# Introducing Nova, our internal platform for coding agents

[Dropbox](https://yomu.fyi/company/dropbox) · Ilya Yakovlev,Andrew Cheung,Binoy Dash,Simran Jumani,Dmitriy Meyerzon,Mark Breitenbach,Ishan Mishra,Kazuaki Okumura,Mike White,Kevin Altschuler · May 21, 2026

## Summary

Dropbox developed Nova, an internal platform that runs AI coding agents in isolated cloud environments integrated with their Bazel monorepo. The platform supports both interactive developer workflows and autonomous background tasks, such as automated CI debugging, flaky test remediation, and codebase-wide migrations. By pairing code generation with automated validation and strict execution guardrails, Nova ensures generated fixes are tested and reproducible.

## Takeaways

- Nova uses an iterative fix-and-validate loop where agents run within isolated environments and receive real build/test feedback if validation commands fail.
- Dropbox uses Nova in automated operational workflows like Deflaker, which analyzes passing and failing logs, proposes fixes, and stress-tests changes over 100 times in CI.
- Keeping deterministic control over CI execution, branching, and code publication outside the agent loop avoids long-running hangs and non-deterministic behavior.

**Tags:** [CI/CD](https://yomu.fyi/topic/ci-cd), [Developer Experience](https://yomu.fyi/topic/developer-experience), [LLMs](https://yomu.fyi/topic/llm), [Reliability](https://yomu.fyi/topic/reliability), [Testing](https://yomu.fyi/topic/testing)

[Read original post](https://dropbox.tech/machine-learning/introducing-nova-our-internal-platform-for-coding-agents)