Eve library

ADR-0003: Multi-Agent AI System

Guide

Revision 1

On this page

Date: 2025-09-25
Status: Accepted
Deciders: AI Platform Team

Context#

Generating high-quality responses requires multiple specialized capabilities:

  • Information retrieval (sources, citations)
  • Teaching/instruction (persona style, pedagogy)
  • Safety moderation (content policies)
  • Audio narration (SSML preparation)

A single monolithic prompt cannot effectively handle all concerns.

Decision#

Implement a Multi-Agent System (MAS) where specialized agents collaborate:

Agents#

Agent Responsibility
Librarian Query planning, source retrieval
Teacher Response generation, persona style
Safety Pre/post moderation
Narrator SSML preparation for TTS

Orchestration Pattern#

  1. Parallel Phase: Librarian + Safety pre-check run concurrently
  2. Generation Phase: Teacher generates with sources
  3. Moderation Phase: Safety post-check
  4. Narration Phase: Narrator prepares SSML (if audio)

Rationale#

Why Multi-Agent#

  • Separation of concerns: Each agent optimized for its task
  • Parallel execution: Reduces latency
  • Modularity: Agents can be updated independently
  • Testability: Each agent tested in isolation

Why This Agent Set#

  • Librarian: Specialized for retrieval-augmented queries
  • Teacher: Focus on pedagogical quality
  • Safety: Dedicated to policy enforcement
  • Narrator: TTS-specific optimizations

Alternatives Considered#

  1. Single Large Prompt: Too complex, hard to maintain
  2. Sequential Pipeline: Higher latency
  3. Router-only: Missing collaboration benefits

Consequences#

Positive#

  • Better response quality
  • Lower latency through parallelism
  • Easier maintenance and testing
  • Flexible agent composition

Negative#

  • Coordination complexity
  • More LLM calls (cost)
  • Debug complexity

Mitigations#

  • Comprehensive logging with correlation IDs
  • Agent-level metrics
  • Cost optimization through caching