Thorsten Ball on working with agents: run more evals, automate everything, use the best models
omarsar0 · x · 2026-10-27
Thorsten Ball published 'How I Work with Agents' (October 2026 edition), and Elvis Omarsar shared his top takeaways: run as many evals as possible (especially on agents' knowledge use), lean heavily into automations that let agents do proactive work—deliberately stress-testing to see what breaks often unlocks new use cases—and scale agents across more tasks in parallel while regularly auditing what tools and knowledge they're missing.
Ball's core rule: use the latest and greatest models, always. If a model is wrong 10% of the time, you don't know which 10%, so cutting corners here ends up wasting more time than it saves. Recommended reading for anyone building with coding agents.
Related event: Thorsten Ball's Essay on Working with Agents Sparks Debate(4 posts)→
More from coding & agent
- Cursor launches Agent SDK: agents as code with Markdown prompts and TypeScript tools — soleio · 2026-10-27
- Vibecheck, the 'usable formal methods' hackathon, sells out two floors in SF — spikedoanz · 2026-10-27
- How do you verify AI agent outputs beyond unit tests and LLM-as-judge? — Practical_Green5775 · 2026-10-27
- AI agents may soon become the only way to run code, not just write it — IgorCarron · 2026-10-27
- Hermes Agent used as browser QA tester finds 8 issues in a bug-seeded site — techlatest_net · 2026-10-27
- Open-source FableCut lets AI agents edit a real video timeline via remote MCP — FastPresence9799 · 2026-10-27