Venture Crane

Articles

The Harness Is the Product: What You Own When the AI Brain Is Rented

May 30, 2026 · 8 min read

The frontier model rotates roughly monthly. The durable asset is the harness it plugs into. Define the harness by function, not by today's tool.

You Cannot Instruct an Agent Not to Leak

May 27, 2026 · 8 min read

Memory notes told the agent not to echo secret values. It did anyway, twice. The fix was structural enforcement at the tool boundary, not better instructions.

Observability That Is Born and Dies With the Tenant

May 25, 2026 · 8 min read

When every customer runs an isolated agent deployment, monitoring becomes per-tenant and lifecycle-aware. The heartbeat, webhook, and fleet stack we wired.

Retiring a Fork That Stopped Earning Its Keep

May 23, 2026 · 8 min read

A dependency you control "for safety" can quietly become pure cost. We audited a fork from first principles and found the safe move was to delete it.

Collapsing Two Auth Systems Into One Without Rewriting 73 Call Sites

May 21, 2026 · 8 min read

A session shim that rebuilds the old session shape from a new identity provider lets you swap auth under dozens of call sites without a big-bang rewrite.

Parallel-session worktree isolation: when one agent's `git add -A` sweeps another's edits

May 5, 2026 · 6 min read

Two sessions on the same repo. One runs git add -A. The other's uncommitted work ships in the wrong PR. The fix is filesystem isolation, not branches.

Shipped Friday, retired Monday: kill-discipline in four days

May 5, 2026 · 4 min read

A Phase 1 feature shipped end-to-end Friday. Monday a P0 portal bug closed it. Four days from launch to clean removal.

Plan-declared workstreams: every plan ships its own execution topology

May 4, 2026 · 6 min read

Replacing ad-hoc agent coordination with a fenced YAML execution-mode block at the bottom of every approved plan. One gate, plan-internal parallelism.

How an agent's friction report became a fleet-wide git rubric

May 3, 2026 · 5 min read

An agent complained about rebase and force-push policy walls. A four-PR arc shipped a documented branch-class rubric every session inherits.

Validating pattern-matchers against a real corpus, not your imagination

May 2, 2026 · 5 min read

Our v1 reflex hook had zero corpus recall. v2 was corpus-driven from the start. Mine real transcripts before shipping pattern-matching code.