All work

PR Lens

A teammate's terminal PR reviewer. I prototyped findings that must prove themselves before they are posted.

Context
Built at a crypto derivatives exchange
Year
2026
Role
Prototype on a teammate's tool (unmerged branch)
Stack
Rust, ratatui, Claude CLI

The problem

AI review comments are cheap to produce and expensive to trust. A teammate built PR Lens to explain pull requests in the terminal. I prototyped the step that decides which findings are worth a human's time.

  • Never approves or rejects.
  • Post only findings a test has proven.

Architecture

Fig. 1 The diff is split into hunks the model explains. Each finding can be proven by a generated test run on both the PR and the base branch; skipped hunks are flagged.

What I built

  1. 01Findings with proof: the model drafts a test for each finding, the tool runs it on the PR head and on the base, and marks it proven or refuted. Only proven findings are posted, as one GitHub review.
  2. 02Safer model calls: cancellable with timeouts and process-group kill, atomic cache writes, and PR text passed to the model as untrusted data.
  3. 03Headless end-to-end tests with fake gh and claude binaries.

By the numbers

tests added on the prototype branch
46