The Knowledge-Driven Workflow

From conversation to computation in four steps.
How domain expertise enters the analytical engine.

Data tells you what is happening.
People tell you why.

Signals detect anomalies. Theses frame questions. Verdicts propose root causes.
But the insight that “if a material has purchases, the flag is wrong, not the date”
— that comes from a person, not a query.

Four steps, one cycle

1. Capture
Subject Matter YAML
→
2. Analyze
consequences
→
3. Implement
instruments
→
4. Rebuild
& review

Each cycle adds knowledge to the system. Subject Matter is the handshake format
between human expertise and the analytical engine.

Capture

Domain knowledge enters the system as a Subject Matter entry —
attributed, scoped, and tri-lingual.

Who tells us why?

👩‍⚗️
Material Managers
Business rules, catalog decisions, classification logic
🩺
Clinical Staff
Process workarounds, tracking gaps, manual steps
💻
IT Leads
System behaviors, interface quirks, midnight splits
💰
Billing Specialists
Pricing logic, reimbursement rules, invoice patterns

Structured knowledge, not free text

smebit_id: smebit_zeta_validity_activity_classification provider: name: Ronnie role: Material Management date: 2026-03-03 category: business_rule content: en: | When is_active contradicts validity dates, purchasing activity tells us which field is wrong. why: en: | The flag and dates are maintained by different processes. Activity is the ground truth for which reflects reality. anchors: - signal_id: signal_active_date_expired - signal_id: signal_inactive_date_valid

Consequence Analysis

The critical step. Once knowledge is captured,
we ask: what does this change?

Five questions for every Subject Matter entry

Question Outcome
Does this sharpen an existing signal? Add enrichment joins, new evidence fields
Does this warrant a new signal? Write new YAML or hand-written SQL
Does this confirm or refine a thesis? Update evidence chain, adjust thresholds
Does this explain a confirmed thesis? Create or refine a verdict
Does this belong with other entries? Create or extend a Dossier

Ronnie’s activity classification rule

“When is_active contradicts the validity dates,
check if the material has purchases.”

Signal Has Purchases Likely Wrong Field
Active + date expired Yes Date — article genuinely in use
Active + date expired No Flag — article genuinely expired
Inactive + date valid Yes Flag — article genuinely in use
Inactive + date valid No Date — article genuinely inactive

One insight, three changes

Before

  • entity_filter — Material-only, no fact joins
  • Severity: all medium
  • Evidence: material fields only
  • No indication of which field is wrong

After

  • hand_written — joins billing + usage
  • Severity: high when real spend > CHF 1K
  • Evidence: + has_purchases, likely_wrong_field
  • Sub-classification per Ronnie’s rule

Implement

Edit or create instruments. Validate. Compile.
The engine turns YAML into SQL.

From YAML to findings

Subject Matter YAML + Signal YAML/SQL
human-authored artifacts
↓
smebitcheck + probecheck
validate against contracts
↓
proberegistry + probecompile + smebitcompile
generate dbt SQL
↓
rebuild.sh --skip-gen
5 tenants, 175 tests each, ~3 minutes

Rebuild & Review

Run the numbers. Does reality match
the expert’s expectation?

Enrichment, not filtering

1,368
active + date expired
findings (unchanged)
1,413
inactive + date valid
findings (unchanged)
81
escalated to high
real spend > CHF 1K

Same population, richer evidence. Every finding now says
which field is wrong and how much money is involved.

hospital_zeta: activity tells the story

Signal Likely Wrong Has Purchases Findings CHF at Risk
Active + expired date yes 610 18,984
Active + expired flag no 758 92,706
Inactive + valid date no 1,197 109,345
Inactive + valid flag yes 216 14,860

826 materials with purchases — activity confirms they’re real.
1,955 without — catalog entries that could safely be cleaned up.

Knowledge Accumulates

Individual entries are atoms.
Dossiers are the stories they tell together.

From atoms to narrative

Subject Matter Sentinel date convention (9999-12-31)
Subject Matter Activity-based validity classification
Subject Matter Material 638876A wrong description
↓
Dossier: Catalog Data Quality at Hospital Zeta

Three separate conversations, three separate experts, one coherent story:
“The material master data at Hospital Zeta has systemic quality issues.”

Why this workflow works

Principle How It Manifests
P10 Human-in-the-loop The SME is the source, not the system
P11 AI as SME AI formalizes, connects, compiles — doesn’t invent knowledge
P12 AI as colleague Consequence analysis is a conversation, not an instruction
P13 No AI in data path Subject Matter content is human-authored; checks are SQL, not LLM
P16 Pragmatic generalization Wait for the second signal before abstracting a new DSL type

The difference between data and knowledge
is the why.

Capture → Analyze → Implement → Review

Every cycle makes the engine smarter —
not by adding AI, but by adding human insight.