docs(core): reposition around GenBI (generate · deploy · know)#2381
Merged
Conversation
Lead the README and docs with GenBI — agents that generate, deploy, and govern dashboards — and demote "context layer" to the mechanism that makes that BI trustworthy (product unchanged). Reclaim the "GenBI" name: the old v1 Docker app is renamed "Wren GenBI Classic (sunset)" and clearly separated. - README: GenBI-led hero, Generate/Deploy/Know pillars, "How Wren compares" table, "Wren is for you if / skip" scoping, a build-&-deploy-a-dashboard quickstart step, and a "note on the GenBI name". - introduction.mdx: GenBI-led hero, "GenBI in three beats" table, the five-layer context model reframed as what makes GenBI correct, sunset rename. - concept + architecture leads: one-line bridges tying context/MDL/memory/ correctness to GenBI. - new pages: concepts/why_wren.md (comparison + scoping) and concepts/knowledge_management.md (the "Know" pillar, single entry point). - guides/model.md, guides/refine.md: lead tweaks linking to the new framing. 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
|
Important Review skippedAuto reviews are disabled on base/target branches other than the default branch. Please check the settings in the CodeRabbit UI or the ⚙️ Run configurationConfiguration used: Repository UI Review profile: CHILL Plan: Pro Run ID: You can disable this status message by setting the Use the checkbox below for a quick retry:
Walkthrough
ChangesGenBI Branding and Documentation Refresh
Estimated code review effort🎯 2 (Simple) | ⏱️ ~12 minutes Possibly related PRs
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
Caution
Some comments are outside the diff and can’t be posted inline due to platform limitations.
⚠️ Outside diff range comments (2)
docs/core/guides/model.md (1)
19-21:⚠️ Potential issue | 🟡 MinorUse
wren-generate-mdlinstead of/wren.The
/wrenskill reference doesn't match the published OSS skills catalog. The documented scaffolding skill iswren-generate-mdlper the official reference at docs.getwren.ai/oss/reference/skills.Suggested fix
- > Use the `/wren` skill to scaffold an MDL project for this database. + > Use the `wren-generate-mdl` skill to scaffold an MDL project for this database.🤖 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/guides/model.md` around lines 19 - 21, The documentation in the guide uses the incorrect skill reference `/wren` when instructing users to scaffold an MDL project. Replace all references to the `/wren` skill with the correct skill name `wren-generate-mdl` to match the official OSS skills catalog. Update the instruction text that currently says "Use the `/wren` skill to scaffold an MDL project" to reference `wren-generate-mdl` instead, ensuring the guidance aligns with the published documentation at docs.getwren.ai/oss/reference/skills.docs/core/guides/refine.md (1)
24-29:⚠️ Potential issue | 🟡 MinorAdd
mainto the memory install examples.These examples are for combining memory with data sources to set up a working CLI environment. The package documentation and other install guides (quickstart, CLI reference) consistently show that
mainshould accompanymemoryto enable the browser UI and interactive prompts. The current examples at lines 27–28 omit it.Suggested fix
- pip install "wrenai[memory,postgres]" + pip install "wrenai[memory,main,postgres]" ... - pip install "wrenai[memory,bigquery]" + pip install "wrenai[memory,main,bigquery]"🤖 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/guides/refine.md` around lines 24 - 29, The pip install examples in the memory data source combination section omit the `main` extra, which is needed to enable the browser UI and interactive prompts. Update both installation commands to include `main` alongside `memory` and the respective data source extras (postgres and bigquery). Ensure the extras are comma-separated within the brackets in the format wrenai[main,memory,datasource] for both the postgres and bigquery examples to match the pattern shown in other documentation sections.
🧹 Nitpick comments (1)
README.md (1)
9-11: ⚡ Quick winNormalize the source-count claim.
This page says “22+ data sources,” while the refreshed intro copy uses “20+.” Please pick one canonical figure or drop the number entirely so the rebrand copy doesn’t drift as connectors change.
🤖 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 `@README.md` around lines 9 - 11, The README.md contains an inconsistent reference to the number of data sources—currently stating "22+ data sources" while other parts of the documentation reference "20+". Search the README.md file for all mentions of data source counts and either standardize them to a single canonical figure or remove the specific number entirely to prevent drift as the connector count changes. Update the introductory section around lines 9-11 to match whichever approach is chosen for consistency across all documentation.
🤖 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/knowledge_management.md`:
- Around line 17-29: The Memory row in the artifact table incorrectly presents
memory as a version-controlled artifact alongside MDL, instructions.md, and
queries.yml, when in fact the memory system is local runtime state stored in
.wren/memory/ and gitignored by default. Revise the artifact table to clarify
that Memory is local runtime behavioral knowledge, and only exported/curated
examples from memory are intended to be version-controlled and shared.
Additionally, update the summary paragraph below the table to distinguish
between the local memory index (runtime state) and the version-controlled
artifacts that form the context layer, ensuring the documentation aligns with
the actual storage model described in memory_system.md.
---
Outside diff comments:
In `@docs/core/guides/model.md`:
- Around line 19-21: The documentation in the guide uses the incorrect skill
reference `/wren` when instructing users to scaffold an MDL project. Replace all
references to the `/wren` skill with the correct skill name `wren-generate-mdl`
to match the official OSS skills catalog. Update the instruction text that
currently says "Use the `/wren` skill to scaffold an MDL project" to reference
`wren-generate-mdl` instead, ensuring the guidance aligns with the published
documentation at docs.getwren.ai/oss/reference/skills.
In `@docs/core/guides/refine.md`:
- Around line 24-29: The pip install examples in the memory data source
combination section omit the `main` extra, which is needed to enable the browser
UI and interactive prompts. Update both installation commands to include `main`
alongside `memory` and the respective data source extras (postgres and
bigquery). Ensure the extras are comma-separated within the brackets in the
format wrenai[main,memory,datasource] for both the postgres and bigquery
examples to match the pattern shown in other documentation sections.
---
Nitpick comments:
In `@README.md`:
- Around line 9-11: The README.md contains an inconsistent reference to the
number of data sources—currently stating "22+ data sources" while other parts of
the documentation reference "20+". Search the README.md file for all mentions of
data source counts and either standardize them to a single canonical figure or
remove the specific number entirely to prevent drift as the connector count
changes. Update the introductory section around lines 9-11 to match whichever
approach is chosen for consistency across all documentation.
🪄 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: 826b2206-02e9-49da-8fb3-33fb6b1138a3
📒 Files selected for processing (14)
README.mddocs/core/concepts/agent_learning.mddocs/core/concepts/correctness.mddocs/core/concepts/knowledge_management.mddocs/core/concepts/memory_system.mddocs/core/concepts/stack_position.mddocs/core/concepts/what_is_context.mddocs/core/concepts/what_is_mdl.mddocs/core/concepts/why_wren.mddocs/core/guides/genbi.mddocs/core/guides/model.mddocs/core/guides/refine.mddocs/core/introduction.mdxdocs/core/reference/architecture.md
… genbi transcripts - Remove every em-dash across the GenBI reposition docs and the README, and rewrite for natural flow (the user finds em-dashes "AI-sounding"). - get_started/quickstart.md: add "Step 9: Build and deploy a GenBI dashboard" so the quickstart ends on the generate-and-deploy-a-report payoff. - guides/genbi.md: expand the U:/A: conversation transcripts to User:/Agent: so readers aren't guessing what the speaker labels mean. - Also fix a stray code fence in the README's China install tip. 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/get_started/quickstart.md`:
- Around line 342-349: The Vercel dashboard navigation path in the Heads-up
section is incomplete and stops at "Deployment Protection" without showing the
remaining steps. Update the navigation sequence to include the complete path:
"Project → Settings → Deployment Protection → Vercel Authentication → Disabled"
so users can immediately locate and disable the authentication setting without
confusion.
🪄 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: c30831a1-3c18-48d5-a09f-be1da9669a45
📒 Files selected for processing (15)
README.mddocs/core/concepts/agent_learning.mddocs/core/concepts/correctness.mddocs/core/concepts/knowledge_management.mddocs/core/concepts/memory_system.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 (10)
- docs/core/concepts/what_is_mdl.md
- docs/core/concepts/memory_system.md
- docs/core/reference/architecture.md
- docs/core/concepts/what_is_context.md
- docs/core/concepts/agent_learning.md
- docs/core/concepts/knowledge_management.md
- docs/core/guides/model.md
- docs/core/concepts/correctness.md
- docs/core/concepts/stack_position.md
- README.md
🚧 Files skipped from review as they are similar to previous changes (1)
- docs/core/guides/genbi.md
… What's next Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01SMFmA9S81sANeNDee62VMh
…unt) - knowledge_management.md: stop presenting the memory index as a version- controlled artifact. It is local runtime state under .wren/memory/ (usually gitignored); only curated pairs exported to queries.yml are repo-backed. Aligns with memory_system.md and operational.md. README bullet updated to match. - quickstart.md: complete the Vercel path (Project → Settings → Deployment Protection → Vercel Authentication → Disabled). - introduction.mdx: "20+" → "22+" data sources, consistent with the rest. Skipped two suggestions: model.md keeps `/wren` (the rest of the docs use the installed `/wren` stub that pulls the generate-mdl guide; switching would be inconsistent), and refine.md omits `main` (it is only for the UI/prompts, not needed for memory commands). Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01SMFmA9S81sANeNDee62VMh
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
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
1 participant
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
Repositions the README and OSS docs to lead with GenBI — agents that generate, deploy, and govern dashboards — and demotes "context layer" to the mechanism that makes that BI trustworthy. The product does not change; this is framing, sequencing, naming, and two new explanation pages.
Core idea: GenBI = Generate · Deploy · Know.
Changes
what_is_context,what_is_mdl,memory_system,agent_learning,correctness,stack_position,architecture) — one-line bridges to GenBI; depth untouched.concepts/why_wren.md(comparison + honest scoping) andconcepts/knowledge_management.md(the "Know" pillar, single entry point for the knowledge-management story).guides/model.md,guides/refine.md— lead tweaks linking to the new framing.Naming change
The old v1 Docker chat-BI app is renamed Wren GenBI Classic (sunset) and clearly separated, so "GenBI" can mean the new generative-BI capability without confusion.
Notes for reviewers
docs.getwren.aipicks these pages up via thesync-docsworkflow on merge. The sidebar entries for the two new pages live in the docs repo and are handled in a separate small PR there (sidebars.ts isn't synced).🤖 Generated with Claude Code
https://claude.ai/code/session_01SMFmA9S81sANeNDee62VMh
Summary by CodeRabbit