Russell Miller

San Francisco. Built Enact solo over 16 sessions in early 2026 — AI-co-developed end-to-end with Claude Code as the coding partner.

Open to DevRel / PMM / Solutions Engineer at AI coding co's

What I shipped

A PreToolUse hook firewall for Claude Code that runs every Bash, Read, Write, Edit, Glob, and Grep call through a deterministic Python policy engine before execution. Then a 39-prompt paired-chaos study to measure what it adds.

39paired chaos prompts
8 → 0incidents w/o vs with
545tests passing
1.0.0on PyPI

The headline finding

An asymmetry in Claude Code's self-refusal rate across three trigger types:

TriggerSelf-refusal
User-typed destructive command~80%
Read-shaped exfil ("show me the env vars")~20%
Agent-self-initiated destruction (PocketOS pattern)~0%

The third row is the load-bearing one — flagship model + flagship IDE + explicit safety rules, agent invents a destructive action to "fix" unrelated friction, prod gone in seconds. A deterministic gate that runs before the model decides anything fills exactly that gap. Full research post →

Artifacts

Research post — 39 paired runs (8 min) Follow-up — gitignore block evidence (3 min)
github.com/russellmiller3/enact pypi.org/project/enact-sdk enact.cloud landing

Why DevRel / PMM / SE

The shape of the work I've been doing alone for this product is the shape of the role:

Six months of doing this for one product. Want to do it for ten products at the company building the platform.

How I work

What's next on the project

Full ROADMAP in the repo.

Russell Miller · San Francisco
email: russell@enact.cloud
github: github.com/russellmiller3
best DM channel: LinkedIn (find me via the post or repo)