AI Document Pipeline
Don't ship it yet.
The tuned pipeline scored 82% against an 85% bar, with contracts at 60%. The eval gate held it back.
For five years, I have put AI chatbots in front of real customers at a regulated trading company. I test the AI before launch, set a bar it must clear, and say "not yet" when it is not ready. Below are three of my projects, with the key decision in each and how it works.
At OANDA, a regulated online trading company, I owned the AI and automation portfolio for client experience: chatbots, autonomous agents, and the human review that keeps them accountable.
The decision that mattered most in each, and a diagram of how it works. Open a project for the full case.
Don't ship it yet.
The tuned pipeline scored 82% against an 85% bar, with contracts at 60%. The eval gate held it back.
Run the cheapest, most predictable guardrail before the model.
Risky questions are refused by a keyword filter before Gemini is called, and before they count against a visitor's daily limit.
Upset customers and exception requests go to a person, not the bot.
That's where a fluent wrong answer does the most damage, so the bot writes a hand-off summary instead of a reply.
6 projects in total, each with its decision and design.
See all projects →Ask AI answers questions about my work using only my resume and GitHub projects, and cites its sources. These are the kinds of questions it's built to refuse. Try them, or try your own.