Source: https://internal-agents.com/agents/cloudflare-code-reviewer # Cloudflare — AI Code Reviewer Cloudflare’s reviewer analyzes merge requests and applies approval decisions, including merge blocks for serious findings. - Company: [Cloudflare](https://internal-agents.com/organizations/cloudflare) - Collection: Agents - Approach type: Agent - Deployment stage: Deployed - Autonomy: Unknown - Evidence strength: Detailed primary - Status: Internal - First reported year: 2026 - Work: Code review - Interfaces: Ci, Cli - Invocation: Event-driven - Entry reviewed: 2026-09-17 ## Purpose ### Summary Cloudflare’s reviewer analyzes merge requests and applies approval decisions, including merge blocks for serious findings. Fact · Reported · High confidence · `cloudflare-code-reviewer--summary` Confidence reason: A linked first-party source states the claim. Evidence: - Supports · [1] [Orchestrating AI Code Review at scale](https://blog.cloudflare.com/ai-code-review/) · The architecture; The coordinator helps keep things focused; Limitations Representative workflow: merge request → structured review and approval state. ## How it works ### Dispatch specialists An OpenCode coordinator assigns reviewers according to change risk. Fact · Reported · High confidence · `cloudflare-code-reviewer--primitives-0` Confidence reason: A linked first-party source states the claim. Evidence: - Supports · [1] [Orchestrating AI Code Review at scale](https://blog.cloudflare.com/ai-code-review/) · The architecture; The coordinator helps keep things focused; Limitations ### Apply review It approves, revokes bot approval or requests changes; a human can force approval with a break-glass comment. Fact · Reported · High confidence · `cloudflare-code-reviewer--primitives-2` Confidence reason: A linked first-party source states the claim. Evidence: - Supports · [1] [Orchestrating AI Code Review at scale](https://blog.cloudflare.com/ai-code-review/) · The architecture; The coordinator helps keep things focused; Limitations ## Where people stay involved - **merge request → structured review and approval state** — Unknown · Level unknown **Unreported:** The source does not establish the required human review boundary. ### Supervision evidence #### Operating model assessment Unclassified for merge request → structured review and approval state; human attention boundary: unknown. Inference · Catalog judgment · Unverified confidence · `cloudflare-code-reviewer--operating-models-0` Confidence reason: The source describes AI Code Reviewer and its work, but does not establish whether a person must approve or inspect each successful output. Qualifications: - Observation date: 2026 Evidence: - Supports · [1] [Orchestrating AI Code Review at scale](https://blog.cloudflare.com/ai-code-review/) · The architecture; The coordinator helps keep things focused; Limitations ## Implementation details ### Harness Plugin-based OpenCode integration in CI. Fact · Reported · High confidence · `cloudflare-code-reviewer--architecture-harness` Confidence reason: A linked first-party source states the claim. Evidence: - Supports · [1] [Orchestrating AI Code Review at scale](https://blog.cloudflare.com/ai-code-review/) · The architecture; The coordinator helps keep things focused; Limitations ### Tool access GitLab review APIs and code-reading tools. Fact · Reported · High confidence · `cloudflare-code-reviewer--architecture-tool-access` Confidence reason: A linked first-party source states the claim. Evidence: - Supports · [1] [Orchestrating AI Code Review at scale](https://blog.cloudflare.com/ai-code-review/) · The architecture; The coordinator helps keep things focused; Limitations ### Context management Shared MR context and per-file patches. Fact · Reported · High confidence · `cloudflare-code-reviewer--architecture-context-mgmt` Confidence reason: A linked first-party source states the claim. Evidence: - Supports · [1] [Orchestrating AI Code Review at scale](https://blog.cloudflare.com/ai-code-review/) · The architecture; The coordinator helps keep things focused; Limitations ### Interfaces ci, cli Fact · Reported · High confidence · `cloudflare-code-reviewer--architecture-interfaces` Confidence reason: A linked first-party source states the claim. Evidence: - Supports · [1] [Orchestrating AI Code Review at scale](https://blog.cloudflare.com/ai-code-review/) · The architecture; The coordinator helps keep things focused; Limitations ### Implementation coverage - **Model:** unreported — Not documented for this subject in the reviewed source. - **Harness:** reported - **Sandbox:** unreported — Not documented for this subject in the reviewed source. - **Tool access:** reported - **Knowledge:** unreported — Not documented for this subject in the reviewed source. - **Context management:** reported - **Credentials:** unreported — Not documented for this subject in the reviewed source. - **Interfaces:** reported ## Validation and failure handling ### Check findings The coordinator deduplicates findings and uses code-reading tools to assess uncertain issues. Fact · Reported · High confidence · `cloudflare-code-reviewer--primitives-1` Confidence reason: A linked first-party source states the claim. Evidence: - Supports · [1] [Orchestrating AI Code Review at scale](https://blog.cloudflare.com/ai-code-review/) · The architecture; The coordinator helps keep things focused; Limitations ## Reported observations **Unreported:** The reviewed source does not document this for the named subject. ## Lessons ### Lesson Cloudflare reports limitations in architectural context, cross-system impact and subtle concurrency analysis. Fact · Reported · Medium confidence · `cloudflare-code-reviewer--lessons-learned-0` Confidence reason: Reported implementation lesson; not a controlled evaluation. Evidence: - Supports · [1] [Orchestrating AI Code Review at scale](https://blog.cloudflare.com/ai-code-review/) · The architecture; The coordinator helps keep things focused; Limitations ## Question coverage and scope - **purpose:** Reported - **workflow:** Reported - **human involvement:** Unreported — The source does not establish the required human review boundary. - **implementation:** Reported - **validation:** Reported - **observations:** Unreported — The reviewed source does not document this for the named subject. - **lessons:** Reported ## Related reading - Built on: [Cloudflare — Internal AI engineering stack](https://internal-agents.com/agents/cloudflare-ai-stack) ## Sources 1. [Orchestrating AI Code Review at scale](https://blog.cloudflare.com/ai-code-review/) - Engineering blog · First party · Evidence - Original URL: - Accessed: 2026-09-17 · Last verified: 2026-09-17