Ingest
File ParserUnstructured data (PDF, PPTX, DOCX) is parsed into structured text blocks.
Architecture Comparison
// 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 excel at formatting pitch decks and summarizing data rooms. 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. Prov. Patent 63/948,559
Extraction is LLM. Evaluation is Go. Separation is the audit trail.
Unstructured data (PDF, PPTX, DOCX) is parsed into structured text blocks.
We utilize Tier-3 LLMs strictly for extraction, isolating typed claims (TAM, Unit Economics, Headcount) without allowing the model to evaluate them.
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 (e.g., unit economics that mathematically cannot scale) are flagged.
The engine outputs a 40-dimensional verdict, culminating in the Clarity Score™ (0–100).
Competitive Physics
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.
RUNE isn't the model.
It's the compiler.