Multi-Step Workflow Orchestration

Complex requests often contain multiple concerns that should be decomposed and handled efficiently.

Problem: Sequential Processing

For complex requests like "I've been charged twice, my discount didn't apply, and I want to cancel", agents may:

• Process concerns one at a time (slow, many round-trips)
• Fetch redundant customer data for each concern
• Lose context between concerns

Solution: Decompose and Parallelize

1. Decompose: Break the request into distinct concerns
2. Share context: Fetch customer data once, share across all concerns
3. Investigate in parallel: Look into each concern simultaneously
4. Synthesize: Combine findings into a unified resolution

For Few-Shot Approach

If the agent handles single concerns well (e.g., 94% accuracy) but struggles with multi-concern requests (58%), the fix is adding few-shot examples demonstrating correct reasoning and tool sequences for multi-concern messages.