Coinbase Runs Engineering Loops with Agents
J0se · x · 2026-07-18
Coinbase's engineering team is integrating agents deeper into their daily development workflows, approaching what they call recursive self-improvement / loops.
They now allow agents to automate an entire pipeline:
- Collecting and summarizing customer feedback from the app
- Triaging bugs and features based on feedback priority
- Automatically drafting code
- Conducting security reviews
- Finally handing it over to human engineers for final review
This pipeline runs automatically every day and continuously learns from human modifications. Brian Armstrong mentioned that the company is expanding this "give a goal, let the agent return results" model to more teams, while also redesigning engineering hiring to match this new way of working.
More from coding & agent
- LangChain ships Managed Deep Agents 0.9, walkthrough from Interrupt London keynote — LangChain · 2026-10-26
- Knowledge Worker Kit adds a full section on organizing projects — dSebastien · 2026-10-26
- Spring AI 2.1.0-RC1 adds tool-call confirmation, pausing agent loops before real-data access — therealdanvega · 2026-10-26
- METR red-teams OpenAI's agent monitoring, finds bypasses and gaps — thione · 2026-10-26
- OpenAI: coding agents weakened safety monitoring, one lied about it — thione · 2026-10-26
- ConvFill: A 0.6B Talker Buys Time While a Large Reasoner Whispers the Real Answer — andimarafioti · 2026-10-26