A four-layer epistemic contract powered by 9 deterministic rules and two Claude models.
Stratensight is built on a deterministic, explicable, reproducible principle: every interpretive output the platform shows is the result of a layered audit, not a free-form LLM completion. This page documents the four layers that enforce that principle — the same layers that run on every analysis on every plan, with no gating.
Acronyms (C4, C5, GROUND-2, GROUND-5, GROUND-6, Option B) are kept as internal references for engineers reading the codebase; each is paired with a human-readable label on first occurrence and consolidated in the glossary at the end.
Each layer addresses a distinct failure mode of LLM-generated narrative. The layers stack: an output that passes Layer 1 still has to pass Layers 2, 3, and 4 before it reaches the user. None is optional.
WHAT IT DOES
Nine deterministic checks (CE1, CE2, CE3, CE4, CE5, S1, M_CAGR_LAST_YEAR_ARTIFACT, L_ACADEMIC_DOMINANCE, D_ABSTRACT_FILL_CRITICAL) audit every analysis BEFORE any narrative is generated. A second pass by a Claude Sonnet 4.6 LLM auditor surfaces contextual issues the rules cannot express. Critical issues can downgrade or block a verdict.
WHY IT MATTERS
No silent contradictions between scores and verdict. The audit runs on every analysis, every plan, with no gating — because scientific credibility cannot be fragmented.
SOURCE — backend/app/services/critical_reader.py:7-8
WHAT IT DOES
C4 Evidence-Certainty Directive (pre-generation): every LLM system prompt receives a language register conditioned on evidence_certainty — VERY_LOW, LOW, MODERATE, HIGH. When certainty is LOW or VERY_LOW, the LLM MUST use hedging vocabulary and MUST NOT use absolute language. C5 Hedge Validator (post-generation): scans the LLM output. If validation fails, retry once at temperature 0.0; on second failure, deterministic pre-validated hedged template fallback.
WHY IT MATTERS
Without this layer, an Executive Summary can read affirmatively ("the evidence demonstrates...") even when the badge shows Conditional / Low certainty. C4+C5 closes the asymmetry.
SOURCE — backend/app/services/_llm_hedging.py + _hedge_validator.py
WHAT IT DOES
Per-analysis whitelist of grounded facts (entities, numbers, years, geographies) passed via GroundingContext. After LLM generation, validate_grounding rejects any output that introduces a fact absent from the whitelist. Wrapper enforce_grounding_with_retry retries at temperature 0.0 then falls back to a deterministic template. Accent-insensitive matching (NFKD), word- boundary regex.
WHY IT MATTERS
An LLM that invents an assignee name, a CPC code, or a citation count silently undermines every downstream interpretation. GROUND-2 cuts hallucination at validation, not at trust.
SOURCE — backend/app/services/_grounding_validator.py
WHAT IT DOES
Explicit REFUSAL RULE injected into LLM system prompts so the model refuses with a calibrated phrase rather than inventing facts when the dataset variables do not support an answer. Three levels: soft (used by personas, narrative_engine), strict (used by chat advisor — anti false-positive FR phrasing), and narrative-specific (used by 11 narrative_sections functions and persona_engine). When detected, both validators bypass normal scrubbing.
WHY IT MATTERS
Hallucination prevention is not enough — the LLM must have a graceful exit when the data does not support the question. GROUND-5 makes refusal a first-class output, not a failure.
SOURCE — backend/app/services/_llm_refusal.py
BRIDGE TO LAYER C
Beyond labeling and hedging, evidence_certainty drives the Layer C Tier gate (Phase 5.3): the verdict surface adapts categorically to the certainty level. HIGH preserves the raw verdict (TIER_HIGH); MODERATE or LOW maps to a directional signal (TIER_MODERATE — INVEST → OPPORTUNITY_SIGNAL, MONITOR → MIXED_SIGNAL, EXPLORE → WEAK_SIGNAL, AVOID → NEGATIVE_SIGNAL); VERY_LOW withholds the verdict entirely and replaces it with INSUFFICIENT_DATA (TIER_LOW). See the methodology page Layer C section for the complete mapping.
Inside the LLM prompt, every fact is tagged with its provenance. The model cannot accidentally treat a derived metric as a primary observation, nor invent a fact under the cover of a grounded one.
Fact present in the analysis dataset whitelist (entity, number, year, geography). Safe to assert affirmatively under certainty rules.
Fact computed from grounded facts via deterministic transformation (e.g. CAGR from yearly counts). Must inherit the grounding of its inputs.
Fact NOT in the whitelist and NOT derivable. The LLM must either refuse (GROUND-5) or hedge as preliminary signal (C4) — never assert as evidence.
SOURCE — backend/app/services/prompt_builder.py (SOURCE_TAG_GROUNDED / _DERIVED / _ABSENT)
The four layers above keep individual LLM outputs grounded. Option B extends the same epistemic discipline to the deterministic templates surrounding them — decision narrative, key insight, and executive outlook — so the user reads a coherent register from badge to recommendation.
text.ts reflects the same certainty register across the explorer and analysis pages.SOURCE — backend/app/services/_ux_calibration.py + decision_engine.py
Stratensight uses two Claude models, each with a tightly scoped role. AI generates text only — never scores, never numbers. Scoring is deterministic Python, always.
ROLE
Auditor (Signal Integrity™ Layer 2)
SCOPE
Reads the full analysis context (scores, metadata, source mode) and may surface up to 8 additional issues that the deterministic rules cannot express. Hard guardrails: allowed_values whitelist, ±0.5 float tolerance, 15-second timeout, 2048 max output tokens. Never invents a fact, never re-scores — flags only.
ROLE
Narrative generation (personas, executive summaries, clusters, Q&A, narrative_sections)
SCOPE
Generates role-aware narrative TEXT only — never scores, never numbers. Always paired with C4 directive (pre-gen), C5 + GROUND-2 + GROUND-5 (post-gen). Always labeled "AI-generated insight" in UI. Silent fallback to deterministic templates when the API returns null or fails validation.
Internal acronyms used by Stratensight engineers, paired with their public labels and short definitions.
HUMAN LABEL
Evidence-Certainty Directive (pre-generation)
WHAT
Block injected into LLM system prompts to constrain language register based on certainty level.
HUMAN LABEL
Hedge Validator (post-generation)
WHAT
Scans LLM output for hedging vocabulary and absolute language. Pairs with C4.
HUMAN LABEL
Grounding Validator
WHAT
Anti-hallucination whitelist enforcement after LLM generation.
HUMAN LABEL
Refusal Rule
WHAT
Three-level abstention protocol (soft / strict / narrative-specific) injected into LLM prompts.
HUMAN LABEL
Source Tagging
WHAT
Provenance flagging — every LLM-readable fact is tagged grounded / derived / absent.
HUMAN LABEL
UX Calibration
WHAT
Deterministic templates conditioned on certainty × language across decision narrative, key insight, and executive outlook.
HUMAN LABEL
Public-facing: "Confidence level"
WHAT
Backend variable VERY_LOW / LOW / MODERATE / HIGH, source for badge color and language register.
HUMAN LABEL
Public-facing reliability metric
WHAT
Backend: branded_scores.intelligence_grade. Drives downgrade rules and disclaimer thresholds.
Eighteen user-facing tokens that appear across decision narratives, persona insights, and score badges. Section 9 above lists internal acronyms for engineers; this section is for everyone reading a Stratensight report. For threshold values and lifecycle weights, see /methodology.
Decision Engine verdict — strong convergent opportunity
Decision Engine verdict — promising but incomplete
Decision Engine verdict — mixed signals, deeper analysis required
Decision Engine verdict — weak or negative signals
Lifecycle phase — early academic exploration
Lifecycle phase — first commercial interest
Lifecycle phase — rapid growth, opportunity window
Lifecycle phase — established technology
Lifecycle phase — saturated, incumbent-dominated
Persona role — strategic capital allocator
Persona role — research / engineering decision-maker
Persona role — IP legal practitioner
Persona role — corporate strategy lead
Persona role — market intelligence analyst
Persona role — C-level decision-maker
Score tier — filing velocity intensity
Openness tier — competitive structure label
Public confidence band — drives badge color and LLM hedging register
Tier gate (Phase 5.3) — subordinates the user-facing verdict to evidence_certainty via categorical mapping
Directional label for INVEST under TIER_MODERATE (MODERATE or LOW certainty)
Directional label for MONITOR under TIER_MODERATE (MODERATE or LOW certainty)
Directional label for EXPLORE under TIER_MODERATE (MODERATE or LOW certainty)
Directional label for AVOID under TIER_MODERATE (MODERATE or LOW certainty)
Verdict withheld under TIER_LOW (VERY_LOW certainty) — no signal can be defended
Stratensight provides patent intelligence signals, not legal opinions or freedom-to-operate assessments. Not a substitute for IP counsel.