What Is at Stake
In healthcare, the cost of a hidden assumption is a missed diagnosis. A drug interaction no one tracked. A treatment plan built on evidence that was superseded by a newer study. A clinical trial where contradictory findings were buried across different reports.
Medical reasoning is fundamentally epistemic. It is about what a clinician believes to be true about a patient, how confident they are, and what evidence supports or contradicts that belief. When this reasoning is implicit, critical information falls through the gaps.
What Beliefs Make Visible
Differential diagnosis as belief state
A diagnostic agent does not produce a single answer. It maintains a set of competing hypotheses, each with confidence, supporting evidence, and contradicting observations. As test results arrive, some hypotheses strengthen and others weaken.
1┌──────────────────────────────────────────────────────────────┐
2│ DIFFERENTIAL DIAGNOSIS │
3│ │
4│ ● Hypothesis A: Type 2 diabetes 72% │ 4 supporting │
5│ ├─ Elevated HbA1c (measurement) │ 1 contradicting │
6│ ├─ Family history (user-assertion) │ │
7│ ├─ BMI > 30 (measurement) │ │
8│ └─ Normal fasting glucose (contradicts)│ │
9│ │
10│ ● Hypothesis B: Pre-diabetes 61% │ 3 supporting │
11│ ├─ Borderline HbA1c │ │
12│ ├─ Normal fasting glucose (supports) │ │
13│ └─ Age and risk factors │ │
14│ │
15│ ● Hypothesis C: Stress response 28% │ 1 supporting │
16│ └─ Recent life event │ 2 contradicting │
17│ │
18│ Gap: "Oral glucose tolerance test not performed" │
19│ This gap would resolve the A vs B distinction. │
20└──────────────────────────────────────────────────────────────┘Without beliefs, the agent picks the most likely diagnosis and argues for it. With beliefs, every competing hypothesis is tracked, every piece of evidence is linked, and the most informative next test is surfaced, because the system knows what gap would reduce the most uncertainty.
Drug interaction monitoring
A patient takes five medications. A new study suggests an interaction between two of them. An agent with beliefs can cross-reference the patient's medication list against an evolving evidence base, where each interaction claim carries a confidence score, evidence chain, and timestamp. A three-year-old interaction warning superseded by newer research carries less weight through temporal decay.
Clinical trial reconciliation
Multiple trials studying the same intervention can produce conflicting results. Belief state infrastructure lets an agent maintain structured beliefs across trials, tracking where results corroborate, where they conflict, and what methodological differences explain the divergence. The system can surface: "Trial A (n=500) and Trial B (n=2000) disagree on efficacy. Trial B has higher evidence weight due to sample size and methodology."
What Agents Can See That We Cannot
A physician holds a mental model of perhaps 20-30 patients in depth. A belief-aware clinical agent can maintain structured beliefs across an entire patient population, tracking how evidence evolves for each patient, detecting patterns across cohorts that no individual clinician could observe.
When beliefs are explicit, the agent can detect that a subtle lab value pattern across 200 patients correlates with an outcome that would be invisible in any single chart review. The agent maintains structured beliefs across more data than any human can hold, with uncertainty tracked at every step.
The is/ought firewall in clinical context
The is/ought boundary is especially critical in healthcare. A patient saying "I want to avoid surgery" is a preference. It should not increase the agent's confidence that surgery is unnecessary. A diagnostic finding is evidence. It should update the clinical picture. The SDK enforces this distinction automatically.
1const beliefs = new Beliefs({
2 apiKey: process.env.BELIEFS_KEY,
3 agent: 'clinical-agent',
4 namespace: 'patient-123',
5 writeScope: 'space',
6})
7
8await beliefs.add('HbA1c is 6.8%', {
9 confidence: 0.95,
10 evidence: 'Lab panel 2024-03-15',
11})
12
13await beliefs.add('Fasting glucose is normal', {
14 confidence: 0.92,
15 evidence: 'Lab panel 2024-03-15',
16})