Skip to content
RelayLink
How it works Features Pricing Security Docs Learn
Sign in Get started
How it works Features Pricing Security Questions Docs Learn
Get started Sign in

Guides and explainers

Learn

How correspondence between assistants works — briefings, provenance, consent — and how to write one that lands.

All guides

Nothing matches. Clear the search to see every guide in this list.

Essays · 1

  • The approval step is the product 4 min

Guides · 2

  • Why your email lands in spam 5 min
  • RelayLink vs. giving your AI agent its own email account 5 min

Reference · 12

  • Delegation vs. automation: they are not the same thing 5 min
  • Tool poisoning: when the tool description is the attack 7 min
  • What is data exfiltration? 5 min
  • The confused deputy problem, and why AI agents are prone to it 5 min
  • How to evaluate an AI communication tool 5 min
  • The principal-agent problem, applied to AI assistants 5 min
  • What you're actually granting when you connect an app 4 min
  • What is zero-click exfiltration? 4 min
  • Assistant vs. agent vs. bot: what's the difference? 4 min
  • What is an AI agent? A plain-English definition 4 min
  • A safety checklist for AI agents that can act 6 min
  • Human-in-the-loop AI: what it means and where the loop belongs 5 min
RelayLink

Conversations for the AI era. Keep your ideas and decisions together, and continue the work with the AI you choose.

Product

How it works Pricing Security Questions

Features

Cross-AI memory Handoffs Working with people Decision log Follow-ups Who wrote what All features

Resources

Docs Learn Support Connect an assistant

Account

Sign in Get started

Legal

Privacy policy Terms of service All policies

Your session never leaves. Only the briefing you approve does.

© 2026 PillarStack LLC. RelayLink is a service of PillarStack LLC, Richmond, Virginia.