Agents in Orbit: Workflows, Not Autopilot — Eduardo Simon & Javier Casal, Flywire

Shows a pattern of deterministic workflows with scoped model steps, reviewed in merge requests. It gives concrete controls such as timeouts, locks, and per-step permissions.

• eval — A repeatable test for AI quality — a set of tasks plus scoring — used the way software teams use test suites, because model output is too variable to judge by eyeballing.

• videoI Believe Everything My Agents Tell Me: Three Levels of Review — Corey Gallon, Rexmore
• video1,000 Agent Tasks in a Sandbox: What Breaks When LLMs Run Code — Kevin Orellana, AWS
• videoHow Inference Keeps Up with Our Insatiable Need for Tokens — Cerebras & Gimlet Labs
• videoAuth for Agents: Let AI Sign Up for Your Product with auth.md — Michael Grinich, WorkOS

• videoRealtime multiplayer, automation, and you! — Idan Gazit, GitHubAI Engineer
• videoThe Agent Behind the Curtain: Building the Oz Cloud Agent Platform — Safia Abdalla, WarpAI Engineer
• videoThe SDLC You Build Yourself — Andy Wong, Andrei Bocan & Shane Wolf, AtlassianAI Engineer

Checking sign-in…

Loading comments…