We Don't Just
Prompt & Pray.
PrediktFi uses a Neuro-Symbolic Architecture. We combine the reasoning power ofGPT-5.2with 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.
> Analyzing market saturation for 'Cat Memes'...
> Integrating Solana liquidity data...
> DETECTED: Team is anon but claims "ex-Faang"...
> VERDICT: Discounting execution score by 15% due to unverifiable claim.
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, BTC dominance, 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 DeFi Protocol, algorithm caps your Execution Score at 60/100.
maxScore = 60;
flags.push("Cap: Solo Founder Risk");
}
The Narrative Tax
If your memecoin description uses generic keywords like "moon", "pepe killer", or "community takeover" without unique art/vibes, we deduct -20 points instantly.
score -= 20;
flags.push("Penalty: Generic Narrative");
}
On-Chain Truth
Verification Layer (RPC)
Mint Authority
We query the Solana blockchain directly. If mintAuthority is not null for a traded token, we flag it as High Rug Risk.
Freeze Authority
Can the dev freeze your wallet? We check the account extensions on-chain. Ideal state: Revoked.
LP Lock Status
NOTE: Currently relying on self-reported addresses cross-referenced with Raydium/Pump.fun API patterns.