Every fact scored 0–1 for certainty. Contradictions detected automatically.
Full provenance to the source paragraph. Human-in-the-loop curation built in.
Try building that in a weekend.
You built retrieval. But retrieval is not knowledge.
A POT is not a vector store. It's a cognitive environment where raw documents transform into validated, interconnected knowledge with explicit certainty scores.
Every fact gets a POT Score. Every relationship is typed and weighted. Contradictions are detected and surfaced. Human curators govern the constitution while automated agents handle extraction at scale.
Upload a document. SciPot handles the rest.
Not just retrieval. A full knowledge lifecycle with certainty, curation, and conflict resolution.
LLM-powered extraction turns documents into atomic, scored knowledge units with full provenance and quality audit.
Every fact carries an explicit certainty score from 0.0 to 1.0. Filter queries by confidence. No more guesswork.
Conflicting facts are automatically detected via similarity-based analysis and constitution edge detection.
LLM-based relationship detection: supports, contradicts, derives_from, refines, is_part_of, and more.
Automated agents extract and score at scale. Human curators govern the constitution and resolve conflicts.
Every fact is auditable: the full chain of who curated it, who resolved conflicts, and exactly which document and fragment it was extracted from.
When evidence supports or contradicts a fact, certainty scores propagate automatically through the knowledge graph following logical rules.
Answers come with certainty levels, source attribution, and explicit warnings about contradictions or low-confidence facts.
The POT Score makes knowledge quality visible and actionable. Query for facts you can stake decisions on, or explore hypotheses with lower-confidence knowledge.
Scores propagate through the knowledge graph: supporting evidence boosts confidence, derivations inherit from premises with decay, and contradictions are flagged for human review.
| 1.0 | Constitution | Foundational axioms, set by human curators only |
| 0.85 | Verified | Multiple sources or explicit human validation |
| 0.50 | Extracted | Extracted with reasonable confidence from sources |
| 0.30 | Inferred | System-inferred from combining other facts |
| 0.00 | Pending | Awaiting verification or insufficient evidence |
import httpx
response = httpx.post(
"https://api.scipot.ai/pots/{pot_id}/synthesize",
headers={"Authorization": "Bearer ik_live_..."},
json={
"query": "What are the key risk factors?",
"max_facts": 10
}
)
result = response.json()
print(result["answer"]) # Synthesized response
print(result["facts_used"]) # Facts with pot_score & provenance
print(result["contradictions_found"]) # Detected conflicts
print(result["epistemic_briefing"]) # Certainty guidance
print(result["strategy_used"]) # "cag", "rag", etc.Adam Smith showed that dividing labor creates economic prosperity. SciPot applies this to cognition: instead of one generalist AI trying to know everything, create specialized knowledge spaces where expertise accumulates, certainty is measured, and intelligence compounds over time.
Knowledge Pots are the workshops of the cognitive era. Each POT develops depth in its domain. Agents inhabit them with context and memory. Organizations build durable intelligence instead of starting from zero every interaction.
SciPot turns any domain into a knowledge-rich environment. Here are some of the highest-value applications developers are building today.
Ingest financial statements, contracts, and regulatory filings into a POT. Detect contradictions across documents and synthesize risk assessments with calibrated certainty scores.
Finance & M&AMaintain a living POT of regulations—FDA, GDPR, SOX—that detects when new rules conflict with existing practices and synthesizes compliance impact for specific products.
Compliance & LegalOne POT per project: architecture decisions, postmortems, runbooks. Certainty scores distinguish firm decisions from casual suggestions. Knowledge compounds with every interaction.
Developer ToolsIngest papers, clinical trials, and datasets. Score propagation through the knowledge graph reflects how real scientific evidence works—not all findings carry equal weight.
Pharma & BiotechUse a POT as the operational brain for agent swarms. Agents log decisions and outcomes; scores distinguish validated patterns from hypotheses. Dual curation lets humans correct what agents learn.
Agent InfrastructureUse a POT as canonical ground truth to evaluate agent outputs in production. Detect when an agent contradicts validated facts, overclaims confidence, or introduces unverified knowledge—turning contradiction detection into a runtime guardrail.
AI ObservabilityMonthly fee with included tokens. No surprises. Scale as you grow.
Tokens cover all operations: ingestion, fact extraction, edge detection, queries, and synthesis.
Service never cuts off abruptly — soft warnings and gradual throttling on overage.
KB2B is a full-stack knowledge management application built entirely on SciPot's API. Persistent conversations, validated knowledge, domain-specific expertise — a working proof of what you can build.
Visit kb2b.app →Choose your entry point.
Questions? hello@scipot.ai