diff --git a/docs.json b/docs.json index 15691dd7..3127d79e 100644 --- a/docs.json +++ b/docs.json @@ -154,7 +154,6 @@ "guides/ai-agents/evaluations", "guides/ai-agents/data-access", "guides/ai-agents/best-practices", - "guides/ai-agents/self-improvement", "guides/ai-agents/ai-writeback", "guides/ai-agents/mcp-servers", "guides/ai-agents/autopilot" diff --git a/guides/ai-agents.mdx b/guides/ai-agents.mdx index 70580d73..d7d90a0a 100644 --- a/guides/ai-agents.mdx +++ b/guides/ai-agents.mdx @@ -43,8 +43,8 @@ This guide covers everything you need to know about AI agents in Lightdash: - - + + @@ -67,4 +67,4 @@ This guide covers everything you need to know about AI agents in Lightdash: - **Multiple agents** - Create specialized agents for different teams or use cases - **Evaluations** - Create test suites to validate your agent’s answers and prevent regressions. - **Conversations** - Monitor all agent interactions in one place, review feedback, and build evaluation sets directly from real threads. -- **Self-improvement (Beta)**- Agents can propose changes to your semantic layer \ No newline at end of file +- **AI writeback (Beta)** - Ask an agent to edit your dbt project in chat and open a pull request with the changes \ No newline at end of file diff --git a/guides/ai-agents/ai-writeback.mdx b/guides/ai-agents/ai-writeback.mdx index 986e274f..15455ff9 100644 --- a/guides/ai-agents/ai-writeback.mdx +++ b/guides/ai-agents/ai-writeback.mdx @@ -28,7 +28,6 @@ For other kinds of changes, the agent will pick a different tool: | --- | --- | | Ask a question about data | Query and discovery tools | | Edit an existing chart or dashboard in Lightdash | `editContent` | -| Propose an in-app change to a metric or dimension for review | `proposeChange` (see [Self-improvement](/guides/ai-agents/self-improvement)) | | Change the underlying dbt repository | `proposeWriteback` | ## Prerequisites @@ -94,4 +93,3 @@ When the pull request is ready, the agent posts the URL in the thread. Open it, ## Related - [dbt write-back](/guides/developer/dbt-write-back) — write back individual custom metrics, dimensions, and SQL Runner queries from the Lightdash UI. -- [Self-improvement](/guides/ai-agents/self-improvement) — let agents propose in-app changes to the semantic layer through reviewable changesets instead of pull requests. diff --git a/guides/ai-agents/getting-started.mdx b/guides/ai-agents/getting-started.mdx index 2d9469d5..62c47787 100644 --- a/guides/ai-agents/getting-started.mdx +++ b/guides/ai-agents/getting-started.mdx @@ -174,8 +174,8 @@ models: 3. For more technical users who want to configure tagging rules in more detail - including how tags interact with permissions and schema visibility - see the [Data access control section.](/guides/ai-agents/data-access#limiting-access-to-specific-explores-and-fields) -### Enable Self-Improvement (optional, Beta) -Allow your agent to propose changes to your semantic layer, including updating descriptions and creating new metrics. Changes are tracked in changesets for review. Read more on [self-improvement (beta)](/guides/ai-agents/self-improvement) feature. +### Enable AI writeback (optional, Beta) +Allow your agent to edit your dbt project from chat — renaming metrics, adding dimensions, or updating descriptions — and open a pull request with the changes for review. Read more on the [AI writeback (beta)](/guides/ai-agents/ai-writeback) feature. ## Setting up multiple agents diff --git a/guides/ai-agents/self-improvement.mdx b/guides/ai-agents/self-improvement.mdx deleted file mode 100644 index f0ee7cce..00000000 --- a/guides/ai-agents/self-improvement.mdx +++ /dev/null @@ -1,104 +0,0 @@ ---- -title: Self-improvement (Beta) -description: Enable AI agents to improve your semantic layer automatically ---- - - - This feature is currently in Beta. Enable it in your agent settings to start - testing with your team. - - -AI agents can now improve your semantic layer by proposing changes to your data models. When enabled, agents can update field descriptions, create new metrics, and refine your data documentation based on conversations and user feedback. All changes are tracked in changesets and can be reviewed or reverted at any time. - -## How it works - -When self-improvement is enabled, your AI agent can: - -1. **Propose changes** to your semantic layer during conversations -2. **Apply changes immediately** to a changeset (batch of changes) -3. **Track all modifications** with full history and attribution -4. **Allow review and rejection** of changes by authorized users - -Changes are visible in the chat interface and can be managed through the Project Settings > Changesets page. - - - - Self-improvement changes in chat updating a description of a dimension - - - Self-improvement changes in chat custom metric - - - -## What agents can improve - -**Update descriptions** for better documentation: - -- Explore descriptions to clarify data sources and use cases -- Metric descriptions to explain calculations and business logic -- Dimension descriptions to provide field context - -**Create new metrics** based on conversations: - -- Custom aggregations derived from existing dimensions - -**Suggest AI hints** for improved context: - -- Ask your agent to recommend AI hints for dimensions, metrics, or tables -- AI hints take precedence over descriptions and aren't visible to end users - -## Enabling self-improvement - -Only admins and developers can enable and use self-improvement. To enable self-improvement for an agent: - -1. Go to your agent settings -2. Toggle the "Enable Self-Improvement" switch -3. Save your changes - - - Enable self-improvement toggle - - -## Managing changes - -All proposed changes are tracked in changesets, which you can access from Project Settings: - -**View all changes:** - -- Navigate to Project Settings > Changesets -- See a complete list of proposed changes with details about what was modified -- View who proposed each change and when - - - Self-improvement changes in changeset view from project settings - - -**Review changes in chat:** - -- Each proposed change appears as a card in the conversation -- Click "View Changeset" to see the full details -- Use the "Reject" button to revert changes you don't want - -**Revert changes:** - -- Individual changes can be rejected directly from the chat interface -- Use "Revert" in the changesets page to undo specific changes -- Use "Revert All" to undo multiple changes at once -- If a project is re-deployed, the changeset will be applied if possible - - - Once a change is reverted, the action cannot be undone. The semantic layer - will return to its previous state for that field or metric. - diff --git a/images/guides/ai-agents/enable-self-improvement.png b/images/guides/ai-agents/enable-self-improvement.png deleted file mode 100644 index 55dc37f5..00000000 Binary files a/images/guides/ai-agents/enable-self-improvement.png and /dev/null differ diff --git a/images/guides/ai-agents/self-improvement-chat-1.png b/images/guides/ai-agents/self-improvement-chat-1.png deleted file mode 100644 index cb7de80e..00000000 Binary files a/images/guides/ai-agents/self-improvement-chat-1.png and /dev/null differ diff --git a/images/guides/ai-agents/self-improvement-chat-2.png b/images/guides/ai-agents/self-improvement-chat-2.png deleted file mode 100644 index c7017f34..00000000 Binary files a/images/guides/ai-agents/self-improvement-chat-2.png and /dev/null differ