BROCS
O ยท Observability, control theory

Observe

Metrics, traces, and alerts for AI systems, exposed to the people who own them. Including the failures that return a 200 and look like nothing.

View as Markdown
Metrics golden signals plus tokens, cost, tool calls
Traces reconstruct what an agent did, with what, on what data
Alerts routed to the builder who owns the app
What matters signals that predict incidents, not dashboard decoration
Model behavior drift, silent provider updates, quality regressions

Observe is the part of the surface concerned with seeing what your AI systems are actually doing: the numbers that say whether it works, the traces that say what it did, the alerts that reach the right person, and the measurements that catch quality moving underneath you.

It is the letter organizations most often think they have covered because they have a monitoring stack. The monitoring stack is necessary and it will not catch the failure that matters most here.

The claim

Traditional monitoring detects systems that stop working. The characteristic AI failure is a system that keeps working and gets worse: the same latency, the same status code, a worse answer. Nothing on a conventional dashboard moves.

That has two consequences. The first is that quality needs its own measurement, which means evals, canaries, and a way for users to flag a bad answer. The second is that traces are not a debugging luxury. They are the only record of what an agent did, and they are what an auditor will ask for.

The tests that matter

  1. Cost, attributed. Can you say what one application cost last month, without asking a vendor?
  2. Reconstruction. For a specific agent run last week, can you list every tool call and every argument?
  3. Who finds out first. If output quality dropped 20 percent tomorrow, would it be your measurement or your customer?

The tension

Observe pulls against Secure more than people expect. The most useful trace is the most complete one, and the most complete one is full of prompts, tool arguments, and retrieved documents, which is to say full of exactly the data you are trying to protect. Redaction, retention, and access control on the telemetry itself are part of the job rather than an afterthought.

Observe hands off to Control: measurement without an actuator is a thermometer, not a loop.

In this part of the surface

  • Metrics: Golden signals plus the AI signals: tokens, cost, tool calls, and refusal rate, attributed per app, per team, and per user.
  • Traces: Reconstructing what an agent did: prompts, tool calls, arguments, results, and the data it touched.
  • Alerts: Routing alerts to the builder who owns the application, not only to a central operations queue.
  • What matters: Which signals predict incidents and which are dashboard decoration, and how to expose observability to people who are not on the platform team.
  • Model behaviour: Drift, silent provider updates, and quality regressions: the failures that return a 200 and look like nothing on a dashboard.
O → C Observe hands off to Control. Keep a hand on the wheel.