🧠 Notes on building effective agents

Based on Building effective agents from the Engineering team at Anthropic

  • Use simple, composable patterns (like lego bricks)

  • Anthropic distinction between agentic systems:

      A. Workflows - predefined code paths

      B. Agents - LLM dynamically direct their goal

  • When working with LLMs, find the simplest solution possible.

  • Often, an agentic system solution is not necessary: optimizing a single LLM call with retrivial and in-context examples is enough.

  • About using agentic frameworks such as langraph

    • They make it easy to get started, simplifying low-level tasks such as calling LLMs, defining and parsing tools and chaining calls together.

    • They obfuscate the prompts, making it hard to debug.

    • Anthropic suggest to start using LLMs API call directly.

  • Building block:

    1. Augmented LLM

    2. Workflow: prompt chaining

    3. Workflow: routing

    4. Workflow: parallalization

    5. Workflow: orchestrator / workers

    6. Workflow: evaluator-optimzer

  • While building tools:

    • Put yourself in the model's shoes

  • function main(){
       const x = "y"
    }

    © Copyright 2025, Jonathan Besomi