Maxwell Collins — Engineer code-rescue.com

Senior software engineer. I build production systems with AI — fast — and the machinery that keeps them correct.

Seventeen years across the full stack — backend, frontend, mobile, data. I build with AI agents under a framework I designed (hooks, structural rules, quality gates that make wrong outcomes impossible), so I move fast without shipping bugs.

17 yrs building software 100+ applications first code at age 12

Open to senior software, AI, and platform engineering roles — full-time or contract, on a team. · Tampa, FL · ET · remote

§ 01 · how i work

One thesis runs through everything I build.

Whether it’s a small internal tool or a million-line legacy estate, the same discipline applies — it’s how I move fast without breaking things, and the difference between code that works once and code you can trust in production.

— enforced the same way across 40+ systems

  1. R1

    Declare a fact once.

    Every other surface derives from it — schema, rules, UI, audit. No hand-synced copies that drift apart.

  2. R2

    The AI proposes; a deterministic verifier disposes.

    Nothing a model generates reaches a side effect — a write, a deploy, a sent message — without passing a mechanical check it can't talk its way around.

  3. R3

    Make the mistake impossible.

    Bad actions are blocked structurally, before they can happen — fail-closed gates over careful prompts. And the guard proves it fires, or the build fails.

  4. R4

    Append-only, evidence-first.

    A claim without a resolvable citation doesn't ship. Truth resolves to a real artifact, or it doesn't count.

§ 02 · selected work

How to read the tags: repo ↗ is public — click to verify the code yourself. private · by capability is client work, described by what it does, never by whose it is. Designed-but-not-yet-built work is labeled as such; nothing here is inflated.

01Legacy estate · AI control plane private · by capability

Letting AI safely operate a million-line legacy estate

What
A federated control plane that lets AI agents read and reason over an 8-application, ~1.78M-line polyglot legacy estate (PHP, Laravel, iOS, Android) without ever breaking it.
Hard problem
Turning an un-editable, multi-decade brownfield — the kind that defeats whole teams — into something an AI can work over safely.
Approach
Tiered permissions (some repos read-only, some guarded-edit), a typed hook-event boundary grounded in real payloads, a fail-closed gate, and a control↔contract meta-test that refuses to ship a guard it can’t prove fires — over nine MCP servers (seven of them code-graph) spanning the estate.
Result
Agents operate the estate safely, with a complete, tamper-evident audit trail of everything they do.
02Correctness factory · self-governing private · by capability

The factory that builds correct systems

What
A project factory that stamps every new repo with a type frame (illegal states won’t compile) and a fail-closed process harness (bad agent actions are blocked before they reach disk).
Hard problem
Making correctness the default for every project I touch — and proving the guards actually work, not just claiming they do.
Approach
The harness governs its own construction: every control is paired with a contract whose must-block example runs through the real entrypoint, so a guard that can’t prove it fires turns the build red. An append-only audit ledger records every block as tamper-evident evidence.
Result
New systems start correct by construction — and the enforcement is demonstrated, never asserted.
03Product SaaS · shipped at scale private · by capability

A property SaaS, rebuilt so illegal states can’t compile

What
A multi-product property & trust-accounting platform — the modern rebuild of a SaaS suite I originally led to 200+ enterprise clients with a team of 8.
Hard problem
Most systems catch bad data with tests and hope; in trust accounting a wrong value is a real liability. The goal was to make the bad state structurally impossible.
Approach
44 structural (ast-grep) rules with valid/invalid fixtures — penny-exact integer money, UUIDv7-only, no hard-delete, audit-log-on-insert — inside an 18-step quality gate that tests its own rules. A feature can’t be built until its contract survives a 7-agent adversarial review.
Result
The bug is removed by construction, not caught by luck — on a product I’ve already shipped and scaled.
04AI pipeline · hallucination firewall private · by capability

A document pipeline that cannot lie into its output

What
A six-stage pipeline that extracts findings from construction-bid PDFs with AI — and treats the model as untrusted.
Hard problem
A language model will confidently invent evidence that was never in the source.
Approach
Every finding survives only if its quoted evidence is a verbatim substring of the source page; on a miss it is permanently deleted to a forensic rejected-log. A hallucination firewall written in code, not hoped for in a prompt — behind a SHA-256 hash-chained audit.
Result
Hallucinations are structurally unable to reach the result, and that property is proven with tests.
05AI evaluation · self-improvement private · by capability

AI that scores and improves AI — without removing a safety rule

What
A multi-tenant platform that scores voice-agent calls, mines failure patterns across organizations, proposes prompt fixes, and gates them.
Hard problem
Letting AI evaluate and tune AI without ever silently deleting a guardrail or pushing a regression live to real callers.
Approach
A four-layer quality gate — including two independent AI judges that block any change which would remove a safety instruction — a memory of fix-types that failed before, and a hard staging boundary where going live needs a human-only confirmation flag (designed after a real incident that took an agent partially offline).
Result
Every AI-proposed change is held behind deterministic gates the whole way to production.
06Agent governance · plugin goalpost ↗

goalpost — stopping agent goal-drift

What
A Claude Code plugin that stops an agent from drifting off task or claiming "done" before it is.
Hard problem
Reliably telling a real done-claim from narrow-scope completion text — portably, across BSD and GNU grep, with no word-boundary assertions.
Approach
Carve-out-aware completion-vocabulary detection, dual-layer state immutability (file-tool + bash), and a CLI that strips sycophancy-activating language from prompts — grounded in interpretability research.
Result
Fail-closed hooks that block a false "Stop" before it lands.
07Autonomous daemon · sensor-verified habit-daemon ↗

habit-daemon — completion that can’t be gamed

What
An always-on daemon that refuses to take your word that you did something.
Hard problem
A self-report is worthless as evidence; the system has to verify against the real world.
Approach
Completion is checked against real sensor data (Concept2 erg, Garmin sleep, vision on a proof photo). A sensor outage degrades to "no data" — never a free pass. A verifier checks the model’s claimed writes against authorized paths and confirms each file on disk. Hash-chained, append-only audit.
Result
Ships with a real, cited scar: a tight retry loop once spawned ~370k dead sessions — backoff + a circuit breaker are in. I harden after every failure; I don’t claim there are none.
more public work
  • operator-doctrine ↗ the published theory the harnesses enforce — a taxonomy of how AI agents fail, and the countermeasures.
  • cc-guide ↗ an evidence-grounded Claude Code reference: 25 real agent failures, each tied to a primary source.
  • lazyrecall ↗ a Rust TUI for browsing, searching, and resuming Claude Code sessions.
  • research ↗ a research-workspace harness with hook-enforced source vetting.
§ 03 · background

Seventeen years, many domains — one engineering instinct.

Software, construction, home inspection, environmental, real estate. The range isn’t drift — it’s the same way of thinking applied wherever I went.

B.A., Economics (financial applications) — Southern Methodist University

  1. 2025 — now

    Independent engineering — Code-Rescue

    AI control planes, correctness-enforced systems, and citation-verified pipelines — 40+ projects, public and private.

  2. 2024 — 2026

    Founder — environmental & home-inspection services

    Built and ran the engineering, marketing, and compliance solo. FL Home Inspector (HI-18109).

  3. 2019 — 2023

    Project Manager & Real Estate Analyst

    A $10M+ portfolio of 20+ projects — plus the company website, data work, and field operations. Many hats; one engineering instinct.

  4. 2016 — 2023

    Full-Stack Developer & Product Manager — building-inspection SaaS

    Led end-to-end development of a connected SaaS suite to 200+ enterprise clients; coordinated a team of 8 (Agile/SCRUM) at a 98% bug-free release rate.

  5. 2009 — 2016

    Self-taught foundations

    First code at 12, reverse-engineering online games. By 15: Java, C++, JavaScript — 10+ game servers, 50+ freelance sites.