# Duku AI Docs

## Docs

- [Overview](https://docs.duku.ai/welcome-to-dukuai/overview.md)
- [Create a Product](https://docs.duku.ai/getting-started/create-a-product.md): Create the top-level container for your targets, explorations, and results.
- [Run Your First Exploration](https://docs.duku.ai/getting-started/run-your-first-exploration.md): Start an exploration and understand what Duku captures.
- [Review Results](https://docs.duku.ai/getting-started/review-results.md): Review the state graph, errors, and screenshots from an exploration.
- [Products & Targets](https://docs.duku.ai/core-concepts/products-and-targets.md): Understand how products and targets relate.
- [Explorations & State Graphs](https://docs.duku.ai/core-concepts/explorations-and-state-graphs.md): Learn how Duku discovers states, transitions, and graphs.
- [Goals & Intent Tests](https://docs.duku.ai/core-concepts/goals-and-intent-tests.md): Understand goals, intents, and how intent tests work.
- [Overview](https://docs.duku.ai/viewport-dashboard/overview.md): See high-level metrics for your organisation.
- [Issues](https://docs.duku.ai/viewport-dashboard/issues.md): Review distinct problems found across your app.
- [Products](https://docs.duku.ai/viewport-dashboard/products.md): Manage the applications and websites your organisation tests.
- [Targets](https://docs.duku.ai/viewport-dashboard/targets.md): Inspect targets, goals, and run history for a deployment.
- [Exploration](https://docs.duku.ai/viewport-dashboard/exploration.md): Review the state graph and runs table for a target.
- [Tests](https://docs.duku.ai/viewport-dashboard/tests.md): Review saved journeys, replay trends, and test runs.
- [Schedules](https://docs.duku.ai/viewport-dashboard/schedules.md): Automate recurring runs for a target.
- [Settings](https://docs.duku.ai/viewport-dashboard/settings.md): Manage API keys, members, and organisation settings.
- [API Keys](https://docs.duku.ai/integrations/api-keys.md): Generate and use API keys for programmatic access.
- [GitHub Actions](https://docs.duku.ai/integrations/github-actions.md)
- [CI integration with GitHub Actions](https://docs.duku.ai/integrations/github-actions/ci-integration-with-github-actions.md): Start Duku from pull requests, deploys, and scheduled workflows.
- [Quickstart: preview action](https://docs.duku.ai/integrations/github-actions/quickstart-preview-action.md): Start Duku automatically for pull request previews.
- [Quickstart: environment action](https://docs.duku.ai/integrations/github-actions/quickstart-environment-action.md): Start Duku automatically for stable environments.
- [Choosing preview vs environment](https://docs.duku.ai/integrations/github-actions/choosing-preview-vs-environment.md): Decide which action fits your deployment model.
- [Configuration reference](https://docs.duku.ai/integrations/github-actions/configuration-reference.md): Review inputs, outputs, secrets, and versioning.
- [Troubleshooting](https://docs.duku.ai/integrations/github-actions/troubleshooting.md): Fix common setup and runtime issues.
- [GraphQL API](https://docs.duku.ai/integrations/graphql-api.md): Query Duku data and trigger runs programmatically.
- [Firewall & WAF Allowlisting](https://docs.duku.ai/integrations/firewall-and-waf-allowlisting.md): Allowlist Duku egress IPs in your firewall, WAF, or bot-management platform.
- [Overview](https://docs.duku.ai/roles-and-permissions/overview.md): Understand what Members and Admins can do.
- [Release Notes](https://docs.duku.ai/changelog/release-notes.md)


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information, you can query the documentation dynamically by asking a question.
Perform an HTTP GET request on a page URL with the `ask` query parameter:
```
GET https://docs.duku.ai/welcome-to-dukuai/overview.md?ask=<question>
```
The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.
Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.