Updates to New User flows from user feedback#607
Merged
Conversation
Rework the overview page around the first-run mental model users need before setup: when to use Agent Canvas, how the UI/backend/workspace/model pieces fit together, which trust boundary to choose, and where to go next. This addresses interview and docs-chat feedback showing confusion around Agent Canvas setup paths, backend execution, model access, and file access.
Rework the setup page from a short install reference into a full lifecycle guide. The page now helps users choose npm, Docker, VM/self-hosted, or source workflows; verify prerequisites; start and confirm the local UI; understand common flags and environment variables; and stop, update, or uninstall Agent Canvas. This targets setup and uninstall confusion surfaced in interview feedback and docs-chat analysis.
Member
Author
|
@jpelletier1 This makes some major changes to the entry point for agent canvas. Take a look when you get a chance and let me know any feedback: |
|
Preview deployment for your docs. Learn more about Mintlify Previews.
💡 Tip: Enable Workflows to automatically generate PRs for you. |
enyst
reviewed
Jul 9, 2026
enyst
reviewed
Jul 9, 2026
enyst
reviewed
Jul 9, 2026
Co-authored-by: Engel Nyst <engel.nyst@gmail.com>
Co-authored-by: Engel Nyst <engel.nyst@gmail.com>
Co-authored-by: Engel Nyst <engel.nyst@gmail.com>
enyst
approved these changes
Jul 9, 2026
enyst
left a comment
enyst
left a comment
Member
There was a problem hiding this comment.
Thank you for this! Let’s try, and we can always continue to iterate.
Contributor
|
@DevinVinson LGTM! |
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
3 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.
Summary of changes
Updates the Agent Canvas docs to better support first-time setup and troubleshooting based on recent user interview feedback and docs-chat query analysis.
Changes include:
npx, global npm install, Docker, source setup, prerequisites, startup confirmation, stop/update/uninstall, and common flags.uv, browser startup issues, port conflicts, Docker daemon errors, backend URL/API key confusion, model/provider errors, ACP credentials, workspace location, MCP settings, automations, and uninstall/update problems.Pages changed:
Context
Recent user interviews showed that Agent Canvas is valuable once running, but users often need more support understanding where the agent runs, what files it can access, how model credentials work, and which setup path to choose.
Docs-chat analysis also showed increased Agent Canvas, install/setup, uninstall, backend, and model configuration questions, with “Canvas vs core concepts” being a high-volume area where users were less consistently getting useful answers.
These docs changes make the onboarding path more explicit and give users concrete recovery steps when setup does not work on the first try.