Skip to content

Work

What I'm building.

Execution infrastructure for the agent era — and the patents that protect the novel parts. Both products are live; both prove their own claims.

Live · open specification

Execution Protocol

Every AI action. Authorized. Executed. Or stopped. With proof.

One structured message in, one terminal outcome out — executed, instructed, or blocked. The boundary sits outside the model, and every outcome ships a signed receipt you can verify offline.

  • the agent only proposes
  • boundary outside the model
  • receipts verify offline
the authorization chainsix links · none collapsible
principalwho owns the authority?
delegationwhat exactly was granted? bounded
agentproposes — no authority of its own
boundaryoutside model control

is this exact action allowed? — deterministic

proofwhat was authorized? signed
executionwhat happened? credential-isolated · attested ✓

the agent proposes · authority decides · the proof outlives the action

Live · gutencode.com

Gutencode

The hard backend domains — done for you, and proven.

Auth, billing, RBAC, tenancy, an agent runtime — an agent-ready backend spine, printed identical in Python, Go, and Node. Clone it, run the verifier, watch it go green, build on top.

  • 35+ domains
  • Python · Go · Node — identical
  • you can't fake GREEN
your machine

$ git clone … && python verify.py

tests   python ✓ · go ✓ · node ✓

parity  python == go == node

durable state survives restart · errors identical ×3

==== VERIFY: GREEN ====

Patents

13 provisional filings · concept-level only

The portfolio covers the three questions that appear the moment an AI agent takes real actions:

Authorization who says the agent can do that?

Reliability does the agent actually work?

Accountability what did the agent actually do?

The high-level story