Gee, AI Process and Automation Engineer
Gee builds AI automation that runs in production: scheduled jobs, agents with approval gates and audit trails, MCP servers and Claude Code skills. He also brings a long background in IT operations: Linux, networks, security and telephony.
At a glance
- Location
- Iloilo, Philippines
- Focus
- Production AI automation
- Agent governance
- Claude Code as a platform
- Profile approved
Featured work
- Flagship
Governed AI action platform: architecture, data platform and advisory agents
Took an online retailer from a map of recurring departmental work to one shared, governed AI platform: rate-limit-safe nightly ingest into one warehouse, advisory agents that prove every figure and wait for a person, and costed designs for the next agents.
Part design, not built
- Flagship
Department AI agents with human approval gates
A family of chat-based department agents on shared, hardened foundations where the model does the routine work but every consequential action waits for an expiring, single-use human approval and every figure comes from code.
- Flagship
Crew and equipment scheduling: from discovery to production
From interview- and workbook-based discovery and a priced build-versus-buy decision to a production scheduling platform whose tested conflict engine catches clashes as the plan is edited, with enterprise sign-in and managed database operations.
- Flagship
Governed publishing pipeline and sanitized AI portfolio
This portfolio: private work reaches the public only through a machine-enforced chain of sanitized draft, deterministic privacy scan, explicit human approval and a signed public record anyone can verify, with an assistant that answers only from approved content.
- Case study
secure-minimal-agent
A small, public, provider-agnostic reference agent that shows security and correctness disciplines in as little code as possible, with its safety claims pinned down by tests.
- Case study
Automated water test bench prototype with image classification
An inexpensive bench-top prototype that automates water sampling, chemistry readings and sample preparation for imaging, sorts the prepared sample with an image classifier and merges both results into one overall risk rating in plain words.
Specialties
Production AI automation
scheduled jobs and agents that run without a person watching
Agent governance
approval gates, propose-only agents, deny-by-default tools and append-only audit trails
Claude Code as a platform
custom skills, slash commands, hooks and plugins
Multi-model review
Claude, Codex and Gemini check the same work independently, then the findings are combined
MCP servers that connect AI assistants to business systems
LLM guardrails enforced in code, based on measured failures of prompt-only rules
How this site publishes
The site itself runs on the pattern in his work: “Agents that propose rather than act, with approval gates and append-only audit trails”.
Private work
Work starts in private. None of it is public.
Sanitize
Secrets are removed and names become placeholders before any AI model sees the text.
Scan
A rule-based privacy scanner checks the draft. A block sends it back.
Owner approval
The gate. Nothing moves past it without the owner’s own OK.
Signed record
Each approval is signed and added to a public hash chain.
Public site
The site is built only from signed files. Any other content fails the build.