Most people get agent design backwards. They start by adding guided workflows when a simple, unguided agent (just an LLM loop + tools) would work better. Why?
1
1
Unguided agents are: - Simpler to implement (single LLM loop + tools) - More powerful by default (no artificial constraints) - Easier to test initially (fewer branching paths)
1
Here's how I build agents: 1. Start with a basic agent loop + function calling 2. Add comprehensive tracing for each tool call 3. Monitor which tool combos actually get used 4. Add guided workflows to address failing evals 5. Use unguided fallback for edge cases

Jan 31, 2025 · 9:34 PM UTC

1
Keep it simple and add new tools incrementally to maintain full test coverage for each new workflow. We're advising this approach to our customers at @gentraceai - lmk what you think!