Search

Policy Q&A

Instant answers from 500-page policy documents, with citations to verify.

The Business Case

HR teams field retirement questions repeatedly. Finding answers requires cross-referencing plan documents, IRS guidelines, and company policies. It’s a high-friction, repetitive task that consumes valuable time.

The Solution

A system that routes intelligently between document retrieval (text) and calculation (math) to provide verified answers.

The key insight: Start with classification. Does this user need a policy lookup, a calculation, or both? By handling this routing automatically, we deliver complete answers, not just search results.

The Solution

A multi-step RAG pipeline that:

  • Classifies each question by type (policy, calculation, or hybrid)
  • Routes to document search, SQL querier, or both
  • Synthesizes a final answer with citations and calculation steps shown

All answers include verbatim excerpts with page references, so HR can verify before forwarding to employees.

Key Decisions

1. Routing over retrieval

Most RAG systems retrieve first, then answer. This system classifies first, then decides what to retrieve. That small change made hybrid questions (policy + math) actually work.

2. Show the math

For calculation questions, the system shows its work. “Based on your age (52) and the 2024 catch-up limit ($7,500), your maximum contribution is…” Transparency builds trust.

3. Conservative citations

When in doubt, show more context. A wrong answer that looks confident is worse than a verbose answer that lets the human verify.

Results

  • Handles policy, calculation, and hybrid questions in a single interface
  • Response time: under 10 seconds for most queries
  • Citation accuracy: verbatim excerpts with page numbers for verification

Interested in something similar?

Let's explore how systems like this could work for your team.