Build an n8n AI Agent node with tools and MCP servers, require human approval for risky tool calls, and test it with evaluations before it touches real data.
Topic
Builder tools
Assistants that help someone read, design, or change software. These stay out of the three tracks.
Add tools to an AI by Zapier step so it can look things up and act across your apps, with per-tool approval, a task limit and Zap history, then migrate any old Zapier Agents.
Store document embeddings in Postgres, search by meaning, and restrict results per user with row level security.
Model an agent as a graph with memory, resumable runs and approval points, using LangGraph in Python.
Describe an app to Bolt in plain language, plan it first, let Bolt Cloud add the database and login, test with dummy data, run a security check and publish.
Describe what you want, review Agent's plan, let it build and test, roll back with checkpoints, then publish.
Expose files, databases or an internal API to an AI app, the MCP host, through a Model Context Protocol server.
Describe a page or app, refine it in chat or visually, and publish to Vercel or push to GitHub.
Describe an app in chat, get a working frontend, backend and auth you can publish and sync to GitHub.
Install Ollama, pull a model and call its local REST API from your own code without sending data to a hosted service.
Hand multi-file coding tasks, tests and commits to an agent that works inside your repo from the command line.
Assign a well-written issue to Copilot cloud agent (formerly coding agent), review its pull request like any contributor's, and approve workflow runs yourself.
Use Cursor's Agent to explore a repo, plan bigger changes in Plan Mode, roll back with checkpoints and run Agent Review before you commit.