> ## Documentation Index
> Fetch the complete documentation index at: https://docs.prysm1.com/llms.txt
> Use this file to discover all available pages before exploring further.

# AgentGuard

> Cost guardrails that keep autonomous agents from overspending — per-request caps, monthly budgets, and model blocks.

AgentGuard is PRYSM's spend-control layer. It turns "please don't let the agent burn
\$50 on a typo" into a declarative guarantee: per-request cost caps, monthly budgets, and
hard blocks on models you never want an agent to reach for.

<Note>
  AgentGuard rules are **guardrails** — in [routing precedence](/concepts/brain-md#routing-precedence)
  they run *after* model selection and always win over routing preferences. A cost cap
  or a compliance block can't be overridden by a rule or even a hard model lock.
</Note>

## Per-request cost caps

Set `max_cost_per_request` in your [BRAIN.md](/concepts/brain-md) (or pass it inline).
If the model PRYSM would pick costs more than the cap, PRYSM **downgrades** the request
to a budget model (`deepseek-v4-flash`) instead of failing.

```yaml BRAIN.md theme={null}
max_cost_per_request: 0.005   # USD
```

**How the estimate works.** PRYSM compares a fast pre-flight estimate —
`(input_price + output_price) × 0.001`, i.e. the blended per-MTok price at a \~1K-token
reference — against your cap. It's deliberately conservative and computed *before* the
call, so you're protected up front rather than billed and apologized to afterward.

<Tip>
  Use [`/route`](/api-reference/route) (or `client.route(...)`) to preview the estimated
  cost of a prompt before sending it — handy for testing that your cap behaves the way
  you expect.
</Tip>

### Example

```yaml BRAIN.md theme={null}
max_cost_per_request: 0.005
rules:
  - when: "writing"
    model: "claude-sonnet-4.5"   # est. ~0.018 > 0.005
```

A writing prompt matches the rule, but `claude-sonnet-4.5`'s estimate exceeds the cap,
so AgentGuard downgrades it to `deepseek-v4-flash`. To honor the preference, raise the cap to
at least the model's estimate or remove it.

## Monthly budgets

Set a soft monthly ceiling to get alerted as you approach it:

```yaml BRAIN.md theme={null}
monthly_budget: 50.00   # USD — alerts on approach
```

Track actual spend any time via [`/usage`](/api-reference/usage), which returns
`total_cost_usd` plus breakdowns by model, provider, and mode.

## Blocking models

List models an agent must never use — for cost, latency, or compliance reasons. A
blocked model is rerouted through your fallback chain:

```yaml BRAIN.md theme={null}
blocked:
  - gpt-5.2-pro      # too expensive
  - grok-4.1-heavy   # too slow

fallback:
  - deepseek-v4-flash
  - claude-haiku-4.5
  - gpt-5-nano
```

If routing (or a rule, or even a `model` lock) selects a blocked model, PRYSM walks the
`fallback` list and routes to the first allowed, available model. If you don't define a
`fallback`, PRYSM uses a sensible default order.

## Putting it together

A typical agent config combines all three: pin good defaults with rules, cap runaway
spend per request, and block the models you never want touched.

```yaml BRAIN.md theme={null}
# Prefer cheap-but-great models, never exceed a cent per call,
# and keep frontier models off the table entirely.
max_cost_per_request: 0.01
monthly_budget: 100.00

rules:
  - when: "code"
    model: "deepseek-v4-flash"
  - when: "writing"
    model: "claude-haiku-4.5"

blocked:
  - gpt-5.2-pro
  - claude-opus-4.6
  - grok-4.1-heavy

fallback:
  - deepseek-v4-flash
  - claude-haiku-4.5
```

## Why it matters for agents

Autonomous agents make many calls without a human in the loop. One mis-routed batch on a
frontier model can dwarf a month of normal usage. AgentGuard makes the cost ceiling a
property of your repository — reviewed in pull requests, enforced on every request, and
impossible for a prompt to talk its way around.

<CardGroup cols={2}>
  <Card title="Configure it in BRAIN.md" icon="file-code" href="/concepts/brain-md">
    Caps, budgets, blocks, and fallback chains — all version-controlled.
  </Card>

  <Card title="Audit spend with /usage" icon="chart-line" href="/api-reference/usage">
    Totals and per-model / per-provider / per-mode breakdowns.
  </Card>
</CardGroup>