## Metadata - Author: [[anthropic.com|Anthropic]] - Full Title:: Building Effective AI Agents - Category:: #🗞️Articles - URL:: https://www.anthropic.com/engineering/building-effective-agents - Read date:: [[2025-06-18]] ## Highlights > These frameworks make it easy to get started by simplifying standard low-level tasks like calling LLMs, defining and parsing tools, and chaining calls together. However, they often create extra layers of abstraction that can obscure the underlying prompts ​​and responses, making them harder to debug. They can also make it tempting to add complexity when a simpler setup would suffice. > We suggest that developers start by using LLM APIs ([View Highlight](https://read.readwise.io/read/01jy0nh01ze6ht0ctb1sy2z6jt)) >  ([View Highlight](https://read.readwise.io/read/01jy0p29qyp8k0etjrrzaec7pr)) >  ([View Highlight](https://read.readwise.io/read/01jy0p29rsz7z1mkhhvnztc108)) > **Voting**: > • Reviewing a piece of code for vulnerabilities, where several different prompts review and flag the code if they find a problem. > • Evaluating whether a given piece of content is inappropriate, with multiple prompts evaluating different aspects or requiring different vote thresholds to balance false positives and negatives. ([View Highlight](https://read.readwise.io/read/01jy0p2f3jvt587bgvbx4ck6cv)) >  ([View Highlight](https://read.readwise.io/read/01jy0p34gayg9seyx440svnbj2)) >  ([View Highlight](https://read.readwise.io/read/01jy0p34gz33zm8ztwyr86xkss)) > **Example where orchestrator-workers is useful:** > • Coding products that make complex changes to multiple files each time. > • Search tasks that involve gathering and analyzing information from multiple sources for possible relevant information. ([View Highlight](https://read.readwise.io/read/01jy0p3f7x82v5qsw64t7szgpp)) > Agents can handle sophisticated tasks, but their implementation is often straightforward. They are typically just LLMs using tools based on environmental feedback in a loop. It is therefore crucial to design toolsets and their documentation clearly and thoughtfully. We expand on best practices for tool development in Appendix 2 ("Prompt Engineering your Tools"). ([View Highlight](https://read.readwise.io/read/01jy0p5hkjvfq147cfvet43gej))