How to Build an AI Agent with Tool Use in 2026 (LangChain + CrewAI Guide)

## Quick Answer

AI agents use an LLM as a planner, tools (functions, APIs) to act, and memory for state. Use LangGraph or CrewAI for orchestration; keep tool sets small; always add human checkpoints for irreversible actions.

- Agents work best for multi-step tasks with clear success criteria - Tool explosion (20+ tools) degrades performance — curate carefully - Always sandbox shell/file tools in production

## What You'll Need

- OpenAI-compatible model with function calling (Assisters, GPT, Claude) - Orchestration framework: LangGraph, CrewAI, or custom loop - Tools defined with JSON schema - Observability: Langfuse or LangSmith

## Steps

1. **Define the goal.** Clear success criteria, not open-ended "help the user". 2. **Curate tools.** Start with 3-5. Each needs a clear name, description, schema. ```ts const tools = [ { name: 'search_docs', description: 'Search internal docs by query', parameters: {...} }, { name: 'send_email', description: 'Send an email (requires human approval)', parameters: {...} }, ]; ``` 3. **Write the planner prompt.** System: `You are an agent. Think step by step. Call one tool at a time.` 4. **Build the loop.** LangGraph or a manual while-loop calling the LLM, parsing tool calls, executing, feeding results back. 5. **Add memory.** Short-term: message history. Long-term: vector store of past interactions. 6. **Checkpoints.** For email, payments, deletions — pause and ask user. 7. **Max iterations.** Hard cap at 10-15 to prevent infinite loops. 8. **Observability.** Log every step to Langfuse. Review failures weekly.

## Common Mistakes

- **Too many tools.** Agents lose focus past 10 tools. - **No iteration limit.** Runaway loops cost thousands. - **Ambiguous tool descriptions.** AI picks wrong tool. - **Skipping human approval.** One wrong email destroys trust.

## Top Tools

| Tool | Use | |------|-----| | LangGraph | State machine for agents | | CrewAI | Multi-agent collaboration | | AutoGen | Conversational multi-agent | | Langfuse | Agent observability | | Pydantic | Tool schema |

## FAQs

**Single agent or multi-agent?** Single agent for < 5 steps. Multi-agent when tasks are specialized (researcher + writer + editor).

**How expensive are agents?** $0.10 - $2 per successful task depending on steps.

**Can agents browse the web?** Yes — Playwright MCP or Browserbase as a tool.

**Do agents hallucinate tool calls?** Sometimes — validate arguments with Zod before executing.

**How do I debug agent failures?** Replay from Langfuse traces step by step.

**What about agent security?** Sandbox file and shell tools. Never expose raw DB access.

## Conclusion

Agents shift AI from chatbot to coworker in 2026. Start with LangGraph + 5 tools + Langfuse. Always checkpoint destructive actions. [Misar Dev](https://misar.dev) builds agents from natural language spec.