docs(core): rewrite GenBI guide around the agent workflow#2380
Merged
Conversation
Reframe guides/genbi.md as a conversation-first guide — how to ask an agent to create a dashboard and how to ask it to deploy — instead of a command walkthrough. Inline wren genbi build/register/verify/open/deploy mechanics now redirect to the wren genbi CLI reference for deep dives. Note that deploy currently supports only Vercel and Cloudflare Pages. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01SMFmA9S81sANeNDee62VMh
github-actions
Bot
added
the
documentation
Contributor
|
Note Reviews pausedIt looks like this branch is under active development. To avoid overwhelming you with review comments due to an influx of new commits, CodeRabbit has automatically paused this review. You can configure this behavior by changing the Use the following commands to manage reviews:
Use the checkboxes below for quick actions:
WalkthroughThis PR comprehensively restructures Wren AI documentation to introduce the "three beats" framework (Know, Generate, Deploy), establish knowledge management as a core concept, rewrite the GenBI guide for agent-driven workflows, extend the quickstart with GenBI deployment, and refresh README/introduction messaging around open-source GenBI positioning across nineteen updated and three new documentation files. ChangesCore concept framework: knowledge, context, and positioning
GenBI and guide rewrites: agent-driven workflows
Introduction, quickstart, and README: user-facing positioning
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~25 minutes Possibly related PRs
Suggested labels
Suggested reviewers
Poem
🚥 Pre-merge checks | ✅ 5✅ Passed checks (5 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@docs/core/guides/genbi.md`:
- Around line 73-85: In the "Preview before you share" section, clarify that the
port 8848 shown in the preview example is not a guaranteed default but rather an
illustrative example. Add a note explaining that the wren genbi open command
serves apps on a dynamic port that is either auto-picked or specified via the
--port flag, so users should expect that the actual port may differ from 8848
depending on port availability or explicit configuration.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Repository UI
Review profile: CHILL
Plan: Pro
Run ID: 1b329f4c-52a6-479f-bdc4-300fe210b57d
📒 Files selected for processing (1)
docs/core/guides/genbi.md
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Contributor
There was a problem hiding this comment.
Actionable comments posted: 1
🧹 Nitpick comments (1)
docs/core/concepts/oss_vs_commercial.md (1)
15-16: 💤 Low valueMinor: Consider reducing "fully" repetition in consecutive table rows.
Lines 15–16 use "fully" in back-to-back table cells ("Free and fully self-hosted" → "Fully managed cloud"). While acceptable in a feature table, rewording one cell slightly can improve readability.
Proposed alternative:
Optional style improvement
- | Free and fully self-hosted | ✅ | ✅ | + | Free, self-hosted | ✅ | ✅ |(Alternative: keep as-is if the emphasis on "fully" is intentional.)
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@docs/core/concepts/oss_vs_commercial.md` around lines 15 - 16, The table rows at lines 15-16 contain repetitive use of the word "fully" in consecutive cells ("Free and fully self-hosted" and "Fully managed cloud"), which reduces readability. Rephrase one of these cells to eliminate the repetition while maintaining the meaning and clarity of the feature comparison. Consider rewording either the self-hosted row or the managed cloud row to convey the same information without repeating the word "fully".
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@docs/core/get_started/quickstart.md`:
- Around line 319-323: Add language identifiers to the fenced code blocks in the
markdown file to comply with MD040 linting rules. Locate the two unlabeled
fenced code blocks: the one starting at line 319 containing the text about using
the /wren skill to build a GenBI dashboard and the one at line 338 about
deploying the dashboard to Vercel. For each block, change the opening fence from
triple backticks (```) to triple backticks followed by the language identifier
text (```text) to properly label these text blocks.
---
Nitpick comments:
In `@docs/core/concepts/oss_vs_commercial.md`:
- Around line 15-16: The table rows at lines 15-16 contain repetitive use of the
word "fully" in consecutive cells ("Free and fully self-hosted" and "Fully
managed cloud"), which reduces readability. Rephrase one of these cells to
eliminate the repetition while maintaining the meaning and clarity of the
feature comparison. Consider rewording either the self-hosted row or the managed
cloud row to convey the same information without repeating the word "fully".
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Repository UI
Review profile: CHILL
Plan: Pro
Run ID: 60a7d265-18eb-4a8e-8134-7e790660f1e7
📒 Files selected for processing (16)
README.mddocs/core/concepts/agent_learning.mddocs/core/concepts/correctness.mddocs/core/concepts/knowledge_management.mddocs/core/concepts/memory_system.mddocs/core/concepts/oss_vs_commercial.mddocs/core/concepts/stack_position.mddocs/core/concepts/what_is_context.mddocs/core/concepts/what_is_mdl.mddocs/core/concepts/why_wren.mddocs/core/get_started/quickstart.mddocs/core/guides/genbi.mddocs/core/guides/model.mddocs/core/guides/refine.mddocs/core/introduction.mdxdocs/core/reference/architecture.md
✅ Files skipped from review due to trivial changes (8)
- docs/core/concepts/memory_system.md
- docs/core/concepts/what_is_context.md
- docs/core/concepts/what_is_mdl.md
- docs/core/guides/model.md
- docs/core/concepts/agent_learning.md
- docs/core/reference/architecture.md
- docs/core/concepts/correctness.md
- README.md
🚧 Files skipped from review as they are similar to previous changes (1)
- docs/core/guides/genbi.md
Group the checkbox table into four themed sections (how you run it, access for your team, security and governance, build/query/support), each with a one-line intro, and add admonitions for "Consider Commercial when" and "Stay on open source when". Add a row for agentic and interactive answer modes (web UI, sandboxed), which is commercial-only. Note the two ways to run Commercial (cloud or self-hosted enterprise). Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01SMFmA9S81sANeNDee62VMh
…interactive row Drop the four-section grouping and admonitions; back to one flat comparison table plus a short "Consider Commercial when" list. Keep the merged agentic and interactive answer modes row. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01SMFmA9S81sANeNDee62VMh
Contributor
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@docs/core/concepts/oss_vs_commercial.md`:
- Around line 21-26: The table row "Free and fully self-hosted" misleadingly
shows a checkmark for Commercial, implying the paid product is free. Fix this by
either splitting the row into two separate rows (one for "Free" and one for
"Self-hosted") or by changing the Commercial column to show ❌ (unavailable) for
the "Free" capability, since the Commercial product is a paid offering. Ensure
the table clearly communicates that the Commercial product is not free while
potentially being self-hosted or fully managed.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Repository UI
Review profile: CHILL
Plan: Pro
Run ID: 5d6fcbec-4dce-46c3-8a2b-73ae1d376656
📒 Files selected for processing (1)
docs/core/concepts/oss_vs_commercial.md
Contributor
There was a problem hiding this comment.
♻️ Duplicate comments (1)
docs/core/concepts/oss_vs_commercial.md (1)
15-16:⚠️ Potential issue | 🟠 Major | ⚡ Quick winFix the conflicting "Free" claim for Commercial (previously flagged).
The "Free and fully self-hosted" table row shows ✅ under Commercial, which contradicts the product description (lines 7, 9) positioning Commercial as a paid enterprise offering. This issue was previously flagged; the fix remains valid: split the row into two separate rows.
Additionally, LanguageTool flagged adverb repetition: "fully" appears in both this row and the adjacent "Fully managed cloud" row. Splitting resolves both concerns.
🛠️ Proposed fix
-| Free and fully self-hosted | ✅ | ✅ | +| Fully self-hosted | ✅ | ✅ | +| Free | ✅ | ❌ | | Fully managed cloud | ❌ | ✅ |🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@docs/core/concepts/oss_vs_commercial.md` around lines 15 - 16, The table row "Free and fully self-hosted" incorrectly shows a checkmark for Commercial, contradicting the product's positioning as a paid enterprise offering. Split this row into two separate rows: one for "Free" (with checkmark only for OSS) and one for "Self-hosted" or similar (with checkmarks for both), which will also eliminate the repetition of the word "fully" that appears in the adjacent "Fully managed cloud" row.
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Duplicate comments:
In `@docs/core/concepts/oss_vs_commercial.md`:
- Around line 15-16: The table row "Free and fully self-hosted" incorrectly
shows a checkmark for Commercial, contradicting the product's positioning as a
paid enterprise offering. Split this row into two separate rows: one for "Free"
(with checkmark only for OSS) and one for "Self-hosted" or similar (with
checkmarks for both), which will also eliminate the repetition of the word
"fully" that appears in the adjacent "Fully managed cloud" row.
ℹ️ Review info
⚙️ Run configuration
Configuration used: Repository UI
Review profile: CHILL
Plan: Pro
Run ID: eb26f648-2ecf-4902-96ea-e6d4f99ff9b2
📒 Files selected for processing (1)
docs/core/concepts/oss_vs_commercial.md
Three short, persona-based scenarios (solo, data team, analytics for your customers) before the single feature table, so readers can self-identify before scanning the grid. Folds the old "Consider Commercial when" list into the scenarios to avoid repeating the same point. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01SMFmA9S81sANeNDee62VMh
… the table One short paragraph under the comparison table that sums up, in plain terms, what moving to Commercial gives a team, and notes that MDL and context carry over unchanged. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01SMFmA9S81sANeNDee62VMh
Replace the dense paragraph with six short, bold-led bullets so the summary is easier to scan. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01SMFmA9S81sANeNDee62VMh
goldmedal
approved these changes
Jun 22, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What
Rewrites
docs/core/guides/genbi.md(the Build & deploy a GenBI app guide) so it reads as an agent-workflow guide, not a command walkthrough.The page now teaches the conversation:
All the per-command mechanics (
build/register/verify/open/deployflags, the DuckDB export snippet) are removed from the guide and redirected to thewren genbiCLI reference for deep dives.Why
The guide overlapped heavily with the CLI reference and led with command syntax. Users drive GenBI by talking to an agent, so the guide should teach that and leave the flag-level detail to the reference.
Notes
docs.getwren.ai) picks this up automatically via thesync-docsworkflow on merge — no docs-repo change needed.🤖 Generated with Claude Code
https://claude.ai/code/session_01SMFmA9S81sANeNDee62VMh
Summary by CodeRabbit