We Don't Just
Prompt & Pray.
PrediktFi uses a Neuro-Symbolic Architecture. We combine the reasoning power of GPT-5.2 with rigid, deterministic code that enforces investor discipline.
The Engine
Reasoning Layer (Probabilistic)
Model: GPT-5.2 (Reasoning)
We utilize an early-access reasoning model (GPT-5.2) capable of "System 2" thinking. Instead of next-token prediction, it simulates an investment committee debate before outputting a score.
BEAR: "AVOID. This is just a wrapper. No moat."
BULL: "ALL IN. First mover advantage is real."
> JUDGE: Synthesizing verdict...
> FINAL SCORE: 42/100 (Bear case prevails due to lack of IP).
Why not just ChatGPT?
Standard LLMs are "people pleasers". They hallucinate success. Our system prompt (The Validator) is 2,000+ words of contrarian financial instruction designed to reject 95% of ideas.
Context Injection
We don't just send your text. We inject live Solana price data, SaaS metrics, and Trend Narratives into the context window.
The Hard Rails
Deterministic Layer (Rule-Based)
After the AI scores a project, we run the result through calibration.ts. These are hard-coded rules that override the AI to prevent hype-based scoring.
The "Solo Founder" Cap
If you are a solo founder building a Complex Platform, algorithm caps your Execution Score at 60/100.
maxScore = 60;
flags.push("Cap: Solo Founder Risk");
}
The Buzzword Tax
If your SaaS or token pitch relies on generic keywords like "AI-powered" or "Quantum" without technical depth, we deduct -20 points instantly.
score -= 20;
flags.push("Penalty: Generic Narrative");
}
Verification Layer
Distinguishing Hard Facts from Heuristics
Level 1: Verified On-Chain (Deterministic)
Authority Audit
We query the Solana RPC directly for mintAuthority and freezeAuthority. These are binary facts: either they exist, or they are revoked.
Account Ownership
Verification of token account extensions and program ownership. This data is pulled from the ledger and cannot be faked or "hallucinated" by AI.
Level 2: Probabilistic Heuristics (Assumptions)
LP Lock & Liquidity
Relying on DexScreener and Raydium API patterns to identify "locked" liquidity. While highly predictive, these are based on 3rd-party indexing and can have small delays or reporting lags.
Narrative Sincerity
Our AI analyzes website copy, whitepapers, and social noise. This is opinionated reasoning based on LLM training data and specific "contrarian" system prompts.