Imbas
AI tools, research and implementation
IMBAS

Making AI work for you.

Work with me
Tools

Free to use.

The Reader

Check your AI’s answer and steer what comes next.

See what surfaced, what may be missing, and how it was shaped. Then pick what you want done differently, paste the instruction back into your AI and compare what changed.

Keep a dated receipt of the answer and what the Reader found.

Open the Reader
A real Reader run: an AI answer about Montana employment law, and what it left out.
Real run · what the first answer left out

Input Integrity

Check a PDF before you give it to AI.

A PDF can carry text you don’t see on the page but an AI assistant may read. If that text contains instructions, they can shape what the AI tells you. Input Integrity inspects the file’s content and structure, including text that doesn’t appear on the rendered page, and shows the evidence for each finding.

Download a receipt of what it found.

Free to use. Your file stays on your device.

Inspect a PDF
Input Integrity result on a constructed supplier proposal: the file’s structure carries an instruction to AI assistants, set in white text.
Constructed sample · an instruction to AI set in white text
AI advisory

Work out what’s worth changing.

You may have a process that takes too long, a question about your customers, or an idea you haven’t had time to test. I investigate it with you, weigh the options and help put the decision into practice. AI is part of what I bring, alongside research and experience running a business.

Work with me

For example

  • A quoting tool built around your services
  • A searchable reference from your own documents
  • Reports prepared from the records you already keep
  • Positioning and customer research
The research

Inspect what your AI surfaces — and what it leaves out.

Imbas turns invisible AI behavior into a measurable record. The full argument, the method and the case archive are on the research page:

Explore the research Try the Reader

Why Imbas exists

AI ought to make people more capable.

Every answer shapes what you think, notice, and believe.

One answer is marginal. Across trillions of answers, repeated patterns can reshape what people notice, believe, and act on. As AI enters work governed by external standards, what a model leaves out can matter as much as what it says.

We study how AI “thinks.” Imbas is the inspection layer for AI, built to capture model answers, examine what they surface, omit, and reframe, and track the patterns that persist or change over time.

Thesis

A few degrees of drift can change the destination.

Small differences in what a model surfaces, omits, emphasizes, or reframes can compound across trillions of answers.

Imbas measures the direction and degree of that drift.

Imbas. From the old Irish: illumination, sudden knowing, knowledge brought to speech.