# Agents and guardrails

> Where agent behaviour, the guardrails and cost limits, and model routing are documented — one page per settings page, with a map from this chapter's old sections.

_Concept · Updated 2026-10-17 · Describes release 0.1.164_

Three pages control how the pillar agents behave in your workspace: **Agent behaviour** (`/portal/agents`), **AI models** (`/portal/settings/models`) and **Guardrails & cost** (`/portal/guardrails`). Everything on them is policy. None of it can weaken the safety floors: the write gate, PII scrubbing at the storage chokepoints and the read-only estate scan are code, not settings. Tuning changes *how much* the agents do and *how well* — never *whether* a human decides a write. This chapter is now one page per settings page; what counts as a write for a given connector stays in **Datasources** → *The read/write gate in detail*, and every term is defined once in the **Glossary**.

## The pages {#the-pages}

- [Configure the agents](/help/configure-the-agents.md) — the seven pillar agents and the **Agent behaviour** page: enablement, the prompt layer, schedules, a model override and extra approval gates, with the procedures.
- [Models, tiers and routing](/help/models-tiers-and-routing.md) — which model serves each tier, what you inherit, the bring-your-own endpoint and its prices, smart escalation, model residency and the set-up procedure from the demo.
- [Guardrails and cost limits](/help/guardrails-and-cost-limits.md) — the write posture, the always-on floors, budgets and the cost cap, PII patterns, egress, the switches around a fix, validation checks, risk exceptions, unmanaged changes and data retention.
- [Approval policy and change tiers](/help/approval-policy.md) — who may release what: the write floor, risk tiers, roles, change classes, windows and the automatic lanes.

## Where the old sections went {#where-the-old-sections-went}

| Old section | Now |
|---|---|
| Three layers · The pipeline · The seven pillar agents · A disabled agent still receives alerts | [Configure the agents](/help/configure-the-agents.md#three-layers-in-precedence-order) |
| Which posture your deployment runs | [Guardrails and cost limits](/help/guardrails-and-cost-limits.md#which-posture-your-deployment-runs) |
| The Agents page, field by field, and its three procedures | [Configure the agents](/help/configure-the-agents.md#the-agents-page-field-by-field) |
| Model tiers: which call uses which tier, what you inherit, the endpoint, prices, when the platform upgrades the model, tier suggestions | [Models, tiers and routing](/help/models-tiers-and-routing.md#model-tiers) |
| Guardrails: the floors, budgets, the cost cap, PII, egress, pre-approved operations, the switches, change safety, P1/P2 analysis, validation checks, risk exceptions, unmanaged changes, data retention | [Guardrails and cost limits](/help/guardrails-and-cost-limits.md#the-floors-you-cannot-switch-off) |
| Where the money went: cached prompt reads | [Models, tiers and routing](/help/models-tiers-and-routing.md#where-the-money-went-cached-prompt-reads) |
| Model residency policy | [Models, tiers and routing](/help/models-tiers-and-routing.md#model-residency-policy) |
| Use cases, troubleshooting, limits and gotchas | Each page keeps the rows about its own settings page |


## Next steps

- Next: [Configure the agents](/help/configure-the-agents.md)
- [All Administer a workspace pages](/help/administer-a-workspace/llms.txt)
- [Documentation home](/help/)