Handshake.AIv0.2.3
ConsoleDocsSpecNotesCompanySign inApply to be a design partner
  • Console
  • Docs
  • Spec
  • Notes
  • Company
  • Sign in
  • Apply to be a design partner
Notes

Working notes from the team building Handshake.

Short essays on the agent trust problem, what we're building, and what we're learning from design partners. Not a blog. Not marketing. Notes.

Why MCP needs a trust layer

The Model Context Protocol gave agents a way to talk to tools. It deliberately left the harder question, who's allowed to do what, on whose authority, with what evidence, for someone else to solve. Here's why that gap matters more every week, and how we think about filling it.

๐Ÿ“… Apr 24, 2026โฑ 6 min read

Three patterns we keep seeing in stalled enterprise agent rollouts

From conversations with security teams at half a dozen Fortune 500s piloting agents in 2026: the same three blockers come up every time. Identity, delegation provenance, and audit trail. None are model-quality problems.

๐Ÿ“… Apr 18, 2026โฑ 4 min read

Receipts, not logs

Why we're building a signed-receipt primitive into the protocol from day one, and what enterprises actually need that current observability tools don't provide.

๐Ÿ“… Apr 11, 2026โฑ 5 min read
Handshake.AI, v0.2.3 spec early access ยท Last updated May 2026
Open-core SaaS team building the Handshake Protocol on a standards-track substrate.

Product

  • Overview
  • Console

Developers

  • Spec
  • Docs

Company

  • About
  • Notes
  • Careers
  • Become a design partner

Legal

  • Terms
  • Privacy
  • Sub-processors
  • Security
Apply to be a design partnerโ†’