Conversation
overview.md - The front door. Rewrote the opening to position KitOps as packaging for AI projects broadly, not just self-hosted models. Added "AI Engineers & Agent Developers" as a persona alongside Data Scientists and DevOps. Expanded the ModelKit and Kitfile descriptions to mention skill files, MCP configs, and prompts as first-class artifacts. why-kitops.md - Expanded the problem statement to include scattered prompts, copy-pasted skill files, and ad-hoc MCP configs alongside the existing model/dataset/code problems. Added a new comparison section "KitOps and Agentic AI Frameworks" that positions KitOps as the versioning layer agent frameworks lack. Updated the recap and ad-hoc storage sections. use-cases.md - Restructured into two main sections: "Self-Hosted Model Deployment" (Levels 1-3, all existing content preserved) and "Agentic AI and Prompt Management" (new). The new section covers three use cases: versioning prompts/skills/agent configs, MCP server configuration management, and combining models with agent artifacts. Each has an "In Practice" walkthrough. modelkit/intro.md - Added the critical framing that not every ModelKit contains a model. Expanded "Why It Matters" to address both self-hosted model teams and agentic AI teams. Removed emoji from headers for consistency. kitfile/kf-overview.md - Added a third column to the section table showing example contents (SKILL.md, .cursorrules, MCP server code). Added a minimal Kitfile example for agent skills (no model). Added a full "Agentic AI Kitfile" example showing prompts, skills, and MCP server configs. Clarified that prompts is for skills/prompts and code is for MCP servers. security.md - Rewrote the intro to position prompt tampering and MCP config manipulation as attack surfaces alongside model tampering. Added a new section "Why This Matters for Agentic AI" with specific scenarios. Updated the Jozu Hub description to mention MCP Registry API. next-steps.md - Added the prompts section to the Kitfile parts list (was previously missing). Fixed the Kitfile requirements description to match the actual spec. Noted that ModelKits don't require a model. What I deliberately did NOT change Quick start and tutorials (as you requested) SEO frontmatter metadata (per your answer) Any technical claims about Kitfile format capabilities - I stayed within what the format actually supports today The existing model-focused content - it's all still there, the agentic AI content is additive Signed-off-by: Brad Micklea <7644938+bmicklea@users.noreply.github.com>
Contributor
There was a problem hiding this comment.
Pull request overview
This PR updates documentation across multiple files to position KitOps for broader AI project packaging, including agentic AI systems alongside the existing self-hosted model focus. The changes expand the narrative to cover prompts, agent skill files, and MCP server configurations as first-class artifacts that can be packaged and versioned alongside models.
Changes:
- Restructured use-cases.md into "Self-Hosted Model Deployment" (existing Level 1-3 content) and "Agentic AI and Prompt Management" (new use cases for versioning prompts/skills, MCP configs, and combined model+agent systems)
- Expanded why-kitops.md with a new "KitOps and Agentic AI Frameworks" comparison section and updated problem statement to include scattered prompts and ad-hoc MCP configs
- Added "AI Engineers & Agent Developers" persona to overview.md alongside existing roles, emphasizing prompts/skills/MCP versioning
- Added clarification to modelkit/intro.md and overview.md that not every ModelKit requires a model
- Updated kitfile/kf-overview.md with a third column in the section table showing example contents, added minimal examples for agent-only ModelKits, and added a complete "Agentic AI Kitfile" example
- Added "Why This Matters for Agentic AI" section to security.md with specific threat scenarios for prompts and MCP configs
- Updated next-steps.md to document the
promptssection (previously undocumented) and clarify ModelKit requirements
Reviewed changes
Copilot reviewed 7 out of 7 changed files in this pull request and generated 2 comments.
Show a summary per file
| File | Description |
|---|---|
| docs/src/docs/why-kitops.md | Added agentic AI frameworks comparison section and expanded problem statement |
| docs/src/docs/use-cases.md | Restructured with Self-Hosted and Agentic sections; added three new agentic use cases |
| docs/src/docs/overview.md | Added AI Engineers persona and examples of agent-focused use cases |
| docs/src/docs/modelkit/intro.md | Added clarification that ModelKits don't require models |
| docs/src/docs/kitfile/kf-overview.md | Enhanced section table with examples; added minimal and agentic Kitfile examples |
| docs/src/docs/security.md | Added agentic AI security considerations section |
| docs/src/docs/next-steps.md | Documented prompts section; clarified ModelKit requirements |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
change suggested by copilot Signed-off-by: Brad Micklea <7644938+bmicklea@users.noreply.github.com>
Deploying kitops-org with
|
| Latest commit: |
f029c9f
|
| Status: | ✅ Deploy successful! |
| Preview URL: | https://24f25f24.kitops-org.pages.dev |
| Branch Preview URL: | https://docs-agentic.kitops-org.pages.dev |
Jwilliamsr
approved these changes
Apr 3, 2026
Contributor
Jwilliamsr
left a comment
Jwilliamsr
left a comment
There was a problem hiding this comment.
Looks good. I like the Agent section of the use cases file.
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
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.
Changes
Updated the overview portions of the docs to highlight the value of ModelKits for agentic use cases. The self-hosted model content is still there, but is treated as a peer rather than as the focus.
overview.md - Rewrote the opening to position KitOps as packaging for AI projects broadly, not just self-hosted models. Added "AI Engineers & Agent Developers" as a persona alongside Data Scientists and DevOps. Expanded the ModelKit and Kitfile descriptions to mention skill files, MCP configs, and prompts as first-class artifacts.
why-kitops.md - Expanded the problem statement to include scattered prompts, copy-pasted skill files, and ad-hoc MCP configs alongside the existing model/dataset/code problems. Added a new comparison section "KitOps and Agentic AI Frameworks" that positions KitOps as the versioning layer agent frameworks lack. Updated the recap and ad-hoc storage sections.
use-cases.md - Restructured into two main sections: "Self-Hosted Model Deployment" (Levels 1-3, all existing content preserved) and "Agentic AI and Prompt Management" (new). The new section covers three use cases: versioning prompts/skills/agent configs, MCP server configuration management, and combining models with agent artifacts. Each has an "In Practice" walkthrough.
modelkit/intro.md - Added the critical framing that not every ModelKit contains a model. Expanded "Why It Matters" to address both self-hosted model teams and agentic AI teams.
kitfile/kf-overview.md - Added a third column to the section table showing example contents (SKILL.md, .cursorrules, MCP server code). Added a minimal Kitfile example for agent skills (no model). Added a full "Agentic AI Kitfile" example showing prompts, skills, and MCP server configs. Clarified that prompts is for skills/prompts and code is for MCP servers.
security.md - Rewrote the intro to position prompt tampering and MCP config manipulation as attack surfaces alongside model tampering. Added a new section "Why This Matters for Agentic AI" with specific scenarios. Updated the Jozu Hub description to mention MCP Registry API.
next-steps.md - Added the prompts section to the Kitfile parts list (was previously missing). Fixed the Kitfile requirements description to match the actual spec. Noted that ModelKits don't require a model.
What I Didn't Change