Casey Knott
Menu

Project index

Evidence, classified

Independent work, lab work, proposed designs, and one professional team contribution. Maturity labels come from the source portfolio, not from marketing.

Standardize

GPT stage

Source guide

Author draft

Operator

Chooses next stage

Extract metadata

GPT stage

Human review

Before publication

ServiceNow

Self Help

Generate HTML

GPT stage

Source guide
external — Author draft
Operator
human — Chooses next stage
Standardize
agent — GPT stage
Extract metadata
agent — GPT stage
Generate HTML
agent — GPT stage
Human review
approval — Before publication
ServiceNow
output — Self Help

Project 01 · Knowledge systems

Multi-Stage Knowledge Publishing Workflow

ServiceNow Self Help content, split into inspectable LLM stages.

LLM workflow · AppliedProfessional experience — team member, not lead
Architecture
Source guide → Operator → Standardize → Extract metadata
Security equivalent
Human review before publication → Privileged change authorization
Strongest lesson
Who determines the next action

Owner context

Reference answer

Vehicle configuration

Domain rules

Gemini Gem

Configured assistant

Technical reference

Owner decision

Purchases, mods, safety

Owner context
data
Vehicle configuration
data
Technical reference
data
Domain rules
policy
Gemini Gem
agent — Configured assistant
Reference answer
output
Owner decision
approval — Purchases, mods, safety

Project 02 · Domain AI

Domain-Specific AI Expert

A Gemini Gem constrained to one vehicle, not the average Gladiator.

Configured assistant · AppliedIndependent project
Architecture
Owner context → Vehicle configuration → Technical reference → Domain rules
Security equivalent
Recommend-only assistant → No standing change privilege
Strongest lesson
Name the class honestly

Schedule

Collect sources

Normalize

Before the model

Gemini analysis

Structured report

Clean skip

No partial publish

Schedule
tool
Collect sources
data
Normalize
validation — Before the model
Gemini analysis
agent
Structured report
output
Clean skip
policy — No partial publish

Project 03 · Automation

TinyClaw

Locally hosted scheduled market reporting that would rather skip than lie.

LLM workflow · AppliedIndependent project
Architecture
Schedule → Collect sources → Normalize → Gemini analysis
Security equivalent
Freshness checks → Integrity of evidence before use
Strongest lesson
Quality is bounded upstream

Inspect document

Untrusted input

Classify state

Article type, gaps

Choose tool

From allowlist

Validate output

Deterministic checks

Request approval

Publish

Correct / retry

Bounded

Safe stop / escalate

Audit log

Tools, decisions, retries, disposition

Inspect document
agent — Untrusted input
Classify state
agent — Article type, gaps
Choose tool
agent — From allowlist
Validate output
validation — Deterministic checks
Correct / retry
tool — Bounded
Safe stop / escalate
policy
Request approval
approval
Publish
output
Audit log
data — Tools, decisions, retries, disposition

Project 04 · Agentic publishing

Knowledge Publishing Agent

A specified, not-yet-built agent that decides which stage a document actually needs.

Agentic workflow · Proposed designIndependent proposed design — not yet built
Architecture
Inspect document → Classify state → Choose tool → Validate output
Security equivalent
Tool allowlist → Authorized capability boundary
Strongest lesson
Enforced loops, not requested loops

Case intake

Suspicious activity reported

Plan collection

Agent decides what evidence is needed

Run approved tools

Read-only, allowlisted, least privilege

Processes / parent-child

Services / autoruns

Network / DNS / logs / hashes

Normalize evidence

Correlate findings

Assess confidence

Fact vs inference

Safe stop / escalate

Recommend actions

With validation + rollback steps

Human analyst decision

Triage JSON

Executive summary + timeline

Risk score with evidence

Case intake
agent — Suspicious activity reported
Plan collection
agent — Agent decides what evidence is needed
Run approved tools
tool — Read-only, allowlisted, least privilege
Processes / parent-child
data
Services / autoruns
data
Network / DNS / logs / hashes
data
Normalize evidence
validation
Correlate findings
agent
Assess confidence
agent — Fact vs inference
Safe stop / escalate
policy
Recommend actions
tool — With validation + rollback steps
Human analyst decision
approval
Triage JSON
output
Executive summary + timeline
output
Risk score with evidence
output

Project 05 · Security triage

Home-Lab Endpoint Triage Agent

Read-only evidence collection, then a human. Adversarially tested in isolation.

Agentic workflow · Built & adversarially testedIndependent home-lab — not employer production
Architecture
Case intake → Plan collection → Run approved tools → Processes / parent-child
Security equivalent
Read-only collection → Least privilege / separation of duties
Strongest lesson
Prove the limits under attack

Product requirement

Human requirements definition

AGENTS.md / agent policy

AI / Codex engineering agent

Credentials — human-only

Workbook / documentation generation

Formula validation

Schema / structure

Compatibility tests

File integrity

Visual QA (rendered PDF)

Human approval

Internal QA artifacts kept out

Customer packaging

Hash / integrity validation

Excel / Google Sheets delivery

Etsy / website distribution

Product requirement
external
Human requirements definition
human
AGENTS.md / agent policy
policy
Credentials — human-only
approval
AI / Codex engineering agent
agent
Workbook / documentation generation
tool
Formula validation
validation
Schema / structure
validation
Compatibility tests
validation
File integrity
validation
Visual QA (rendered PDF)
validation
Human approval
approval
Customer packaging
tool
Internal QA artifacts kept out
policy
Hash / integrity validation
validation
Excel / Google Sheets delivery
output
Etsy / website distribution
external

Project 06 · Product engineering

Clearward

Move toward a calmer life — structured organization systems as a product.

AI-assisted product engineering · AppliedIndependent digital-product business
Architecture
Product requirement → Human requirements definition → AGENTS.md / agent policy → Credentials — human-only
Security equivalent
AGENTS.md control plane → Authorization policy for privileged automation
Strongest lesson
Privileged automation, even for spreadsheets

Public user (browser)

Next.js public routes / UI

Service-role credentials stay server-only

API / RPC boundary

Server-only; validate every input

AI drafting agent

Validation agent

Human approval gate

Published content

Immutable, versioned

Private tables · RLS · service-role only

Public read API · RLS public-safe columns

CI/CD validation

ESLint, Vitest, pgTAP, Playwright, migrations, audit

Human-approved deploy

Public user (browser)
external
Next.js public routes / UI
application
API / RPC boundary
validation — Server-only; validate every input
Service-role credentials stay server-only
policy
AI drafting agent
agent
Validation agent
validation
Human approval gate
approval
Published content
data — Immutable, versioned
Private tables · RLS · service-role only
data
Public read API · RLS public-safe columns
data
CI/CD validation
validation — ESLint, Vitest, pgTAP, Playwright, migrations, audit
Human-approved deploy
approval

Project 07 · Secure platforms

Basaltborne

Know your gear. Run what works. — AI-assisted publishing with RLS and CI as controls.

AI-assisted platform engineering · DevelopingIndependent production-track platform
Architecture
Public user (browser) → Next.js public routes / UI → API / RPC boundary → Service-role credentials stay server-only
Security equivalent
Row-Level Security → Authorization enforced at the data layer
Strongest lesson
Publication is privileged