Conversation
added 2 commits
March 13, 2026 15:59
jackfischer
approved these changes
Mar 13, 2026
Contributor
Greptile SummaryThis PR makes a broad sweep of documentation improvements: it rewrites Key issues found:
Confidence Score: 3/5
Important Files Changed
Prompt To Fix All With AIThis is a comment left during a code review.
Path: fern/docs/pages/introduction.mdx
Line: 91
Comment:
**Broken email link (mailto removed)**
The `support@credal.ai` address was changed from a clickable `mailto:` hyperlink to plain bold text, making it impossible for users to click and open their email client. Every other support email in the codebase (including `quickstart.mdx`) uses the linked form.
```suggestion
Questions or need help? Reach out at **[support@credal.ai](mailto:support@credal.ai)**.
```
How can I resolve this? If you propose a fix, please make it concise.
---
This is a comment left during a code review.
Path: fern/docs/pages/introduction.mdx
Line: 83-84
Comment:
**Internal hyperlinks removed from Security section**
Two useful cross-links that were present in the previous version of this section were dropped in this PR:
- `detailed audit logs` previously linked to `/user-guide/platform/administration/audit-log-data-exports`
- `SSO and SCIM integration` previously linked to `/user-guide/platform/administration/single-sign-on-sso`
Restoring these helps users navigate to the relevant feature pages directly from the introduction, which is a common entry point. Consider adding them back:
```suggestion
- Supports human-in-the-loop approval flows and detailed [audit logs](/user-guide/platform/administration/audit-log-data-exports)
- Flexible deployment: cloud or on-prem, with [SSO and SCIM](/user-guide/platform/administration/single-sign-on-sso) integration for identity and access management
```
How can I resolve this? If you propose a fix, please make it concise.
---
This is a comment left during a code review.
Path: fern/docs/pages/platform/actions/custom-names-descriptions.mdx
Line: 36
Comment:
**Absolute URL for internal link**
This is the only internal link in the entire docs codebase that uses an absolute `https://docs.credal.ai/...` URL. Every other internal cross-reference uses a root-relative path (e.g., `/user-guide/platform/...`). Using the hardcoded domain will silently break in staging, PR preview, or any environment not served from `docs.credal.ai`.
```suggestion
You can distribute and scale usage of your customized actions in any surface through our [custom MCP servers](/user-guide/platform/mcp-servers/overview). Your HR, Finance, Product, etc. team can then manage their own blessed set of tools for the entire organization to use.
```
How can I resolve this? If you propose a fix, please make it concise.
---
This is a comment left during a code review.
Path: fern/docs/pages/platform/mcp-servers/import-server/setting-up-controls.mdx
Line: 6
Comment:
**Contradictory messaging about human approval availability**
The opening paragraph of this page already states that admins *can* "require human approval before specific actions execute" as a current feature. The new Note, however, ends with "…as well as the ability to enforce human approval on any of these actions" framed as a coming-soon item.
A reader will reasonably interpret this as "human approval on MCP server actions is not yet available," which directly contradicts the sentence above. If the coming-soon item refers specifically to *bulk / automatic* enforcement (as opposed to per-action configuration), the Note should clarify that distinction to avoid confusion.
How can I resolve this? If you propose a fix, please make it concise.Last reviewed commit: 34351d4 |
![greptile-apps[bot]](https://avatars.githubusercontent.com/in/867647?s=60&v=4){kind=small}
| ## Support | ||
|
|
||
| For questions or support? Reach out to our team at **[support@credal.ai](mailto:support@credal.ai)**. | ||
| Questions or need help? Reach out at **support@credal.ai**. |
Contributor
There was a problem hiding this comment.
Broken email link (mailto removed)
The support@credal.ai address was changed from a clickable mailto: hyperlink to plain bold text, making it impossible for users to click and open their email client. Every other support email in the codebase (including quickstart.mdx) uses the linked form.
Suggested change
| Questions or need help? Reach out at **support@credal.ai**. | |
| Questions or need help? Reach out at **[support@credal.ai](mailto:support@credal.ai)**. |
Prompt To Fix With AI
This is a comment left during a code review.
Path: fern/docs/pages/introduction.mdx
Line: 91
Comment:
**Broken email link (mailto removed)**
The `support@credal.ai` address was changed from a clickable `mailto:` hyperlink to plain bold text, making it impossible for users to click and open their email client. Every other support email in the codebase (including `quickstart.mdx`) uses the linked form.
```suggestion
Questions or need help? Reach out at **[support@credal.ai](mailto:support@credal.ai)**.
```
How can I resolve this? If you propose a fix, please make it concise.
Comment on lines
+83
to
+84
| - Supports human-in-the-loop approval flows and detailed audit logs | ||
| - Flexible deployment: cloud or on-prem, with SSO and SCIM integration for identity and access management |
Contributor
There was a problem hiding this comment.
Internal hyperlinks removed from Security section
Two useful cross-links that were present in the previous version of this section were dropped in this PR:
detailed audit logspreviously linked to/user-guide/platform/administration/audit-log-data-exportsSSO and SCIM integrationpreviously linked to/user-guide/platform/administration/single-sign-on-sso
Restoring these helps users navigate to the relevant feature pages directly from the introduction, which is a common entry point. Consider adding them back:
Suggested change
| - Supports human-in-the-loop approval flows and detailed audit logs | |
| - Flexible deployment: cloud or on-prem, with SSO and SCIM integration for identity and access management | |
| - Supports human-in-the-loop approval flows and detailed [audit logs](/user-guide/platform/administration/audit-log-data-exports) | |
| - Flexible deployment: cloud or on-prem, with [SSO and SCIM](/user-guide/platform/administration/single-sign-on-sso) integration for identity and access management |
Prompt To Fix With AI
This is a comment left during a code review.
Path: fern/docs/pages/introduction.mdx
Line: 83-84
Comment:
**Internal hyperlinks removed from Security section**
Two useful cross-links that were present in the previous version of this section were dropped in this PR:
- `detailed audit logs` previously linked to `/user-guide/platform/administration/audit-log-data-exports`
- `SSO and SCIM integration` previously linked to `/user-guide/platform/administration/single-sign-on-sso`
Restoring these helps users navigate to the relevant feature pages directly from the introduction, which is a common entry point. Consider adding them back:
```suggestion
- Supports human-in-the-loop approval flows and detailed [audit logs](/user-guide/platform/administration/audit-log-data-exports)
- Flexible deployment: cloud or on-prem, with [SSO and SCIM](/user-guide/platform/administration/single-sign-on-sso) integration for identity and access management
```
How can I resolve this? If you propose a fix, please make it concise.| Custom names and descriptions only affect how actions appear within Credal. The underlying integration or MCP server functionality remains unchanged. | ||
| </Note> | ||
|
|
||
| You can distribute and scale usage of your customized actions in any surface through our [custom MCP servers](https://docs.credal.ai/user-guide/platform/mcp-servers/overview). Your HR, Finance, Product, etc. team can then manage their own blessed set of tools for the entire organization to use. |
Contributor
There was a problem hiding this comment.
Absolute URL for internal link
This is the only internal link in the entire docs codebase that uses an absolute https://docs.credal.ai/... URL. Every other internal cross-reference uses a root-relative path (e.g., /user-guide/platform/...). Using the hardcoded domain will silently break in staging, PR preview, or any environment not served from docs.credal.ai.
Suggested change
| You can distribute and scale usage of your customized actions in any surface through our [custom MCP servers](https://docs.credal.ai/user-guide/platform/mcp-servers/overview). Your HR, Finance, Product, etc. team can then manage their own blessed set of tools for the entire organization to use. | |
| You can distribute and scale usage of your customized actions in any surface through our [custom MCP servers](/user-guide/platform/mcp-servers/overview). Your HR, Finance, Product, etc. team can then manage their own blessed set of tools for the entire organization to use. |
Prompt To Fix With AI
This is a comment left during a code review.
Path: fern/docs/pages/platform/actions/custom-names-descriptions.mdx
Line: 36
Comment:
**Absolute URL for internal link**
This is the only internal link in the entire docs codebase that uses an absolute `https://docs.credal.ai/...` URL. Every other internal cross-reference uses a root-relative path (e.g., `/user-guide/platform/...`). Using the hardcoded domain will silently break in staging, PR preview, or any environment not served from `docs.credal.ai`.
```suggestion
You can distribute and scale usage of your customized actions in any surface through our [custom MCP servers](/user-guide/platform/mcp-servers/overview). Your HR, Finance, Product, etc. team can then manage their own blessed set of tools for the entire organization to use.
```
How can I resolve this? If you propose a fix, please make it concise.| For every MCP server, admins can enable or disable individual tools and require [human approval](/user-guide/platform/governed-actions/human-approval-options) before specific actions execute. If a third-party server exposes actions that are too sensitive or not relevant for your organization, simply turn them off. For actions you want to allow but monitor closely, approval enforcement ensures nothing runs without a human sign-off first. | ||
|
|
||
| <Note> | ||
| **Tool Syncing:** Credal automatically refreshes the list of available tools every time `tools/list` is called through the MCP gateway. You can also manually refresh tools using the refresh button in the UI. Background refreshes with version control to synchronously approve changes are coming soon, as well as the ability to enforce human approval on any of these actions. |
Contributor
There was a problem hiding this comment.
Contradictory messaging about human approval availability
The opening paragraph of this page already states that admins can "require human approval before specific actions execute" as a current feature. The new Note, however, ends with "…as well as the ability to enforce human approval on any of these actions" framed as a coming-soon item.
A reader will reasonably interpret this as "human approval on MCP server actions is not yet available," which directly contradicts the sentence above. If the coming-soon item refers specifically to bulk / automatic enforcement (as opposed to per-action configuration), the Note should clarify that distinction to avoid confusion.
Prompt To Fix With AI
This is a comment left during a code review.
Path: fern/docs/pages/platform/mcp-servers/import-server/setting-up-controls.mdx
Line: 6
Comment:
**Contradictory messaging about human approval availability**
The opening paragraph of this page already states that admins *can* "require human approval before specific actions execute" as a current feature. The new Note, however, ends with "…as well as the ability to enforce human approval on any of these actions" framed as a coming-soon item.
A reader will reasonably interpret this as "human approval on MCP server actions is not yet available," which directly contradicts the sentence above. If the coming-soon item refers specifically to *bulk / automatic* enforcement (as opposed to per-action configuration), the Note should clarify that distinction to avoid confusion.
How can I resolve this? If you propose a fix, please make it concise.
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.
Added "Coming Soon" sections across 7 documentation pages for undocumented features (HITL enforcement, conditional rules, rate limiting, eval gates, version control, security controls, registries)
Documented existing action justifications feature in
monitoring.mdx
Added MCP servers hyperlink to
custom-names-descriptions.mdx
Updated
introduction.mdx
to reflect current product positioning
Minor wording updates (4-eyes → version control workflows, quality → evaluation standards)