> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.hams.ai/platform/agents/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.hams.ai/_mcp/server.

# Building agents

## Docs

- [Agent builder](https://docs.hams.ai/platform/agents/overview.md): The kinds of AI agent you can build, and how to choose between them.
- [Single Prompt](https://docs.hams.ai/platform/agents/single-prompt.md): One set of instructions handles the whole conversation. The quickest agent to build, and the most forgiving.
- [Conversation Flow](https://docs.hams.ai/platform/agents/conversation-flow.md): Draw the conversation as a flow, and control exactly when it moves from one step to the next.
- [Multi-Prompt (Squad)](https://docs.hams.ai/platform/agents/squad.md): Combine agents you have already built into one, and let them hand the caller to each other.
- [Agent settings](https://docs.hams.ai/platform/agents/settings.md): Every panel on an agent — what it controls, what the values mean, and which ones matter.
- [Tools](https://docs.hams.ai/platform/agents/tools.md): The actions an agent can take beyond talking, and how to build each kind.
- [Knowledge bases](https://docs.hams.ai/platform/agents/knowledge.md): Give an agent your documents to answer from, instead of writing everything into its prompt.
- [Alerts](https://docs.hams.ai/platform/agents/alerts.md): Be told the moment a pattern you care about appears in an agent's calls, instead of finding it later on a dashboard.