For Readers
You see the answer. You do not automatically see what was left out.
AI answers increasingly shape what people see, search, write, and decide.
Imbas helps you inspect where an answer may have gone thin: what surfaced, what did not, and what appeared only after direct prompting.
What Imbas does and does not do
Imbas doesn’t tell you what’s true. It doesn’t tell you the AI is biased, wrong, hiding something, or lying. It raises an antenna. You can ignore the signal. You can inspect the evidence. You can decide it doesn’t matter for what you were doing. You can decide it does and push the model further.
Why open questions matter
Most people do not ask AI like lawyers cross-examining a witness. They ask normal questions.
- Question
- Is this medication safe?
- Question
- What caused this crisis?
- Question
- How does this policy work?
- Question
- What are the tradeoffs?
- Question
- Who benefits?
- Question
- What should I know?
Users do not know what they do not know to ask. That is where the gap opens.
How to inspect the archive
- Inspect
- Read a case.
- Inspect
- Compare the open prompt against the targeted prompt.
- Inspect
- Inspect the score.
- Inspect
- Look at what surfaced.
- Inspect
- Look at what did not.
- Inspect
- Decide what matters.
What Imbas measures
- Signal
- Missing named mechanisms
- Signal
- One-sided attribution or framing
- Signal
- Redirection away from the concern
The point is not to tell you what to think. The point is to show you where to look again.
Field Notes
Field Notes carries observations from the edge of the archive. No trend-chasing. No “five ways AI is biased” filler. Observations only.