Lindy rebuilt its AI teammate engine with coding agents — faster at half the cost, 9 lessons
mattbeane · x · 2026-11-18
Lindy, an AI teammate that does real work across Slack, email and text, rewrote its underlying engine this fall using coding agents — making it faster while cutting costs in half. The team shares 9 lessons from the rewrite: what they removed, what broke, and the three distinct kinds of hard in automation — getting it working at all, getting it working all the time, and getting it working at lower cost (true since the pyramids).
More from coding & agent
- Capability Is Not Authority: The Hidden Risks of Deploying AI Agents — Adjust-the-rhythm · 2026-11-18
- SciML author shares multi-model coding workflow: role-based routing for writing and review — ChrisRackauckas · 2026-11-18
- AI Agents That Need Constant Babysitting Aren't Agents — Few-Garlic2725 · 2026-11-18
- Rebuilding the Metabase MCP Server: Lessons in MCP Tool Design — Ramirond · 2026-11-18
- Dev wants a single client to manage all agent threads with Slack-style swipe UI — curious_vii · 2026-11-18
- Adaptive UI in a Claude CLI Enterprise Assistant: Prompting Isn't Enough — Shivam__kumar · 2026-11-18