Ship AI agents with confidence.

Pre-deploy regression testing for multi-agent LLM systems. Replay proposed prompt, model, and agent changes against your recorded production traces — byte-identical where it doesn't need to change, targeting ~85% lower replay cost than re-running live.

The counterfactual gap.

Agent regressions surface in production. Faithful replay answers “what happened.” Naive full re-execution reintroduces sampling noise and burns tokens. Neither tells you whether your proposed prompt change would have broken customer 27 in yesterday's traces.

How it works.

1. 1

   Record.

   Wrap your LangGraph app. ConeReplay captures every LLM call, tool invocation, and cross-agent message — each tagged with a per-turn causal vector clock.

2. 2

   Replay with a twist.

   Propose a change. ConeReplay computes the causal cone of affected events. Out-of-cone events are served byte-identically from the recording. In-cone events re-execute with deterministic, content-hash-derived seeds.

3. 3

   Review.

   Get a divergence report per trace — or aggregated across a corpus — straight into your PR. Ship only changes that do what you intended.

<1s and 100% measured on the v0.1 synthetic benchmark corpus; ~85% is the design target from the patent specification, pending live-oracle measurement.

Quickstart.

What a pilot looks like in code. The SDK ships to you at beta onboarding — recording is two lines.

# Beta SDK — delivered at onboarding
# Record production traces
from conereplay import Recorder
from conereplay.sdk.langgraph import attach_to_langgraph_app

recorder = Recorder(store_path="./traces")
attach_to_langgraph_app(my_app, recorder)

# Replay a proposed change against the recorded corpus
$ conereplay corpus --traces ./traces --modify change.json --report report.html

Start with a paid pilot: the migration audit.

Model deprecations are forced migrations — another wave lands every few months. Before you flip the switch, know exactly which of your production conversations would have gone differently on the new model.

Fixed scope, fixed price. Two pilot slots per month.