c59066949a
- Add Layered() method to Go SDK for per-source-class consensus queries - Add LayeredQueryParams, LayeredResult, TierResolution types to Go SDK - Create conflict example demonstrating Skeptic and Layered endpoints - Update quickstart.md with sections 6 (conflict detection) and 7 (authority tiers) - Remove tracked Go binary and add data/ to .gitignore The new quickstart sections demonstrate Episteme's differentiating features: - Skeptic endpoint shows "Trust but Verify" conflict analysis - Layered endpoint shows per-tier resolution (Clinical vs Anecdotal) Note: Pre-existing large files flagged by pre-commit hook (technical debt from prior sessions) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> |
||
|---|---|---|
| .. | ||
| agile-agent-team.md | ||
| consumer-health-intelligence.md | ||
| financial-due-diligence.md | ||
| glp1-living-review.md | ||
| README.md | ||
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 |
|---|---|---|
| Consumer Health Intelligence | All Four | Draft |
| Financial Due Diligence | All Four | Draft |
| Agile AI Agent Team | 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 |
|---|---|
| Git + CI already does this. Not a database problem. |
Contributing Use Cases
When adding a use case:
- Apply the Postgres Test rigorously
- Lead with the catastrophe (what goes wrong without Episteme)
- Show failing SQL for each feature
- Map to specific pillars
- Include a 5-minute local demo variant
- Be honest about what Postgres CAN do
Template: See financial-due-diligence.md for structure.