Skip to content

docs: add MLflow tracking as example of AI provider agnosticism principle #1333

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
atxtechbro wants to merge 1 commit into
base: main
Choose a base branch
from
Open

docs: add MLflow tracking as example of AI provider agnosticism principle #1333

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 4 additions & 0 deletions knowledge/principles/ai-provider-agnosticism.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -66,6 +66,10 @@ Historical note: `.claude/command-templates/` are intentionally retired; they re
- Strengths: Novel OpenAI models, cutting-edge capabilities, unique availability
- MCP: TOML config with mcp_servers sections

## Implementation Example: MLflow Tracking

MLflow session tracking (`tracking/parse_session.py`) demonstrates provider agnosticism by extracting actual commands rather than maintaining provider-specific patterns. Instead of N×M complexity (N providers × M patterns), it uses a single parser that looks for `git`, `gh`, and bash commands regardless of AI formatting. This avoids provider detection entirely - working automatically with Claude Code, OpenAI Codex, and future assistants.

## Relationship to Other Principles
Copy link
Copy Markdown
Contributor

@amazon-q-developer amazon-q-developer bot Sep 25, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The final paragraph effectively explains the N×M problem avoidance, but it could be strengthened by mentioning the specific technical approach used (regex patterns for actual commands vs provider-specific formatting patterns). This would make the example more concrete and educational.


- **[Systems Stewardship](systems-stewardship.md)**: Consistent interfaces across providers
Expand Down