Blog

Engineering notes and governance explainers.

What we're proving, how the replay engine actually works, and what it means for teams that need to show their work.

Subscribe via RSS →
Runback Team · July 14, 2026

How to pick between the Vercel AI SDK integration, an OpenTelemetry exporter, and the framework-agnostic manual recorder — with the actual commands for each.

Runback Team · July 14, 2026

Why capturing the request at the wrapLanguageModel boundary — not at your own call sites — is what makes replay mean something.

Runback Team · July 14, 2026

How @runback/redact scrubs API keys, JWTs, SSNs, and card numbers in-process, before anything is sent anywhere.

Runback Team · July 14, 2026

The exact algorithm behind Runback's signed, append-only audit record — and what it means for EU AI Act and APRA CPS 230 compliance.

Runback Team · July 14, 2026

A walkthrough of a real failing agent — from error-first navigation to editing the exact captured request and replaying it.

Runback Team · July 14, 2026

A stress test of Runback's replay engine: reproducing a genuine, lock-free data race byte-for-byte, three runs in a row, proven in CI on every push.