checkout-service p99 response time hit 412ms over the last 30 minutes, well above the 125ms SLO baseline. Correlated with a 2.8x spike in error_rate for the payments upstream; deploy d-4821 rolled out 38 minutes ago.
How an agent works
An agent watches one thing and acts on it. Not a workflow, just a standing watch that usually does nothing and acts the moment it should.
You stay in control
An agent does what you'd do, and only what you've authorized.
The same trusted numbers
It acts on the same governed metrics as your dashboards, and every action is logged and traceable.
You approve anything that writes
It alerts and recommends on its own; anything that changes data is yours to approve.
Try it on a test channel first
Point a new agent at a throwaway channel and watch its judgment before it touches anything real.
No false alarms
It remembers what it already flagged and waits before acting again, so it won't alert you about the same thing twice.
What you can put an agent on
Catch SLO drift before your users notice
It correlates your Prometheus latency and error-rate metrics with deploy events and product usage data, and flags the moment a service breaks its SLO baseline, with the likely cause already identified, so you can roll back or scale before customers file tickets.
Surface capacity pressure before it saturates
When CPU, memory, or disk utilization trends toward a threshold, it tells you which services are affected, how fast they are growing, and how long until saturation at current rate, so capacity planning stops being a quarterly guess and starts being a standing watch.
Flag metric anomalies with the blast radius
When a metric breaks its trend, it surfaces the affected labels, the magnitude of the deviation, and the downstream services involved, so you know whether it is noise or an incident before the on-call page fires.
Run any Python it needs to get the job done
Beyond alerts and write-backs, an agent can run arbitrary Python, so it can do whatever the task actually requires: call an API, kick off a job, reshape the data, or wire into your own tooling. The action space is yours to define.
Why not just build it yourself?
You could rig one of these with a cron job and a Slack webhook in an afternoon. The watching is the easy part. Here's what you'd own forever, and don't, here:
- →The cross-source join: not one tool's data, but it reconciled against the rest of your stack
- →A trusted, consistent metric: the same number your dashboards use
- →The investigation into why, when something fires
- →A full audit trail of everything it did
- →The upkeep, when the schema drifts or the script breaks at 2am
The data it works from
Every Prometheus object, modeled and query-ready the moment you connect.
It runs on your real Prometheus instance (noisy exporters, label cardinality explosions, and stale time series included), not a tidy demo.
Where it acts
Slack
A message in the channel you choose, with the context and a button to act on it.
A summary in the inbox of the people who need to see it.
Webhook
A payload to your own systems, to wire the agent into whatever you already run.
Warehouse write-back
A flag written back to your warehouse for everything downstream to pick up.
Hand off to Fi
Kick the question to Fi to investigate the why and propose the fix.
MCP
Expose it to your own agents and tools over MCP, and drive it from your stack.
Run it in your own VPC or fully self-hosted. Everything it does is pure SQL and Python you can inspect.
Build your agents with Fi
Fi is your AI analyst. It helps you build and customize everything in Definite, including the agents that watch and act.
Fi
Your AI analyst. Ask questions in plain English, and let it help you build and customize everything in Definite, including your agents.
Meet Fi →Agents
The watchers and actors. Once you've built one, it runs on its own, keeping an eye on what matters and acting the way you would.
Autonomous agents →Get started
- 1Connect Prometheus, and the sources it needs to reconcile against. Synced and modeled in an afternoon.
- 2See the numbers tie out to what you already trust.
- 3Put an agent on one thing you can't afford to miss. Fi helps you build it.