---
title: Checks
description: Deterministic server-side assertions that run on every finished run. No LLM cost.
section: verify
order: 2
---

# Checks

A deterministic, server-side assertion against a finished run's output. Pass or fail with metadata. Configured per agent in the dashboard. No LLM cost.

Use checks for things expressible as a rule. Save LLM-as-judge for things that require taste.

## Check types

| Type | What it asserts |
|------|-----------------|
| JSON schema | Output conforms to a schema |
| Regex match | Output matches (or doesn't match) a pattern |
| Length bounds | Output length within N to M characters or tokens |
| Required fields | Output object contains specific keys |
| Tool-call assertion | Agent did (or didn't) call tool X |
| Numeric range | Numeric output falls within bounds |

Each check returns `pass` or `fail` with metadata like `{"expected": "100-500", "got": 47}`. Multiple checks evaluate independently; one failure doesn't short-circuit the rest.

A failing check can mark the run with a badge, feed into the score distribution (`status='success' AND all checks passed` is the success criterion for cost-per-successful-run), and trigger an alert on the same routes Pulse uses.

## Tier availability

| Tier | Checks |
|------|--------|
| Starter | Basic (length, required fields, simple regex) |
| Team | Full (schema, tool-call, complex regex, numeric) |
| Business | Full |
| Enterprise | Full |

## Example: schema check

A `support-triage` agent returns:

```json
{
  "department": "billing",
  "severity": 2,
  "reasoning": "Customer asked about an invoice"
}
```

The schema pins the contract:

```json
{
  "type": "object",
  "required": ["department", "severity"],
  "properties": {
    "department": {"enum": ["billing", "support", "engineering"]},
    "severity": {"type": "integer", "minimum": 1, "maximum": 5}
  }
}
```

Runs that come back with a different shape or unknown department fail the check immediately. The dashboard surfaces the diff; failures cluster so a prompt regression appears as one incident.

:::tip
Checks are the right first move on a new agent. Pin the output contract first, add a rubric later if scoring requires taste. Pinning shape catches most regressions without spending a token.
:::