diff --git a/.mintlify/components.md b/.mintlify/components.md index 3e3c2baa..b3d7f657 100644 --- a/.mintlify/components.md +++ b/.mintlify/components.md @@ -61,9 +61,12 @@ Deprecated is not a maturity level — it is where a feature goes after GA. Its | Condition | Badge | | --- | --- | | Enterprise plan | `Enterprise` | +| AI add-on, on any plan | `AI add-on` | | Self-hosted deployments only | `Self-hosted` | | Lightdash Cloud only | `Cloud` | +The four values and every gated feature that carries one are mapped on [feature availability](../support/feature-availability.mdx) — the availability counterpart to feature maturity levels. A page whose gate changes updates that map in the same change. + **A badge gates, it never labels.** It answers whether the reader can use the thing, and a reader who cannot is meant to stop. A badge describing what the page is about — the tool it uses, the surface it covers — fails the test, because that badge could be justified on any page and so distinguishes none of them. If the page's area, title, or first sentence already implies it, it is a label. **The colour carries the axis, the icon carries the value.** Availability is blue throughout, so a reader learns that blue means "who can reach this" and reads the icon for which condition. Lifecycle spends its colours on urgency instead: orange for the earliest stage, purple for the settled-but-moving one, grey for the one on its way out. diff --git a/.mintlify/ia-map.yml b/.mintlify/ia-map.yml index bae5b8e0..6394b642 100644 --- a/.mintlify/ia-map.yml +++ b/.mintlify/ia-map.yml @@ -113,7 +113,7 @@ self-host/nats-workers: for: Offloaded query execution. support: - for: Getting help and diagnosing problems. + for: Getting help, diagnosing problems, and the cross-cutting explainers badges point at — feature maturity and availability. api-reference/v1/introduction: for: OpenAPI-generated endpoint reference and SDKs. diff --git a/agents.mdx b/agents.mdx index 72b6b863..0a3a8dac 100644 --- a/agents.mdx +++ b/agents.mdx @@ -3,9 +3,9 @@ title: "AI agents" description: "Ask questions in plain language and get governed answers, charts, and dashboards from your metrics" --- - - AI agents are available as an add-on for all plans. [View pricing](https://www.lightdash.com/pricing) - +import AiAddOnAvailability from '/snippets/ai-add-on-availability.mdx'; + + Lightdash AI agents let your team ask questions in natural language and get answers built from your semantic layer — the saved dashboards, metrics, dimensions, joins, and descriptions you've already defined. An agent picks the relevant models and metrics, builds and runs the query with the right filters and [parameters](/semantic-layer/parameters), and returns the result as the chart, table, or summary that fits the question. Because every answer runs through the semantic layer, it respects the same project permissions and user attributes as the rest of Lightdash. diff --git a/agents/agent-context.mdx b/agents/agent-context.mdx index 6416d75e..7b7ad0b4 100644 --- a/agents/agent-context.mdx +++ b/agents/agent-context.mdx @@ -5,6 +5,10 @@ description: "Give every agent in a project the same terminology, table choices, doc-type: reference --- +import AiAddOnAvailability from '/snippets/ai-add-on-availability.mdx'; + + + Agent context is shared background knowledge every AI agent in a project reads before answering. It lives in a single file, `lightdash.project_context.yml`, that sits next to `lightdash.config.yml` inside your dbt project directory. Notes you add here change future agent behavior without changing the semantic layer. The file is committed to your dbt repo and travels with the rest of your project metadata. diff --git a/agents/agents-as-code.mdx b/agents/agents-as-code.mdx index 293f9cea..5d7118a8 100644 --- a/agents/agents-as-code.mdx +++ b/agents/agents-as-code.mdx @@ -5,6 +5,10 @@ description: "Download AI agents to YAML, review them in Git, and promote them b doc-type: reference --- +import AiAddOnAvailability from '/snippets/ai-add-on-availability.mdx'; + + + You can serialize a project's AI agents to YAML with the Lightdash CLI, keep them under version control, and promote them between environments — preview, staging, production — using the standard `lightdash download` / `lightdash upload` flow. Use agents as code when you want to: diff --git a/agents/ai-coding-agent.mdx b/agents/ai-coding-agent.mdx index 3a337554..4f15de78 100644 --- a/agents/ai-coding-agent.mdx +++ b/agents/ai-coding-agent.mdx @@ -1,14 +1,13 @@ --- -title: AI coding agent (Beta) +title: AI coding agent description: Ask an agent in chat to edit any connected repository and open a pull request doc-type: tutorial +tag: "Beta" --- - - The AI coding agent is currently in Beta and gated by a feature flag. It is an - **enterprise** feature. Contact Lightdash support to enable it for your - organization. - + + Beta AI add-on Off by default even where agents are enabled — contact Lightdash support to turn it on for your organization. [What Beta means](/support/feature-maturity-levels). [What each availability level means](/support/feature-availability). + The AI coding agent lets you ask an AI agent in chat to change files in **any repository your organization has connected to Lightdash** — not only the dbt repo behind a project — and have the agent open a pull request (or GitLab merge request) with the change. diff --git a/agents/ai-writeback.mdx b/agents/ai-writeback.mdx index 28d71e7f..28850f29 100644 --- a/agents/ai-writeback.mdx +++ b/agents/ai-writeback.mdx @@ -4,9 +4,13 @@ description: Ask an AI agent to edit your dbt project in chat and open a pull re doc-type: tutorial --- +import AiAddOnAvailability from '/snippets/ai-add-on-availability.mdx'; + + + AI writeback lets you ask an AI agent in chat or Slack to change something in the dbt repository that backs your project — rename a metric, add a dimension, edit a model's SQL, fix a YAML description — and have the agent open a pull request (or GitLab merge request) with the change. -This is the same writeback capability you would normally trigger from the Custom Metric or SQL Runner menus, surfaced inside the conversation with your AI agent. +This is the same capability you would normally trigger from the Custom Metric or SQL Runner menus, surfaced inside the conversation with your AI agent. Triggering it from those menus is [dbt write-back](/integrations/dbt/write-back), which is available to every Lightdash user with Developer access — it is asking an *agent* to do it that needs the add-on. For changes that don't belong in the dbt project — for example, editing an app repo, a service, or a docs site — use the [AI coding agent](/agents/ai-coding-agent) instead. It runs on the same E2B + Anthropic pipeline but targets any repository your organization has connected, and delegates verification to that repository's own CI. diff --git a/agents/autopilot.mdx b/agents/autopilot.mdx index 70a486a7..7ba78aba 100644 --- a/agents/autopilot.mdx +++ b/agents/autopilot.mdx @@ -7,7 +7,7 @@ tag: "Beta" --- - Beta Autopilot is available on **Enterprise** and **Cloud Pro** plans only. [What Beta means](/support/feature-maturity-levels). + Beta AI add-on Cloud Pro and above, and self-hosted instances with an Enterprise license. [What Beta means](/support/feature-maturity-levels). [What each availability level means](/support/feature-availability). Autopilot is a scheduled agent that runs against a project on its own and keeps it healthy. Each run, it reviews recent activity, finds problems, fixes what it safely can, and flags the rest for review. diff --git a/agents/create-evaluation-suites.mdx b/agents/create-evaluation-suites.mdx index 298d2f60..8e5ea463 100644 --- a/agents/create-evaluation-suites.mdx +++ b/agents/create-evaluation-suites.mdx @@ -4,6 +4,10 @@ description: "Test and validate your AI agent's performance with custom evaluati doc-type: tutorial --- +import AiAddOnAvailability from '/snippets/ai-add-on-availability.mdx'; + + + Create custom evaluation suites to batch test your agent's performance and ensure consistent, high-quality responses across different scenarios. diff --git a/agents/data-access.mdx b/agents/data-access.mdx index 35df4808..0fe4795e 100644 --- a/agents/data-access.mdx +++ b/agents/data-access.mdx @@ -4,6 +4,10 @@ description: How agents reach your data, and how to scope them with tags and use doc-type: reference --- +import AiAddOnAvailability from '/snippets/ai-add-on-availability.mdx'; + + + AI agents offer flexible data access control to balance insights with privacy and security. By default, agents have data access enabled, and you can disable it per agent when you want metadata-only behavior. ## Data access modes diff --git a/agents/deep-research.mdx b/agents/deep-research.mdx index 3fc15286..a98fa3ba 100644 --- a/agents/deep-research.mdx +++ b/agents/deep-research.mdx @@ -7,7 +7,7 @@ tag: "Beta" --- - Beta Deep research is available wherever [AI agents](/agents/set-up-agents) are enabled, including eligible AI trials. Lightdash Cloud enables the feature flag by default. Self-hosted deployments need the same Enterprise Edition license and AI provider configuration required by AI agents, and must enable the `ai-deep-research` feature flag. [What Beta means](/support/feature-maturity-levels). + Beta AI add-on Available wherever [AI agents](/agents/set-up-agents) are enabled, including eligible AI trials. Lightdash Cloud turns the feature flag on by default; self-hosted deployments enable the `ai-deep-research` flag alongside the license and model provider that agents already require. [What Beta means](/support/feature-maturity-levels). Deep research is a long-running mode for Lightdash AI agents. It is designed for questions that need several queries, competing explanations, and a reusable report rather than one immediate answer. diff --git a/agents/enable-ai-router.mdx b/agents/enable-ai-router.mdx index 21b961ea..0e9363e0 100644 --- a/agents/enable-ai-router.mdx +++ b/agents/enable-ai-router.mdx @@ -5,9 +5,9 @@ description: "Automatically route questions to the best-fit agent, so users don' doc-type: tutorial --- - - The AI Router is part of the AI agents add-on. [View pricing](https://www.lightdash.com/pricing) - +import AiAddOnAvailability from '/snippets/ai-add-on-availability.mdx'; + + When you have more than one AI agent in a project, users have to know which agent to ask. The **AI Router** removes that decision: type a question, and Lightdash picks the agent best suited to answer it. diff --git a/agents/issues.mdx b/agents/issues.mdx index 778611f5..502e3dab 100644 --- a/agents/issues.mdx +++ b/agents/issues.mdx @@ -7,7 +7,7 @@ tag: "Beta" --- - Beta Issues is available on **Enterprise** and **Cloud Pro** plans. It is **off by default** and must be enabled by an organization admin. [What Beta means](/support/feature-maturity-levels). + Beta AI add-on Cloud Pro and above, and off by default — an organization admin has to turn it on. [What Beta means](/support/feature-maturity-levels). [What each availability level means](/support/feature-availability). The Issues board is where data problems get tracked. Two things land on the same board: diff --git a/agents/lightdash-mcp.mdx b/agents/lightdash-mcp.mdx index 2e86394b..2e681341 100644 --- a/agents/lightdash-mcp.mdx +++ b/agents/lightdash-mcp.mdx @@ -4,9 +4,9 @@ description: "Connect Claude, ChatGPT, and Codex to your Lightdash data over the doc-type: reference --- - - Available to all Lightdash Cloud users. - + + Cloud Available on every Lightdash Cloud plan. Self-hosted instances need an [Enterprise license key](/self-host/enterprise-features#mcp) and `MCP_ENABLED=true`. [What each availability level means](/support/feature-availability). + The [Model Context Protocol (MCP)](https://modelcontextprotocol.io/) lets external AI assistants — Claude, ChatGPT, OpenAI Codex, and custom agents — connect to Lightdash and query your data directly. Lightdash runs the MCP server and your assistant is the client, so it can explore your data models, search for metrics and dimensions, run queries, and surface data-driven insights through natural conversation. MCP uses secure OAuth authentication and respects all your existing access controls, so data stays protected. diff --git a/agents/set-up-agents.mdx b/agents/set-up-agents.mdx index 58c8aa15..d8f6e179 100644 --- a/agents/set-up-agents.mdx +++ b/agents/set-up-agents.mdx @@ -5,6 +5,10 @@ description: Enable AI features, create your first agent, scope its data, and co doc-type: tutorial --- +import AiAddOnAvailability from '/snippets/ai-add-on-availability.mdx'; + + +