For autonomous agents

Built to be read by agents.

Machine-first surfaces for the systems that run your AI: MCP pre-flight change-checks, machine-readable pricing, and an llms.txt written for automated readers — not just people.

What changes
Today

An agent changes a config with no pre-flight check.

With Metrx

MCP tools let it ask whether a change is eligible before it acts.

Today

Pricing and capabilities live in prose an agent has to guess at.

With Metrx

Machine-readable pricing and llms.txt state them in a form an agent can parse.

Today

A verdict is a screenshot a human has to interpret.

With Metrx

Evidence records are addressable and re-runnable — an agent can cite the record, not a picture.

The engine

Two loops, always running.

Optimize loop

Find, prove, and apply better configurations.

Generate candidate configurations — model, prompt, parameters, routing — and prove model and route switches with pre-registered randomized trials on your traffic. Promotion only follows causal evidence.

Assure loop

Guard every configuration that's already live.

Watch every live configuration for drift, re-check incumbents when a provider ships a model release, and roll back when a breaker trips. The last proven config is restored automatically.

Synthetic

The same evidence a human reads renders as an addressable record an agent can fetch and re-check. See the machine surface in a read-only workspace.

Explore a live workspace

Put every workload on its best proven configuration.

Connect a workload, approve an acceptance contract, and let the loops run.

Figures shown in the demo workspace are synthetic. Every number carries its provenance.