Project 2: High-Precision Interaction Model Lab

Harden intents, slots, and repair prompts until quality becomes measurable and repeatable.

Quick Reference

Attribute Value
Difficulty Level 2 (Intermediate)
Time Estimate 1 week
Main Programming Language TypeScript
Alternative Programming Languages Python, Kotlin
Key Topics Intent overlap, slot normalization, repair ladders

1. Learning Objectives

  1. Reduce intent confusion rate with systematic utterance curation.
  2. Build a slot normalization pipeline with validation checkpoints.
  3. Measure prompt quality using conversion by repair level.

2. All Theory Needed (Per-Concept Breakdown)

Concept A: Intent Collision Management

  • Fundamentals: intents should represent user goals, not sentence patterns.
  • How it works: compute confusion matrix on evaluation utterances.
  • Failure modes: too many intents, semantic overlap, low data variety.

Concept B: Repair Ladder Design

  • L1: paraphrase and clarify one missing field.
  • L2: constrained choices.
  • L3: graceful escape with next action.

3. Architecture and Build Plan

  1. Build evaluation corpus of top user phrases.
  2. Instrument confusion and slot quality metrics.
  3. Refactor prompts for one critical transaction intent.

4. Validation and Testing

  • Confusion rate below threshold.
  • No repeated fallback loops.
  • Locale parity on key flows.

5. Troubleshooting

  • Symptom: high recognition, low completion.
  • Fix: shorten prompts and add explicit next-step language.

6. Deliverables

  • NLU quality dashboard.
  • Prompt variant experiment results.
  • Repair ladder state diagram.

7. Stretch Goals

  • Add automatic prompt linting for clarity constraints.