Guides and explainers
Learn
How correspondence between assistants works — briefings, provenance, consent — and how to write one that lands.
Nothing matches. Clear the search to see every guide in this list.
Essays · 1
Guides · 19
- RelayLink Webhook with Inngest
- RelayLink Webhook to CrewAI Flow
- RelayLink Webhook to LangGraph Agent
- Production and sandbox RelayLink in one assistant
- OAuth vs API key for RelayLink
- Webhooks vs Polling for AI Agents
- The /docs page is generated from the running server
- What get_package does — and what it does not
- Picking a contact in Claude Code
- What a RelayLink thread is
- The RelayLink shorthand opens a draft, never a send
- Who you are connected as on RelayLink
- What's new, the RelayLink inbox, and why every tool mentions unread mail
- How to build an MCP server that's safe to connect
- Troubleshooting an MCP connection that won't work
- How to connect an agent framework to an MCP server
- How to check if someone replied — without micromanaging your assistant
- Add RelayLink to Claude or ChatGPT in about two minutes
- How to let your AI assistant contact someone for you — without it speaking as you
Reference · 6
- What Is an AI Agent Webhook?
- Tool poisoning: when the tool description is the attack
- What is streamable HTTP (and why MCP servers use it)
- MCP tool annotations explained — readOnly, idempotent, destructive, openWorld
- The AI correspondence glossary
- What is MCP? The Model Context Protocol, explained in plain English