> ## Documentation Index > Fetch the complete documentation index at: https://docs.lightdash.com/llms.txt > Use this file to discover all available pages before exploring further. # Choosing the right AI workflow in Lightdash > A practical guide to picking the right Lightdash AI surface for your user, task, and governance needs. Lightdash exposes multiple AI surfaces, and the right one depends on **who is asking**, **what they are trying to do**, and **how much governance you need**. This guide helps you decide which workflow to use for which task, and how they fit together. The common foundation across every surface is the **Lightdash semantic layer**: governed metrics, joins, descriptions, permissions, project context, verified answers, and evaluations. Investing there pays off no matter which AI surface a user picks. ## Quick decision tree Pick the first item that matches what you are trying to do: * **Want business users to ask governed questions in natural language?** Use [Lightdash AI agents in the app](/guides/ai-agents/using-ai-agents). * **Want the answer to happen in a shared team conversation?** Use [Lightdash AI agents in Slack](/references/integrations/slack-integration). * **Want Claude, Cursor, Codex, ChatGPT, or a custom agent to query Lightdash?** Use [Lightdash Data MCP](/references/integrations/lightdash-mcp). * **Want your AI coding tool to understand Lightdash docs and YAML syntax?** Use the [Lightdash Docs MCP](/guides/ai-overview#lightdash-docs-mcp) together with [agent skills](/guides/developer/agent-skills). * **Want to create or edit saved charts and dashboards interactively?** Use [AI agent content editing](/guides/ai-agents/content-tools) or MCP content tools where enabled. *(Beta)* * **Want bulk or reviewable dashboard edits?** Use [dashboards as code](/guides/developer/dashboards-as-code) with `lightdash download` and `lightdash upload`. * **Want to change a core metric, dimension, join, model, or description?** Edit dbt / Lightdash YAML, review through Git, and validate before deploy — or use [AI writeback](/guides/ai-agents/ai-writeback) where enabled. *(Beta)* * **Did the agent get something wrong?** Improve descriptions, AI hints, project context, [verified answers](/guides/ai-agents/verified-answers), [evaluations](/guides/ai-agents/evaluations), or [Reviews](/guides/ai-agents/reviews) findings. *(Reviews is Beta.)* ## Comparison | Workflow | Best for | Typical user | Output | Governance model | Related docs | | ------------------------ | ------------------------------------------------------------- | ------------------------------ | -------------------------------------------------------- | ------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | AI agents in app | Governed self-serve questions and visualizations | Business user | Answers, charts, saved threads | Agent-scoped tags, project permissions, user attributes | [AI agents](/guides/ai-agents), [Using AI agents](/guides/ai-agents/using-ai-agents), [Getting started](/guides/ai-agents/getting-started) | | AI agents in Slack | Shared team Q\&A on data | Business user, team channel | Threaded answers with charts | Same as in-app agents, plus Slack workspace scoping | [Slack integration](/references/integrations/slack-integration), [AI agents](/guides/ai-agents) | | Lightdash Data MCP | Querying Lightdash from external AI clients | Power user, developer, analyst | Model / metric discovery, metric queries, content lookup | OAuth, project permissions, user attributes | [Lightdash MCP](/references/integrations/lightdash-mcp), [AI router](/guides/ai-agents/ai-router) | | Lightdash Docs MCP | Giving coding agents Lightdash concept + YAML context | Developer with an AI IDE | Docs answers used inside the AI tool | Public docs, no auth | [Docs MCP](/guides/ai-overview#lightdash-docs-mcp) | | Agent skills | Teaching AI coding agents Lightdash YAML conventions | Developer / analytics engineer | Correct YAML, CLI usage, best practices | Local to the developer's machine | [Agent skills](/guides/developer/agent-skills) | | Content editing *(Beta)* | Interactive chart / dashboard creation and edits via an agent | Analyst, agent operator | New / updated saved charts and dashboards | Enabled per agent, scoped by agent permissions | [Content tools](/guides/ai-agents/content-tools), [Editing dashboards with agents](/guides/developer/editing-dashboards-with-agents) | | Dashboards as code | Bulk, reviewable, version-controlled dashboard changes | Developer / analytics engineer | YAML dashboards in a repo | Git review, previews, validation | [Dashboards as code](/guides/developer/dashboards-as-code) | | AI writeback *(Beta)* | Agent-proposed changes to dbt / Lightdash YAML | Analytics engineer | PRs / YAML edits for metrics, dims, descriptions | Feature flag, Git review, dbt / Lightdash validation | [AI writeback](/guides/ai-agents/ai-writeback) | | Reviews and evaluations | Improving agent accuracy over time | Agent owner, data lead | Verified answers, eval scores, review findings | Verified answers, evals suite, Reviews *(Beta)* | [Verified answers](/guides/ai-agents/verified-answers), [Evaluations](/guides/ai-agents/evaluations), [Reviews](/guides/ai-agents/reviews), [Best practices](/guides/ai-agents/best-practices) | ## Use AI agents for governed self-serve Lightdash AI agents in the app and in Slack are the **managed experience for business users**. They ask questions in natural language, and the agent answers using your saved dashboards, metrics, dimensions, joins, descriptions, and visualizations — all defined in the Lightdash semantic layer. Key points: * Agents respect **project permissions**, **space access**, and **user attributes**, so users only see data they are allowed to see. * Scope each agent to a **subset of models and tags** so it stays focused on a domain instead of the whole project. * Use **Slack** when the answer belongs in a team conversation; use the **in-app** experience when the user wants to iterate on charts and threads. * Reinforce the agent with descriptions, AI hints, verified answers, and evaluations rather than expanding scope. See [Using AI agents](/guides/ai-agents/using-ai-agents), [Data access](/guides/ai-agents/data-access), and [Best practices](/guides/ai-agents/best-practices). ## Use MCP when the user wants to stay in another AI tool The Lightdash Data MCP server lets external AI clients — Claude, Cursor, Codex, ChatGPT, or a custom agent — talk to Lightdash. It is best for **power users, developers, and external AI clients**, not as the primary end-user product for business teams. MCP supports: * **OAuth** login with the user's Lightdash identity. * The same **permissions and user attributes** as the rest of Lightdash. * **Model and metric discovery**, **metric queries**, and **content discovery** (dashboards, charts, saved queries). * Reusing agent context, so an MCP client can benefit from the same tags, hints, and verified answers as a Lightdash AI agent. MCP clients are **not** the same as the managed Lightdash AI agent UI. They give an external tool a governed pipe into Lightdash, but the UX, memory, sharing, and moderation live in whatever AI client the user chose. See [Lightdash MCP](/references/integrations/lightdash-mcp), [AI router](/guides/ai-agents/ai-router), and the [AI overview](/guides/ai-overview) for how the pieces fit. ## Use Git and YAML for durable definitions Changes to **metrics, dimensions, joins, model SQL, business logic, and descriptions** should live in **dbt or Lightdash YAML**. Route those changes through: * **Git review** — PRs, code owners, and diffs. * **Previews** — validate on a preview project before merging. * **Validation** — `lightdash validate`, dbt tests, and CI checks. * **Dashboards as code** — use `lightdash download` and `lightdash upload` for bulk or reviewable dashboard changes. * **AI writeback** *(Beta)* — let an agent propose YAML changes, but keep them behind the same review and validation gates. Ad-hoc agent edits are great for exploration; durable definitions belong in version control. ## Use feedback loops to improve agent quality If an agent gets something wrong, resist the urge to widen its scope. Instead, close the loop: * Improve **descriptions** and **AI hints** on the underlying models, metrics, and dimensions. * Add **project context** and refine the agent's tag scope. * Save good responses as **[verified answers](/guides/ai-agents/verified-answers)** so the agent reuses them. * Add **[evaluations](/guides/ai-agents/evaluations)** to catch regressions when you change context or prompts. * Use **thumbs up / thumbs down** and **[Reviews](/guides/ai-agents/reviews)** *(Beta)* findings to prioritize fixes. * If routine questions keep needing SQL, fix the **semantic layer**, not the prompt. ## Important cautions * **MCP is a power-user / developer surface.** It is not the main end-user product for business teams — direct most business users to Lightdash AI agents in the app or Slack. * **Raw SQL and the SQL Runner should be an escape hatch.** If routine questions require SQL, improve the semantic layer instead of relying on the agent to write SQL. * **Keep writeback and self-improvement controlled.** AI writeback, content editing, and Reviews are Beta — use previews, PR review, and validation before anything reaches production. * **Broad agents usually perform worse than focused ones.** Prefer several domain-specific agents scoped to a small set of tags and models over one project-wide agent. * **Do not upload sensitive context as knowledge documents** unless the entire agent audience is allowed to see it. Agent knowledge is visible to everyone who can use the agent. ## Related docs * [Using AI with Lightdash (overview)](/guides/ai-overview) * [AI agents](/guides/ai-agents) * [Using AI agents](/guides/ai-agents/using-ai-agents) * [Getting started with AI agents](/guides/ai-agents/getting-started) * [Data access](/guides/ai-agents/data-access) * [Best practices](/guides/ai-agents/best-practices) * [AI router](/guides/ai-agents/ai-router) * [Content tools](/guides/ai-agents/content-tools) *(Beta)* * [AI writeback](/guides/ai-agents/ai-writeback) *(Beta)* * [Reviews](/guides/ai-agents/reviews) *(Beta)* * [Verified answers](/guides/ai-agents/verified-answers) * [Evaluations](/guides/ai-agents/evaluations) * [Lightdash MCP](/references/integrations/lightdash-mcp) * [Slack integration](/references/integrations/slack-integration) * [Agent skills](/guides/developer/agent-skills) * [Dashboards as code](/guides/developer/dashboards-as-code) * [Editing dashboards with agents](/guides/developer/editing-dashboards-with-agents)