# Episteme Use Cases

Real-world scenarios that demonstrate why Episteme exists and what it enables that traditional databases cannot.

## The Postgres Test

Every use case must answer: **"Could I build this with Postgres + a clever schema?"**

If yes → It's not a compelling use case.
If no → Identify which Episteme pillar makes it impossible.

## The Four Pillars

| Pillar | What It Enables | Postgres Gap |
|--------|-----------------|--------------|
| **First-Class Contradiction** | DB holds conflicting facts without forcing resolution | Must pick one value or version-table chaos |
| **Invalidation Cascades** | Retracted evidence flags all downstream decisions | Recursive CTEs don't scale, app logic drifts |
| **Multi-Signature Consensus** | Weighted trust via cryptographic co-signatures | Join tables have no cryptographic proof |
| **Semantic Decay** | Old data fades from hot path but remains auditable | Manual WHERE clauses, inconsistent decay rates |

## Use Case Tiers

### Tier 1: Production-Ready

| Use Case | Pillars | Status |
|----------|---------|--------|
| [Financial Due Diligence](./financial-due-diligence.md) | All Four | Draft |
| [Agile AI Agent Team](./agile-agent-team.md) | All Four | Draft |
| Life Sciences Evidence Chains | All Four | Planned |

### Tier 2: Hello World

| Use Case | Pillars | Status |
|----------|---------|--------|
| Competing News Sources | Contradiction, Decay | Planned |

### Tier 3: Dropped (Failed Postgres Test)

| Use Case | Why Dropped |
|----------|-------------|
| ~~Coding Agent Branch Simulation~~ | Git + CI already does this. Not a database problem. |

## Contributing Use Cases

When adding a use case:

1. Apply the Postgres Test rigorously
2. Lead with the catastrophe (what goes wrong without Episteme)
3. Show failing SQL for each feature
4. Map to specific pillars
5. Include a 5-minute local demo variant
6. Be honest about what Postgres CAN do

Template: See [financial-due-diligence.md](./financial-due-diligence.md) for structure.