AI Agents Hour
Join Mastra cofounders Shane Thomas and Abhi Aiyer for weekly conversations about the latest in AI.
They discuss breaking AI news, chat with guests from the industry, and go deep on the technical challenges of building AI agents.
Listen on:
Latest Episodes
March 12, 2026
#71
Meta Acquires Moltbook, Openai Releases GPT 5.4, TypeScript Is #1 on GitHub (This Week In AI)
A lot happened in eight days. Meta acquired Moltbook, a social network built entirely for AI agents, not humans. OpenAI dropped GPT-5.4 Thinking and GPT-5.4 Pro, Codex got forks for multi-agent workflows and Windows support, and there are rumblings of OpenAI building a GitHub alternative. Anthropic fired back hard — multi-agent PR code review for Claude Code, while loops via /loop, the Claude Marketplace, and a way to pull your context from other AI tools.
March 10, 2026
#70
The Biggest Threat to AI Agents (with Ismail Pelaseyed)
Ismail Pelaseyed from Superagent is back on Agents Hour, and this time he's talking about something most builders aren't thinking about yet — supply chain attacks on AI agents. Guardrails protect against what you tell your agent to do. But what about everything your agent reads, fetches, and installs on its own? That's the gap Brin is built to fill.
March 4, 2026
#69
Missile Strikes Disrupt AWS and Claude, Anthropic Banned from US Government, Cloudflare vs Vercel
This week in AI saw geopolitical turmoil, major funding news, and a shift in software development. Missile strikes in the UAE and Bahrain disrupted AWS and Claude services. Meanwhile, after Anthropic banned its models from autonomous weapons and mass surveillance, the Trump administration banned Anthropic from government contracts—posing a major supply chain risk. On the same day, Sam Altman secured a deal with the Department of War as OpenAI announced a $110 billion funding round, highlighting a sharp contrast in approaches.
March 1, 2026
#68
How to Build Reliable AI Agents with Datasets, Experiments, and Error Analysis
Yujohn from Mastra explains why datasets and experiments are essential for building production-grade AI agents. If you're building an agent, you need a way to verify it's working correctly before and after you make changes. Datasets provide that baseline. You create a collection of test cases (ground truth) that represent the scenarios your agent should handle. Then you run experiments: pass each test case through your agent and measure the results. This is error analysis in practice. You start by identifying where your agent fails, then build scorers to quantify those failure modes over time. Smaller teams often ship first and add datasets later, once they have user feedback. Larger teams need them earlier. But eventually, every production agent needs this. The demo shows how Mastra makes this accessible. You can create datasets through the UI, add items manually or import from CSV, and run experiments with a single click. The results show you exactly what went wrong: which tool calls failed, what the agent output was, and how it compared to ground truth. You can also compare experiments side by side to see if your prompt tweaks actually improved things. And because all the data lives in your own database, you can write your own agents to analyze the results, dig into traces, and iterate. The SDK makes it easy to integrate into CI/CD: run experiments on pull requests, gate deployments on eval scores, or just collect data from production and curate datasets later.
February 27, 2026
#67
A Coding Agent That Never Compacts
Abhi walks through Mastra Code, a new open-source coding agent with observational memory that compresses context without losing it.
February 25, 2026
#66
AI NEWS: Stripe's Minions, Distillation Attacks on Claude, Cloudflare's Code Mode
Shane and Abhi break down the biggest AI news from the past few days. Anthropic identified industrial-scale distillation attacks on Claude by DeepSeek, Moonshot AI, and MiniMax. Anthropic also released a groundbreaking report analyzing millions of AI agent interactions using Claude. Stripe is shipping 1,300+ AI-generated PRs per week with their Minions system. Code Mode for MCP is becoming a standard part of the MCP ecosystem, and we cover skills benchmarks, trajectory explorer for agent traces, Vercel AI Gateway video support, and more.
February 24, 2026
#65
How to Orchestrate Coding Agents with Conductor, with Charlie Holtz
Shane and Abhi welcome Charlie Holtz from Conductor to AI Agents Hour. Charlie shares how frustration with managing multiple Claude Code instances led to building Conductor. They discuss Conductor's July 2025 launch as the first agent orchestration Mac app, early design choices, and its impact on the market.
February 20, 2026
#64
AI NEWS - Something Big is Happening: Gemini 3.1 Pro, GPT-5.3-Spark, and Anthropic $30B fundraise
It's time for another AI News roundup with Shane and Abhi! This week was absolutely massive. Matt Shumer's viral article about AI automation, which describes his own job being automated in real time, has reached 84 million views. Anthropic raised $30 billion at a $380B valuation (one of the largest private raises in tech history). Claude Sonnet 4.6 launched with a 1M token context window. And the Chinese model tsunami is real: Qwen 3.5, GLM 5.0, MiniMax M2.5 (nearly Opus-level at 1/8 the cost), and DeepSeek v4 rumors.
February 12, 2026
#63
Observational Memory: The Human-Inspired Memory System for AI Agents, with Tyler Barnes
Tyler Barnes, founding engineer at Mastra, introduces Observational Memory. It is a new memory system for AI agents that achieves state-of-the-art results on LongMemEval with a completely stable context window. Unlike semantic recall (which uses RAG and invalidates prompt caching), Observational Memory compresses conversations into dense observations while maintaining a stable, fully cacheable context. The result: 94.87% accuracy on LongMemEval with GPT-5 mini. This is the highest score recorded by any memory system to date. In this conversation, Tyler explains how the system works, why it outperforms raw context, and how you can integrate it into your agents in under 20 minutes. We also dive into the research, the benchmarks, and what's next for Observational Memory.