Skip to content

Chennai Rohith AI-Code Sarathi Submission - #24

Open
rohith-s wants to merge 2 commits into
nasscomAI:masterfrom
rohith-s:participant/rohith-chennai
Open

Chennai Rohith AI-Code Sarathi Submission#24
rohith-s wants to merge 2 commits into
nasscomAI:masterfrom
rohith-s:participant/rohith-chennai

Conversation

@rohith-s

Copy link
Copy Markdown

Name: Sane Rohith
City / Group: Chennai
Date: 2026-06-15
AI tool(s) used: Codex

Submission Checklist

  • uc-0a/agents.md — present and updated
  • uc-0a/skills.md — present and updated
  • uc-0a/classifier.py — runs without crash
  • uc-0a/results_[city].csv — output present
  • uc-rag/agents.md — present and updated
  • uc-rag/skills.md — present and updated
  • uc-rag/rag_server.py — not the stub, your implementation
  • uc-mcp/agents.md — present and updated
  • uc-mcp/skills.md — present and updated
  • uc-mcp/mcp_server.py — passes at least one test_client.py test
  • 3+ commits with meaningful messages, one per UC
  • All sections below filled

UC-0A — Complaint Classifier

Which failure mode did you encounter first?

Severity blindness: safety-related complaints such as child, school, injury, hospital, ambulance, hazard, fell, or collapse could be classified without Urgent priority.

Which enforcement rule fixed it? Quote from your agents.md:

"Priority must be Urgent if the description contains any severity keyword: injury, child, school, hospital, ambulance, fire, hazard, fell, collapse."

Your commit message for UC-0A:

UC-0A Fix severity blindness: starter code had no enforcement → added severity triggers, fixed taxonomy, reasons, and review flags

Verification checkpoints:

  • All severity-signal rows classified as Urgent
  • No invented categories outside the defined taxonomy
  • Justification column present and non-empty for every row

UC-RAG — RAG Server

Not completed in this submission.

UC-MCP — MCP Server

Not completed in this submission.

CRAFT Reflection

Which step of the CRAFT loop was hardest across all three UCs?

The Refine step, because similar complaint text can match multiple categories and the classifier needed explicit precedence rules.

What did you add to agents.md manually that the AI did not generate?

I added exact category enforcement, severity keyword enforcement, the reason-field requirement, and the NEEDS_REVIEW rule for ambiguous complaints.

One specific task in your real work where you will use R.I.C.E in the next 7 days:

I will use R.I.C.E to write clearer prompts for classifying support or operations requests with fixed categories and escalation rules.

… severity triggers, fixed taxonomy, reasons, and review flags
@github-actions

Copy link
Copy Markdown

Hi there, participant! Thanks for joining our RAG-to-MCP Workshop!

We're reviewing your PR for the 3 Use Cases (UC-0A, UC-RAG, UC-MCP). Once your submission is validated and merged, you'll be awarded your completion badge!

Next Steps:

  • Make sure all 3 UCs are finished.
  • Ensure your commit messages match the required format.
  • Fill out every section of the PR template.
  • Good luck!

…ed CMC policy scope, JSON-RPC handling, and isError refusals
@github-actions

Copy link
Copy Markdown

Hi there, participant! Thanks for joining our RAG-to-MCP Workshop!

We're reviewing your PR for the 3 Use Cases (UC-0A, UC-RAG, UC-MCP). Once your submission is validated and merged, you'll be awarded your completion badge!

Next Steps:

  • Make sure all 3 UCs are finished.
  • Ensure your commit messages match the required format.
  • Fill out every section of the PR template.
  • Good luck!

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant