Agents Are Distributed Systems — What Navan and TikTok Learned
A timeout on a refund tool doesn't mean failure. It means unknown. Two AI Engineer talks on running agents in production, from the teams doing it.
Conference
The latest in Conference
9 stories · prices and picks kept current
45% of Agent Sessions Are Shopping: Best Buy's Agentic Commerce Stack
Best Buy's Ahnaf Prio maps the agentic commerce stack — MCP, A2A, ACP, UCP, AP2 — and explains why browser-driving shopping bots failed at checkout.
Agents That Beat reCAPTCHA — and the End of Line-by-Line Review
Two AI Engineer conference talks in depth: how one agent cleared Turnstile and reCAPTCHA v2 alone, and why Aviator's co-founder says the diff is dead.
Mike Krieger: Anthropic Ships on Two-Week Persevere-or-Pivot Reviews
Instagram's co-founder on porting 200K lines over a weekend, why code review is really a comprehension bottleneck, and how Anthropic Labs kills projects every two weeks.
AWS AI-Native Teams: Five Habits Behind the Productivity Gains
Clare Liguori of AWS on Amazon's 50-team agent pilot: a median 4.5x gain in deployment velocity, the five habits behind it, and why half the teams missed.
$3B and 35 Businesses: Long Lake's Blueprint for AI Diffusion
Varun Shenoy on why AI still hasn't reached a 200-person property firm — and what owning 35 services businesses taught Long Lake about deploying agents.
Figma Shipped Its MCP Server in 3 Months While the Spec Changed
Jesse Lumarie on shipping Figma's MCP server as a 20% project: why React and Tailwind beat the scene graph, and the eval that started in Excel.
Stripe's Billing Agent Rule: Vibe-Code the Sandbox, Not Production
Metronome co-founder Andrew Garvin demoed an agent building a Lovable-style credit pricing model from one sentence — and drew a hard line at the production boundary.
Uber's uReview: 25,000 AI Code Review Comments a Week
Uber built a multi-agent code review engine because review time tripled. Figma's lesson: verification beats prompting. Two AI Engineer talks, unpacked.