Casey Knott
Menu

Career narrative

A working record, not a role announcement

This site is the public version of a project portfolio compiled in September 2026. It is not a resume written for one job title. It is a record of how I actually build things: architecture first, AI inside explicit boundaries, validation with evidence, and a human decision where being wrong is expensive.

  1. 01

    Operational security systems

    Professional experience

    On the Chelan County PUD service desk I joined a knowledge-publishing effort led by a senior IT specialist. I did not lead that project. Running real Self Help guides through a multi-stage GPT pipeline taught me that AI is something you architect in stages — and that a person still determined every next action.

  2. 02

    Automation

    Independent

    TinyClaw took a daily manual gather and turned it into a locally hosted scheduled pipeline. The design problem was not “call a model.” It was idempotence, freshness, and the willingness to skip a run rather than publish a partial report.

  3. 03

    AI experimentation

    Independent

    A Gemini Gem constrained to one vehicle — a 2025 Jeep Gladiator Sport S with Max Tow — made the configured-assistant class concrete. Context engineering and constraint definition did more than model choice. High-impact suggestions still route to me.

  4. 04

    Agentic systems

    Independent home-lab / design

    The Knowledge Publishing Agent is a specified design, not yet built. The Endpoint Triage Agent is built, isolated, and adversarially tested in a contained Hyper-V lab. That distinction is intentional. I will not collapse a design and a lab build into the same claim.

  5. 05

    Application architecture

    Independent product / platform

    Clearward ships structured Excel and Google Sheets products under software-grade QA. Basaltborne is a production-track publishing platform with Row-Level Security, migrations, API boundaries, and a multi-layer CI suite. Secure platform engineering there is labeled developing, not finished.

  6. 06

    Secure AI thinking

    Throughline

    Across every project the same controls recur: least privilege, tool allowlists, untrusted input, deterministic validation, audit, safe-stop, rollback, and human approval. They are not slogans. They are the parts that survived contact with real failure modes.

How the work is labeled

Professional experience

Chelan County PUD service desk. Team member on the ServiceNow Self Help publishing workflow. A senior IT specialist led that work.

Independent projects

Jeep domain assistant, TinyClaw, Clearward, Basaltborne.

Lab work

Home-lab Endpoint Triage Agent, including isolation and red-team testing against my own agent.

Self-directed design

Knowledge Publishing Agent — specified, not yet built. Phase 2 of the published roadmap.

Skills as evidence

Not a decorative cloud. Each skill points at the projects that actually used it.

AI

Automation

Software Engineering

DevOps / CI/CD

Databases

Cybersecurity

Testing / Validation

Security Systems

Product

These seven projects sit at different scales — a weekend experiment, a home lab, and two platforms built for real customers — but the underlying discipline does not change: define the architecture and the boundaries first, let AI agents do the drafting and the heavy lifting inside those boundaries, validate what comes back with evidence rather than trust, and keep a human decision at every point where the cost of being wrong is real.