Agent Architecture/Prompt Engineering for Agents
Intermediate9 min

Few-Shot Examples for Agent Tasks

Using few-shot examples to teach agents complex behaviors: example trajectories, tool call demonstrations, and dynamic example selection.

Quick Reference

  • Few-shot examples for agents include full trajectories: user query → tool calls → observations → final response
  • Place 2-3 examples in the system prompt showing the ideal reasoning and tool usage pattern for your domain
  • Use dynamic example selection: embed the user query, retrieve the most relevant examples from a library, inject into the prompt
  • Examples teach formatting, tool selection order, and reasoning depth more effectively than instructions alone
  • Balance example count vs context budget — each trajectory example consumes 200-500 tokens

Why Trajectory Examples Work

Regular few-shot examples show input → output. Agent few-shot examples show the full trajectory: input → reasoning → tool call → observation → more reasoning → final output. This teaches the LLM not just what to answer, but how to think through the problem.

Example typeWhat it teachesToken costEffectiveness
Input → OutputWhat to sayLow (50-100 tokens)Low for agents — doesn't show reasoning
Input → Tool → OutputWhich tool to useMedium (150-300 tokens)Medium — shows tool selection but not iteration
Full trajectoryHow to think and iterateHigh (300-500 tokens)High — teaches the complete reasoning pattern