Step-by-step articles on Tool Use & Agent Loops, part of our AI Agents collection.
Showing 10 articles
"Agent" is used for many things, but the core idea is simple: an AI agent is an LLM that decides which tools to call, sees the results, and keeps going until the task is done . Your code runs the tools; the model chooses what to do next. The loop Send the user...
Tool use (also called function calling) lets a model request that your code run a function. The model never runs code itself; it returns a structured request and waits for your result. 1. Describe the tools tools = [ { "name": "search_products", "description":...
The model chooses tools based only on their names, descriptions and schemas. A vague description is the most common reason an agent picks the wrong tool or invents arguments. Write descriptions like documentation for a new teammate { "name": "create_refund", "...
The manual agent loop is always the same: call the model, run the requested tools, send results back, repeat. The Anthropic SDKs include a tool runner (currently in beta) that does this for you, with type-checked tool inputs. TypeScript with Zod import Anthrop...
When a request needs several independent lookups ("compare the weather in Delhi, Mumbai and Bengaluru"), the model can return multiple tool_use blocks in a single response. Running them one after another wastes time. Execute in parallel const toolUses = respon...
Reading data is low-risk. Sending emails, moving money or deleting records is not. A human-in-the-loop step pauses the agent and asks for approval before risky tools run. Classify your tools Read-only (search, get_*): run automatically. Reversible writes (draf...
An agent can only do what its tools allow. Good guardrails assume the model will sometimes make mistakes or be manipulated, and limit the damage when it does. 1. Least privilege Give each agent only the tools its job needs. Scope credentials: a read-only datab...
Every turn of an agent adds to the conversation: tool calls, large tool results, the model's replies. Long tasks can grow past the context window, and even before that, a bloated context makes the model slower, more expensive and less focused. 1. Keep tool res...
Agents are exciting, but they cost more, are slower and are harder to test than fixed code. Many features are better built as workflows : LLM calls arranged in a flow that your code controls. Start with the simplest thing One LLM call - classification, summari...
Agents are non-deterministic, so traditional "input X gives exactly output Y" tests only go so far. A solid testing strategy combines normal tests for your code with task-level evaluations of the agent's behaviour. 1. Unit-test the tools Tools are ordinary fun...
