Pre-merge performance gate

Your AI wrote it.
Nobody read it.

ShadowTel replays real production traffic against every pull request and blocks the merge if the change makes your system slower, less reliable, or more expensive to run.

ShadowTel / traffic-replay  · PR #482 Refactor payment processing loop Required
Running traffic replay…
  • p95 latency18ms412msFAIL
  • error rate0.02%1.80%FAIL
  • cost / 1k req$0.11$0.34FAIL
  • memory (rss)512MB754MBWARN
Replayed 12,450 requests over 180s against production baseline.

Review stopped scaling

Agents write code faster than any team can read it. The checks that used to catch expensive changes were people, and the people are underwater.

+31%

Code merging with no review at all — not human, not agentic.

3.4×

Production incidents per code change.

+441%

Median time senior engineers spend in code review.

Faros AI Engineering Report 2026 — two years of telemetry from 22,000 developers across 4,000 teams.

How it works

No new agent in your request path. No staging environment to maintain.

01 — MIRROR

Point a slice of live traffic at us

Request mirroring you already have in Envoy, nginx, or your service mesh. No code changes.

02 — REPLAY

Every PR gets a disposable sandbox

We replay the mirrored traffic against it, holding writes and outbound calls inside the sandbox.

03 — GATE

Pass or fail on the pull request

Compared against your OpenTelemetry baseline, with the dollar delta attached. You set the budgets.

Built to be side-effect free

A gate with authority to stop a deploy has to be safe before it is useful.

Writes stay in the sandbox

Mutating requests are held or served by sandbox-local stand-ins. They never reach production data stores.

Outbound calls are intercepted

Payment providers, email, and third-party APIs are stubbed at the sandbox boundary. Nothing bills, nothing sends.

Production is untouched

Mirroring is fire-and-forget at your proxy. Your users' requests are never held waiting on us.

Want to be one of the first five
teams to run it?

I'm looking for design partners already shipping agent-written code and feeling it. Half an hour, no deck.

Book a call
Deterministic Open source Cost-aware Blocking