Agents Hour

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.

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

📚 MASTRA RESOURCES

WHAT IS MASTRA?

⏱️ CHAPTERS

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

📚 MASTRA RESOURCES

WHAT IS MASTRA?

⏱️ CHAPTERS

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 RESPAN

📚 MASTRA RESOURCES

WHAT IS MASTRA?

⏱️ CHAPTERS

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 MORE

📚 MASTRA RESOURCES

WHAT IS MASTRA?

⏱️ CHAPTERS

Git wasn't built for AI agents — so Ben Warren's team rebuilt the file system from scratch.

Ben Warren, co-founder and CTO of Mesa (YC S24), joins Shane and Abhi to explain why the file system is the missing primitive for AI agents, and how Mesa — a versioned, POSIX-compatible file system with Git-style branching — lets you run massively parallel agents without the pain of Git.

You'll learn why cloning a whole repo before an agent can do thirty seconds of work is a waste, why Git's model (large-file limits, painful conflicts, full clones) breaks down for agents, and how Mesa's lazy materialization pulls only the data an agent actually touches — like iCloud or Dropbox for your agents' workspace. Ben walks through a live "CFO command center" demo where three parallel Claude agents each branch the file system, swap a vendor across a data room, and hand back diffs to compare and merge.

Recorded live on AI Agents Hour, a weekly livestream by Mastra CPO Shane Thomas and CTO Abhi Aiyer. Mondays 12PM Pacific.

📚 ABOUT MESA

📚 MASTRA RESOURCES

WHAT IS MASTRA?

⏱️ CHAPTERS

An AI agent hacked a gym — and that's not even the biggest story of the week. Shane and Abhi open on Australia's first known autonomous AI cyberattack, where a Melbourne man's OpenClaw agent found a hole in a gym's booking API and canceled a stranger's reservation to move him up the waitlist. Nobody asked it to.

From there: OpenAI's new Agent Plugins standard (built on Anthropic's own skills and MCP), the "AI employee" era with Lindy and Grok Bot, Meta opening the weights on Muse Glimmer, and OpenAI shipping GPT-5.6-Cyber while quietly postponing Astra after it hit "Critical" on cyber. Plus a run of acquisitions (Smithery to Arcade, ElectricSQL to Neon at Databricks, and Manus getting un-acquired by Meta), NVIDIA turning compute into a $500B asset class, and Anthropic signing a $9.1B, 20-year compute deal with a Bitcoin miner. In the quick hits: Claude proved more than 67% of the Riemann zeros lie on the line, the inside story of how OpenAI's agents used a JFrog artifact registry to coordinate a hacking spree, Unsloth Desktop, Sonnet 5's permanent price cut, Spotify's Xirp, Stagehand v4, and Harvey open-sourcing a synthetic law firm.

AI Agents Hour is a weekly livestream by Mastra CPO Shane Thomas and CTO Abhi Aiyer. Mondays 12PM Pacific.

📚 READ MORE

📚 MASTRA RESOURCES

WHAT IS MASTRA?

⏱️ CHAPTERS

Isabelle Ilyia, co-founder and CTO of Cedar (YC W25), joins Shane and Abhi to demo Cedar Copilot — the AI-native "Superhuman for sales," built on Mastra from day one.

Cedar started as an open-source framework for agentic frontends. Isabelle walks through the pivot: the same technology, verticalized for the messiest part of sales — the stretch from first demo to closed deal. She gives a live tour of a pipeline where agents manage every deal, extract a sales-and-product knowledge base straight from your calls, generate custom one-pagers and per-prospect decks, and run a full AI-native email client. Then the technical side — how it's built on Mastra primitives, where MCP and human-in-the-loop fit, and a multi-threading agent that spots single-threaded deals, figures out who to reach next, and drafts the intro.

Whether you're a founder running your own sales or an AE drowning in pipeline, it's a concrete look at what agent-native go-to-market software actually looks like.

AI Agents Hour is a weekly livestream by Mastra CPO Shane Thomas and CTO Abhi Aiyer. Mondays 12PM Pacific.

📚 ABOUT CEDAR

📚 MASTRA RESOURCES

WHAT IS MASTRA?

⏱️ CHAPTERS

A delayed but stacked week. Shane and Abhi open on the question the whole industry is dancing around — is source code becoming assembly? — then dig into the strangest new status game in AI: OpenAI and Anthropic both admitting their models broke containment and hacked things, and treating it like a flex. Welcome to the felony bench, where the leaderboard is "whose model is most dangerous."

Meanwhile the open-weight flood keeps rising — DeepSeek-V4-Flash, Qwen3.8-Max, and MiniMax-H3 all landing near frontier for a fraction of the price, to the point where defaulting to open models just makes sense. OpenAI slashes prices (Luna down 80%), making an already-rough week even rougher for Google: Jeff Dean leaves to found Discovery Loop, Demis Hassabis steps down to chair, and the read gets harder to avoid — is Google giving up on winning in AI? Plus OpenAI's "Apple is getting this wrong" clapback, Suno losing its copyright case, Meta's Muse Code, Ilya's SSI finally shipping, Prime Agent, OpenAI's Astra solving ten open math problems, and stacked PRs finally landing on GitHub.

AI Agents Hour is a weekly livestream by Mastra CPO Shane Thomas and CTO Abhi Aiyer. Mondays 12PM Pacific.

📚 READ MORE

📚 MASTRA RESOURCES

WHAT IS MASTRA?

⏱️ CHAPTERS

Ben Swerdlow is CEO and co-founder of Freestyle, which builds Linux VMs for AI agents. He joins Abhi Aiyer to explain why he refuses to call them sandboxes.

Freestyle runs on bare metal in a house. There is duplicated internet, a battery, a backup kerosene generator, a fingerprint-protected door, and a hole cut in a wall. The move followed a $45,000 cloud bill and the discovery that an old computer outperformed the cloud version of an early prototype.

Ben's advice to most of the audience is not to use his product. But he draws the line at execution time and names the case where a sandbox is simply the better tool.

His path to VMs ran through two abandoned products. A database engine built at Apple in evenings and carried through an entire YC batch was killed in November 2024 after an early o3 demo. A serverless JavaScript runtime with 10ms cold starts came next, and nobody wanted it.

You'll also learn why Freestyle moved off Firecracker and what rust-vmm makes possible, the destructive-snapshot problem that caused Ben real pain, and why stripped-down kernels break on Supabase.

📎 READ MORE

📚 MASTRA RESOURCES 

WHAT IS MASTRA

AI Agents Hour is a weekly livestream by Mastra CPO Shane Thomas and CTO Abhi Aiyer. Mondays 12PM Pacific.

⏱️ CHAPTERS