ToolMulti-Step Agent Setups
LangGraph
Low-level framework for stateful, controllable agent workflows.
Effort: High
Task · Production guardrails
Best Practices and Tools for Production AI Agents
Principles, sandboxes, hooks and observability that keep agents predictable once real users and real data are involved.
6 picks
Filter & sort these →- SetupMulti-Step Agent Setups
Deterministic guardrails with Claude Code hooks
Run your own scripts at agent lifecycle events: format, lint, block risky commands.
Effort: Medium
- Use caseMulti-Step Agent Setups
Building effective agents: the patterns
Prompt chaining, routing, parallelisation, orchestrator-workers, evaluator-optimizer.
Effort: Low
- Use caseMulti-Step Agent Setups
12-Factor Agents
Principles for LLM software good enough to put in front of customers.
Effort: Low
- ToolMulti-Step Agent Setups
E2B sandboxes for agent code execution
Secure cloud environments where agents can run code and tools.
Effort: Medium
- ToolMulti-Step Agent Setups
Langfuse: tracing and evals for agents
Open-source tracing and evaluation so you can see what your agent actually did.
Effort: Medium
Newsletter
Practical discoveries, without the noise.
The best new agent workflows and tools we've vetted, with a clear verdict on each. Short, occasional, useful.