HomeProductReasoning Modes
EVIDENCE-BASED AI MEDICAL ANALYSIS

Choose how far the AI is allowed to reason.

Evidence-based AI medical analysis is one of three reasoning modes — Evidence-Based, Interpretive, or Extractive — that you choose per query. The mode changes how much the AI infers, never whether it cites: all three hold one citation standard, and unsourced lines never pass silently.

Adams, T. · Case #IME-4812 342 pages · 2 packets
Extractive Evidence-Based Interpretive
Is the right-knee course improving since the injury?
Evidence-based answer
The record documents 7 visits since 4/02, each noting improvement. p.38p.140
Course is consistent with improvement, per the cited visit notes. 7 visits
No imaging after 4/02 — flagged, not assumed. FLAGGED
3 modes
One citation standard
Per query
Switch modes on any question
Flagged
Unsourced lines never pass silently

Extractive: verbatim, and nothing else.

Extractive mode pulls the record’s exact language — quotes, values, dates — each with the page it came from. No paraphrase, no inference, no smoothing. Use it when only the record’s own words will hold up.

Exact quotes with page-level citations
Nothing added between the record and the report
Extractive mode · verbatim only
“Pain improving. Full extension regained. Continue home exercise program.”
Progress notep.140
“Patient reports right knee feels more stable than last visit.”
Visit 4/02p.38
Quotes only. Nothing added between the record and the report.
Evidence-based mode · cited chain
Fact — 7 visits documented since 4/02p.38
Fact — improvement noted at each visitp.140
Conclusion — course consistent with improvementCITED ×2
No post-4/02 imaging — flagged, not assumedFLAG

Evidence-Based: conclusions built only from cited facts.

The default for most legal and claims work. The AI connects facts across documents and draws a conclusion, but every step in the chain is a cited fact from the file. If a step can’t be sourced, the chain stops and the gap is flagged.

Every reasoning step traces to a source page
Anything the record can’t support is flagged, not stated

Interpretive: clinical reading, clearly labeled.

Interpretive mode reads between documents the way a clinical reviewer would — context, significance, what a pattern of findings suggests. Interpretation is labeled as interpretation, kept separate from fact, and still anchored to the cited record underneath.

Interpretation is labeled as interpretation
Citations still attach to every underlying fact
Interpretive mode LABELED AS INTERPRETATION
[Interpretation] A steadily improving course over 7 documented visits would be atypical for an unaddressed structural injury; the pattern reads as consistent with the conservative-care plan in the notes.
Underlying facts citedp.38p.140
Clinical reading, clearly labeled and anchored to cited facts.
Same question · three modes · one standard
Extractive — the record’s own words CITED
Evidence-Based — conclusions from cited facts CITED
Interpretive — labeled clinical reading CITED
Unsourced statements: flagged, never stated
The constant

The mode changes the reasoning. Never the receipts.

Whichever mode you pick, the output holds one standard: every factual statement cited to its page and source, and anything unsourced flagged for human review. That is what makes the work audit-grade and legally defensible — in any mode, at any depth.

See Verifiable AI Citations

Pick the depth. Keep the receipts.

Three steps from question to cited answer, at exactly the reasoning depth your work calls for.

01
Pick the mode

Extractive, Evidence-Based, or Interpretive — set per query, or as a default for the matter or team.

02
Ask, or generate

A plain-English question or a full work product. The AI reads the record at the depth the mode allows.

03
Review with citations

Every line links to its source page. Flagged lines show where the record ran out, queued for your review.

Who controls the reasoning depth.

Different files call for different inference ceilings — the citation standard stays the same.

FAQ

Reasoning modes, answered.

Extractive returns the record’s own words: direct quotes with page citations and nothing added. Evidence-Based draws conclusions, but only from facts it can cite, with every reasoning step traceable. Interpretive adds labeled clinical reading and context — and the facts underneath it are still cited.

Most teams file from Extractive or Evidence-Based output: Extractive when you need the record verbatim, Evidence-Based when you need cited conclusions. Interpretive text carries its interpretation label with it, so nothing labeled as reading is mistaken for record fact. The AI drafts; your team decides what gets filed.

No. The mode changes how much the AI may infer, never whether it cites. In all three modes every factual statement traces to a page and source, and statements that cannot be sourced are flagged rather than written as fact.

Yes. The mode is set per query, so you can ask the same question of the same file in all three modes and compare the answers. You can also set a default per matter or per team to keep output consistent.

The mode acts as an explicit ceiling on inference. Reviewers always see which mode produced an answer, every line carries its citation, and flagged lines show exactly where the record ran out — a reasoning trail you can defend under scrutiny.

Related capabilities.

Same engine, same citation standard — other ways the platform reasons over the same cited record.

Pick a mode. Every answer still shows its sources.

Upload one file and ask it the same question in all three modes — the cited sample comes back the same day. Handled under our BAA; never used to train a model.