Human-in-the-loop Tool Validation LLMs can become dangerous when hooked up to tools To help safeguard against this you can require human validation before the tool is run (or run in certain ways) https://
python.langchain.com/en/latest/modu
les/agents/tools/human_approval.html
… h/t @PieterHumphrey for the idea

→ View original post on X — @hwchase17