---
title: "AI governance, approvals and usage controls | Tale"
description: "Configure connector approvals, review recorded actions, set model usage budgets, and apply chat guardrails for your team and AI agents in Tale."
---
Governance

# Set the rules for your team and agents

Control access, configure connector approvals, and review recorded actions. Set model usage budgets and chat filters for the work your team and agents carry out.

## See the rules in the work

Inspect workflow runs, compare answers, and check the tools and sources available to agents.

01 Automations

### Follow the run and its decisions

A configured workflow can review an access report and prepare a notification. Inspect its steps, approval decisions, and recorded effects in the run detail.

> Illustrative demo: a configured scheduled workflow reviews an access report and prepares a Slack notification.

02 Agents

### Choose the tools the work needs

Equip each project agent with explicit tools and credentials. Managed model calls use Tale’s gateway controls; direct subscription access follows a different path.

> Illustrative demo: project agents with distinct responsibilities and selected models; their tools and permissions are configured separately.

## What does governance cover?

Choose which connector writes need approval, which tools agents may use, and which content and usage rules apply.

- 01Approve connector writesAutomation connector writes pause when your policy requires approval. External writes require it by default; reads and internal platform writes follow different rules.[Approval concepts](https://docs.tale.dev/platform/approvals/concepts)
- 02Inspect the proposed operationReview the destination and exact input before approving. Reject an incorrect operation, fix the workflow or input, and start a new run.[Approval concepts](https://docs.tale.dev/platform/approvals/concepts)
- 03Read the audit trailInspect recorded actions and approval decisions with their actor and time. Use the audit log to investigate what happened.[Audit logs](https://docs.tale.dev/platform/admin/governance/audit-logs)
- 04Set organization rulesConfigure shared instructions, access policies, and agent tool grants. Enforced permissions and filters complement the instructions you give a model.[Guardrails](https://docs.tale.dev/platform/admin/governance/guardrails)
- 05Configure chat content filtersEnable content safety, personal-data detection, and optional moderation for the chat directions you choose. Test the patterns and failure behavior your work needs.[Guardrails](https://docs.tale.dev/platform/admin/governance/guardrails)
- 06Set budgets for metered workTrack recorded model usage and set budget rules for supported paths, including managed agent runs. Direct subscription calls use the provider’s own controls.

## Governance FAQ

### What does governance control?

### Where do I decide a connector approval?

### Can I choose which connector writes require approval?

### Does every agent action wait for approval?

### How do content filters and data controls apply?

## Work you can try with your team

Start with a clear brief, defined deliverables, and a review process.

### Coordinate operations with AI agents

## Related modules

- [AutomationsRepeat workflows with triggers and approvals.](https://tale.dev/platform/automations)
- [ProjectsPlan, assign, and review work with your team.](https://tale.dev/platform/projects)
- [AgentsDelegate tasks to agents with their own tools and runtime.](https://tale.dev/platform/agents)
- [ChatsAsk questions, check sources, and hand off tasks.](https://tale.dev/platform/chat)

## Read the docs

- [Approval concepts](https://docs.tale.dev/platform/approvals/concepts)
- [Configure approvals](https://docs.tale.dev/platform/approvals/configure)
- [Approvals in workflows](https://docs.tale.dev/platform/automations/approvals-in-workflows)
- [Audit logs](https://docs.tale.dev/platform/admin/governance/audit-logs)
- [Guardrails](https://docs.tale.dev/platform/admin/governance/guardrails)

## See your team’s next workflow in Tale

Bring a task to a guided demo, or start a workspace and try it with your own agents.
