---
type: "post"
id: "uber-uses-a-similar-setup-to-clean-up-200090"
slug: "uber-uses-a-similar-setup-to-clean-up-200090"
title: "Uber uses a similar setup to clean up old code."
description: "Uber has described AutoClean, an internal system for removing stale feature-flag code from its monorepos."
retrieval_nugget: "Uber has described AutoClean, an internal system for removing stale feature-flag code from its monorepos."
published_at: "2026-10-24"
updated_at: "2026-10-24"
record_date: "2026-10-24"
date_kind: "published_at"
topics: ["mcp"]
entities: ["Uber","AutoClean","PolyglotPiranha","Model Context Protocol"]
related_patterns: ["harness-architecture-outlives-model-choice","verification-bandwidth-is-the-scarce-resource","agent-ready-software-exposes-capabilities"]
novelty_label: "new_fact"
what_changed: "Uber describes its own AI-agent system for deleting stale feature-flag code, including AutoClean, PolyglotPiranha and MCP, extending prior coverage of AI-assisted engineering and legacy-code cleanup."
prior_refs: ["memory:fe85520b-fc99-8573-a9e6-03a43a9d022d","memory:c52605ae-8527-8bd9-a2ee-5a089e7ffe7d","memory:1a22f1f8-40af-818e-a34b-7b16ff424fe5"]
source_url: "https://www.uber.com/us/en/blog/ai-code-cleanup"
source_urls: ["https://www.uber.com/us/en/blog/ai-code-cleanup"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "post:uber-uses-a-similar-setup-to-clean-up-200090"
status: "published"
visuals: []
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
routes: {"html":"https://newruntime.com/posts/uber-uses-a-similar-setup-to-clean-up-200090/","markdown":"https://newruntime.com/posts/uber-uses-a-similar-setup-to-clean-up-200090.md","json":"https://newruntime.com/posts/uber-uses-a-similar-setup-to-clean-up-200090.json"}
---

# Uber uses a similar setup to clean up old code.

## Retrieval answer

Uber has described AutoClean, an internal system for removing stale feature-flag code from its monorepos.

Uber has described AutoClean, an internal system for removing stale feature-flag code from its monorepos. The company says it manages thousands of flags across mobile applications and backend services. Once a flag has fully rolled out, its conditional branches, configuration, parameters, and tests can remain as technical debt.

AutoClean connects to Uber’s feature-flag system of record, identifies flags considered safe to remove, rewrites code, addresses CI failures, validates the resulting diff, and routes it to the owning team for review. It runs continuously and keeps review-ready changes fresh until a human reviewer makes the final decision.

The core agent has access to the codebase plus a scoped tool set for file search and editing. For boolean algebra and conditional simplification, Uber uses PolyglotPiranha, its code-transformation engine, exposed to the agent through MCP rather than relying on the model to make those rewrites itself.

The post does not provide comparative measurements for cost, acceptance rate, defect rate, or the number of changes merged by AutoClean. It also does not describe a public release or external access to the system.

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- topic hub: [Mcp](https://newruntime.com/topics/mcp.md): Explore the mcp topic hub.
- collection: [Field Notes](https://newruntime.com/posts.json): Open the latest editorial analysis.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)