askOdin — AI Judgment Infrastructure for Capital Allocation

Category Definition

Architecture: Deterministic Compiler vs. Probabilistic AI

// WHY JUDGMENT ≠ GENERATION

The greatest systemic risk in modern venture capital is conflating narrative generation with structural judgment.

Legacy AI tools (ChatGPT, Claude, and their respective wrappers) are probabilistic generation engines. They format pitch decks and summarize data rooms competently. LLMs optimize for persuasion — they applaud a well-written narrative, but they cannot evaluate mathematical business physics.

askOdin is a deterministic physics engine. We do not generate text; we compile logic.

The Doctrine

LLMs optimize for persuasion.
askOdin compiles for physics.

The askOdin Protocol Stack

U.S. PATENT PENDING 63/948,559

The RUNE Protocol™ Architecture

Extraction is LLM. Evaluation is Go. Separation is the audit trail.

01_ingest.go PARSE
01

Ingest

File Parser

Unstructured data (PDF, PPTX, DOCX) is parsed into structured text blocks.

02_extract.go LLM · ISOLATED
02

Extract

Probabilistic Isolation

We run Tier-3 LLMs strictly for extraction, isolating typed claims (TAM, Unit Economics, Headcount) without letting the model evaluate them. The probabilistic layer reads. It does not judge.

03_compile.go COMPILE
03

Compile

Deterministic Go Engine

The extracted claims are routed entirely outside the neural network. A statically-typed Go engine mathematically evaluates the variables against the askOdin Judgment Graph™. This is where terminal physics violations — unit economics that mathematically cannot scale — are flagged.

04_score.go VERDICT
04

Score

The Clarity Framework Aggregator

The engine outputs a verdict across 40+ forensic dimensions, culminating in the Clarity Score™ (0–100).

Competitive Physics

The LLM Commoditization Reality

When generic LLMs get faster and cheaper, the AI startups built as wrappers face an existential problem. For us, it just makes the extraction layer cheaper to run. Better LLMs are good for our margins, not bad for our moat.

Here is the difference. An LLM gives you inference. We give you a benchmark universe. The LLM can generate a verdict that sounds right; it cannot issue a score the same way twice, against the same standard, that an LP can audit two years from now. That is not a model problem. That is an architecture problem.

commoditization.diff DETERMINISTIC

- Probabilistic LLM: inference, non-reproducible verdict

+ askOdin: deterministic compile against 100,000+ benchmarked scores

// calibrated on public deal data

// same input → same Clarity Score, every time

+ auditable by an LP two years from now

RUNE isn't the model.
It's the compiler.