Why generic AI wrappers fail at due diligence
Using a general-purpose AI chatbot to scan a 300-page merger agreement presents three immediate liability risks for a deal team:
- Hallucination: Chat models will invent clauses that sound plausible when asked leading questions.
- Instability: Asking the exact same prompt twice can yield different severities or entirely different findings.
- Boilerplate blindness: Generic AI struggles to separate a standard "no-shop" provision from an actual transaction risk.
Anweshna solves this by treating the LLM strictly as a text-extraction module within a larger, deterministic software pipeline.
The 7-Layer Architecture
1. Multi-Industry Ruleset Architecture
Before scanning begins, documents are routed through industry-specific taxonomies. A pharmaceutical IP agreement is evaluated under vastly different materiality thresholds than a commercial real estate lease. Our taxonomy governs what the AI is allowed to look for.
2. Dual Scoring Engines
Documents pass through either our Precision Scan (for targeted agreements) or our Map-Reduce Deep Scan (for massive, 500+ page data room dumps). The Deep Scan chunks, analyzes, and synthesizes findings across a document hierarchy while preserving global context.
3. Missing-Information Detection
A risk doesn't just exist in what is written; it exists in what is omitted. Our scoring_policy engine maintains baselines of required disclosures per industry and deterministically flags when critical schedules, appendices, or financial clauses are missing from the data room.
4. Negation-Aware Risk Detection
Contracts frequently list risks they have explicitly mitigated. Our two-tier negation detection engine ensures that "Company is NOT subject to any litigation" does not trigger a false-positive litigation flag.
5. Evidence Verification (Citation Integrity)
Every finding surfaced by the AI must carry a quoted span from the source document. Our proprietary evidence_verifier engine strips away the LLM's response and deterministically searches the original extracted PDF/Word text. If the exact quote or figure cannot be located, the finding is tagged [UNVERIFIED].
6. Second-Stage Materiality Verifier
Our deterministic secondary pipeline reads the AI's findings and classifies them by evidence type, severity, and disposition. It separates standard merger boilerplate from live regulatory actions, ensuring a "stockholder approval" clause is never flagged as a material risk.
7. Risk Taxonomy & Blocking Gates
The final layer computes the composite deal score. We enforce "critical-phrase floors" (e.g., "going concern") that unconditionally override the AI's subjective score and force the category into a "Blocked" state, stopping the deal until a human reviewer intervenes.
The Value Moat
By shifting the burden of severity assessment, hallucination checking, and category gating out of the AI and into deterministic code, Anweshna achieves an 84.6% precision rate on deal-blocking flags. Read the full AI Accuracy & Benchmark Report to see our pipeline's performance on public M&A filings.