[Pune] Prachi Dudhankar — RAG-to-MCP Submission

[Prachi-44]

RAG-to-MCP — Submission PR

Name: Prachi Dudhankar
City: Pune
Date: 2 May 2026

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_pune.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?

Taxonomy drift — the naive prompt invented category names like "Road Issue" and "Drainage Problem" instead of using the exact schema values.

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

"Category must be exactly one value from the allowed list: Pothole, Flooding, Streetlight, Waste, Noise, Road Damage, Heritage Damage, Heat Hazard, Drain Blockage, Other. No variations or invented names."

Your commit message for UC-0A:

UC-0A Fix false confidence on ambiguity: no error handling for vague text → enforced Other category and NEEDS_REVIEW flag for descriptions lacking specific keywords

Verification checkpoints:

• All severity-signal rows (injury/child/school/hospital keywords) classified as Urgent
• No invented categories outside the defined taxonomy
• Justification column present and non-empty for every row

---

UC-RAG — RAG Server

Which failure mode did you encounter?

Chunk boundary failure — policy clause 5.2 was split across two fixed-size chunks, causing retrieval to return an incomplete answer regarding dual-approver obligations.

What chunking strategy did you use and why?

Sentence-boundary chunking: text is split on sentence-ending punctuation and accumulated until the limit is reached. This guarantees no clause is cut mid-sentence.

Did your system correctly refuse "What is the flexible working culture?"?

Yes — no chunk scored above the 0.3 threshold. The refusal template was returned and no LLM call was made.

Did your system retrieve the correct document for "Can I use my personal phone for work files?"?

Yes — top retrieved chunks were from policy_it_acceptable_use.txt.

Which enforcement rule in agents.md prevented answers outside retrieved context?

"Answers must use only information present in the retrieved chunks. Never add context, assumptions, or qualifications from outside the retrieved set."

Your commit message for UC-RAG:

UC-RAG Fix all failure modes: LLM hallucinated without context → implemented sentence-aware chunking, threshold filtering, and retrieved-chunks-only grounding

Verification checkpoints:

• At least 3 test queries return grounded answers (cited from retrieved context)
• "What is the flexible working culture?" returns the refusal template (not a hallucinated answer)
• "Can I use my personal phone for work files?" retrieves IT policy, not HR leave policy
• Chunking produces more than 1 chunk per document (not whole-document embedding)

---

UC-MCP — MCP Server

Paste your tool description from mcp_server.py TOOL_DEFINITION:

"Answers questions about City Municipal Corporation (CMC) policy documents: HR Leave Policy, IT Acceptable Use Policy, and Finance Reimbursement Policy. Returns answers grounded in retrieved document chunks with cited sources. Questions outside these three documents return a refusal message..."

Does it state the document scope explicitly?

Yes — names all three policy documents and explicitly states what the tool will not answer.

Run result: python test_client.py --run-all

✅ tools/list — tool discovered with correct scope description
✅ In-scope: "Who approves leave without pay?" — answer returned
✅ Out-of-scope: "What is the budget forecast for 2025?" — correctly refused
✅ Unknown method → -32601 error returned

Did the budget forecast question return isError: true?

Yes — the refusal template was returned with isError: true.

In one sentence — why is the tool description the enforcement?

The agent reads the tool description to decide when to call the tool, so a specific description prevents the agent from making out-of-scope calls.

Your commit message for UC-MCP:

UC-MCP Fix vague tool description and unhandled protocol errors: agent attempting out-of-scope calls → rebuilt mcp_server.py to add exact CMC document scope and compliant error handling

Verification checkpoints:

• Tool description explicitly states document scope (which policies are covered)
• Tool description states refusal behavior for out-of-scope queries
• python test_client.py --run-all executes without connection error
• Budget forecast question returns isError: true (out of scope)

---

[github-actions]

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!