/2104996240190792029Pro 200 usage cut and Pro 500: https://thenextweb.com/news/openai-devday-pro-200-usage-cut-pro-500-planMicrosoft 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/2104997638462652838xAI and dot.com: https://www.techbuzz.ai/articles/musk-s-xai-snatches-dot-com-domain-before-openai-s-dots-launch 📚 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 Intro01:42 Dots04:34 Microsoft Autopilot04:59 GPT-6.1 Sol06:17 Ultrafast06:35 Private Intelligence07:16 Codex in the cloud and code review08:26 Codex Security Cloud09:01 Decisions API10:03 Agents API and Bedrock Managed Agents10:56 Are plugins the new app stores?12:07 MCP events12:42 ChatGPT Space, Pages and more14:06 Sign in with ChatGPT14:16 Pro 500 and the $200 plan14:38 OpenAI Marketplace14:53 Choose your lock-in17:02 Reactions: the Pro plan rug pull17:51 Devin and Codex subscriptions18:57 Pi and Mastra Code19:44 TypeSafe on the Decisions API20:35 The Dots demo flop21:11 xAI buys dot.com21:59 Outro