Venture Crane

Articles

The Grant Table Is the Kill Switch: Access Control for a Shared AI Employee

Jul 1, 2026 · 8 min read

Several people share one autonomous agent: the identity provider proves who they are, but a grant read live on every request decides whether they still get in.

What an Agent May Do Is Not How It May Start

Jun 30, 2026 · 7 min read

One authorization setting was answering two unrelated questions. Splitting exposure from initiation is what made the entitlement model enforceable.

Bake Every Author-Built Connector In, Keep It Inert Until Bound

Jun 29, 2026 · 8 min read

When a vendor has no MCP server you author your own. The real decision is where that connector code lives: baked into one shared image, inert until bound.

Template Gives You Consistency, Not Credibility

Jun 28, 2026 · 6 min read

Per-vertical content a practitioner respects cannot be stamped from one template. Depth at altitude takes serial authoring through an adversarial critique loop.

Ground It or Flag It: Ending Agent Confabulation

Jun 23, 2026 · 7 min read

The agent failure to fix is not guessing - it is confident, unmarked inference dressed as fact. The cure separates disclosure from verification.

An Agent Should Write the Script, Not Be the Loop

Jun 21, 2026 · 5 min read

When an agent task burns money, the reflex is to make the run survivable. Often the real fix is upstream: the agent should write the script, not be the loop.

We Accidentally Built a Shadow System of Record

Jun 20, 2026 · 6 min read

A review caught our agent console rendering the customer's own data back to them. We had built a shadow system of record nobody designed.

claude.ai as a Routing Surface, Not a Content Generator

Jun 17, 2026 · 5 min read

MCP turns a conversation interface into a capable operator by exposing production tools directly - the LLM becomes the routing layer, not a content generator.

Overlay Drift: The Fleet Observability Gap That Looks Like a Deployment

Jun 17, 2026 · 5 min read

Deploying a new overlay version does not mean all instances have it - persistent processes require active drift detection, not deployment confirmation.

An Agent That Can Edit Its Own Autonomy Ceiling Has No Ceiling

Jun 16, 2026 · 5 min read

OS-level file ownership - not prompt instructions - is the only reliable way to prevent an AI agent from modifying its own governance constraints.