Transparency

No black box. Here's exactly how it works.

Bernard makes a strong claim: every sentence in every draft traces back to something you said. This page documents the four mechanisms that make that claim checkable — not a marketing promise, an architectural guarantee.

Mechanism 01

Provenance trace. Every line, one source.

Before any draft is generated, the transcript is segmented into spans — each span is a discrete statement, belief, or anecdote from the interview. The LLM receives the spans as the source material for drafting. Each sentence in the output carries a span reference.

In the review queue, you can switch to attributed view. Every sentence in the draft shows the transcript span it was drawn from. If a sentence doesn't trace to a span — meaning the model invented it — it is flagged for your review before it can be published.

This is structural, not aspirational. The pipeline is built so the model cannot return a claim without a source reference. Hallucination isn't suppressed by a prompt; it's blocked by the schema.

  • Transcript is segmented into named spans before drafting begins
  • Drafting prompt references spans by ID — output must cite sources
  • Review queue attributed view maps each sentence back to your words
  • Unsourced claims are flagged, not silently published

Draft sentence

"The diaphragm doesn't just move air — it stabilizes your spine from the inside."

↓ attributed to

Transcript span · 02:14

"…because the diaphragm, when it fires correctly, is actually the primary stabilizer of the lumbar spine. It's not the core. The diaphragm is the core."

Mechanism 02

Atoms. Your ideas, accumulated.

Each interview is parsed into atoms — discrete units of knowledge extracted from your transcript. Atoms accumulate across months into a workspace knowledge graph.

An atom is one of: a belief (a claim about how the world works), a case (a patient or client story), a condition (a diagnostic or context), an archetype (a type of person you work with), or an objection (a common resistance you address). Each atom links back to the interview span it came from.

When a future interview surfaces a related belief or case, the atom graph recognizes the connection. Drafts can draw on prior thinking — the blog post from March can reference the case story from January, correctly attributed to both original interviews.

  • Five atom types: beliefs, cases, conditions, archetypes, objections
  • Each atom links to the transcript span it was extracted from
  • Atoms accumulate across all interviews in a workspace
  • Future drafts draw on the full graph, not just the current session
belief Pain is a movement problem, not a tissue problem
case Two-year bursitis diagnosis resolved in one screen
condition Dysfunctional breathing pattern, diaphragm offline
archetype The runner who stopped running
objection "My MRI shows a disc bulge — isn't that the cause?"
belief Imaging and symptoms almost never match in adults over 30

Mechanism 03

Voice phrases. Per clinician, not per workspace.

Voice is per person, not per practice. Bernard maintains a phrase library and voice notes for each clinician — distinct from the workspace-level settings — so multi-clinician practices produce content that sounds like the right human, not a blend.

A voice phrase is a word or expression the clinician uses frequently and distinctively — "load it up," "the body knows," "downstream symptom." Phrases are extracted from transcripts over time and built into the drafting brief as preferred vocabulary. Competing phrases that are generically AI-sounding get suppressed.

Voice freshness tracks how recently each phrase appeared in a transcript. Phrases that haven't surfaced in recent interviews are flagged as stale — they stay in the library but lose drafting priority until you use them again.

  • Phrase library maintained per clinician, not per workspace
  • Phrases extracted from transcripts and added on accept
  • Voice freshness score drops when a phrase goes unused
  • Generic AI phrases actively suppressed in the drafting brief
load it up fresh downstream symptom fresh the body knows fresh
address the root cause ok movement is medicine ok
holistic approach stale journey to wellness suppressed

Mechanism 04

The loop. Gets quieter every month.

Every action in the review queue feeds back into the system. Accept, edit, or reject a draft — Bernard records the outcome and adjusts the next month's briefs accordingly.

Interview → transcript → spans

You record a 15-minute prompted interview. The audio is transcribed and segmented into labeled spans. Each span is a discrete, citable unit of content.

Spans → atoms → drafts

New atoms are extracted and added to the workspace graph. The drafting brief is built from: relevant atoms, your active voice phrases, channel-specific format rules, and the current transcript spans. The model drafts. Every claim cites a span.

Review queue → voice tuning

You accept, edit, or reject drafts in the review queue. Accepted phrases are promoted in your phrase library. Rejected phrasing is demoted. Edits are analyzed for new phrase candidates. Month over month, the drafts need less correction.

Publish → next interview

Approved content publishes to Buffer, WordPress, Astro, or clean export. The cycle resets for the next interview — now with a richer atom graph, fresher phrase library, and tighter voice model than the month before.

An honest note

What this doesn't guarantee.

Provenance trace means every drafted claim links to something you said. It doesn't mean every claim is factually correct — if you say something inaccurate in the interview, the draft will faithfully reflect the inaccuracy. The system amplifies your voice, including the wrong notes. The review queue is the final check, and it's yours to make.

Bernard also doesn't guarantee the atoms graph is exhaustive. Atom extraction is LLM-assisted — it catches most of what's worth catching but isn't a verbatim record of your thinking. Think of it as a working index, not an archive.

Architecture questions? Ask Dr. Q directly.

Founding owners get direct access to the person who designed this. If something here raises a question, it's a good sign you're the kind of owner we want to work with.

"The trust problem in AI content isn't solvable with better prompts. It's solvable by making the source of every claim visible and checkable. That's what provenance trace is."

— Dr. Q, founder