Top AI Product

Coding agents like Claude Code and Codex do a lot in a single session, and most of it scrolls past too fast to learn from. Spotlight, from Backplanes, reads those sessions and turns them into reports — what the agent actually did, what’s worth keeping, what to fix, and where you could save time next run.

## What Spotlight does

Spotlight watches every move across a Claude Code or Codex session and hands back quick, structured feedback rather than a raw transcript. The pitch is recursive improvement: each report is meant to make your next run tighter, by surfacing the patterns that worked and the dead ends that didn’t. Privacy is built in — local redaction strips PII and credentials before anything leaves your laptop. It’s free for individuals and teams and runs on macOS, Linux, and WSL 2.

## Why it matters

As more engineering shifts onto agents, the bottleneck moves from writing code to supervising and improving how the agent works. A feedback layer that reviews agent sessions — like a retro for every run — is the kind of tooling that turns ad-hoc agent use into something you can actually get better at over time.