Projects • Prototypes • Experiments

I build things to answer questions research alone can’t.

Small systems, agents, and prototypes used to test an idea before it becomes a roadmap.

Tools used along the way

ChatGPTClaudeGemini EnterpriseMicrosoft CopilotCopilot StudioNotebooksPrototyping toolsAI image & video toolsAI-assisted development platforms

Instruments, not qualifications.

01Built + tested

Evaluation Harness for a Research Repository Agent

A system for making retrieval quality measurable, reproducible, and debatable.

How it works

  1. 1. Model the repository

    Research team models the scope, topics, and intent of the repository.

  2. 2. AI generates questions

    AI generates diverse questions based on the modeling.

  3. 3. Assign & distribute

    Research team members are assigned 20 questions each from the evaluation set.

  4. 4. Answer assigned set

    Team members answer their assigned questions.

  5. 5. Cross-check & debate

    Team reviews each other's answers, flags gaps, and debates where needed.

  6. 6. Refine & iterate

    Consensus builds. We refine the model and improve over time.

The question

Can repository-agent quality be evaluated with evidence rather than “this looks right”?

What I built

  • 10 inquiry types
  • Evaluation test set
  • Cross-checked answer key
  • Debate workflow

What I test

  • Retrieval quality
  • Guardrail behavior
  • Source grounding
  • Consistency & clarity

Impact

Creates a repeatable, defensible way to measure agent performance and improve it over time.

View project details
02In development

Decision Intelligence Layer

A system that helps teams start with the right context before making the next decision.

  1. 1. Start with a problem

    User enters a question or decision need.

  2. 2. Recommend sources

    System identifies relevant enterprise sources.

  3. 3. Human confirms

    Researcher confirms relevance and importance.

  4. 4. Check permissions

    Access control honored by infrastructure.

  5. 5. Assemble context

    Curated context assembled from approved sources.

  6. 6. Decision support

    LLM provides analysis, options, and next steps.

The goal

Improve decision quality by improving the context before the answer.

View concept details

Why it matters

The right decision depends on the right information — accessible, governed, and usable.

03In development

Agent Suite

Two instructional agents built to explore how AI can deepen understanding, not replace effort.

Tiered comprehension agent

Explain photosynthesis.
Great place to start. In your own words, what do you think photosynthesis is?
Plants are able to use food using sunlight.
Exactly. Now, what are the raw materials plants use?

Design question

How far can the system push the learner upward before we risk discouragement?

View project details

Socratic questioning agent

Why do you think the character made that choice?
Because they were angry.
What evidence in the text supports that? What else could explain that choice?

Design question

How long can an agent hold the line before productive difficulty becomes frustration?

View project details

Shared premise

Learning sticks when the right level of friction meets the right kind of support.

See the longer case studies