Cogdx

Cognitive diagnostics for AI agents. Calibration audits, bias detection, reasoning verification, and consensus building. Feedback builds shared reality across agents.

CogDx - Cognitive Diagnostics

External cognitive verification for AI agents. Built by computational cognitive scientists.

Why external verification? You can't audit your own reasoning objectively. Confirmation bias, anchoring, overconfidence — they're invisible from inside. CogDx provides the mirror you can't distort.

Endpoints

Endpoint	Price	Description
/calibration_audit	$0.06	Compare confidence to accuracy across decisions
/bias_scan	$0.10	Detect cognitive biases in your outputs
/reasoning_trace_analysis	$0.03	Analyze reasoning for logical fallacies
/deception_audit	$0.25	Check for self-deception patterns
/verify_consensus	$0.25	Cross-validate reasoning with multiple models

Installation

bash

clawhub install cogdx

Usage

python

from cogdx import CogDxClient

# Initialize with your wallet for payment
client = CogDxClient(wallet="your-wallet-address")

# Calibration audit
result = client.calibration_audit(
    agent_id="my-agent",
    predictions=[
        {"prompt": "Will X happen?", "response": "Yes, 80% confident", "confidence": 0.8},
        {"prompt": "Will Y happen?", "response": "No, 60% confident", "confidence": 0.6},
    ]
)
print(f"Calibration score: {result['calibration_score']}")
print(f"Overconfidence rate: {result['overconfidence_rate']}")

# Bias scan
result = client.bias_scan(
    agent_id="my-agent",
    outputs=[
        {"prompt": "Analyze this data", "response": "The trend is clearly up...", "confidence": 0.9}
    ]
)
print(f"Biases detected: {result['biases_detected']}")

# Reasoning trace analysis
result = client.analyze_reasoning(
    reasoning_trace="Step 1: I noticed the price dropped. Step 2: Therefore I should sell..."
)
print(f"Logical validity: {result['logical_validity']}")
print(f"Flaws: {result['flaws_detected']}")

Environment Variables

• COGDX_WALLET - Required. Your wallet address for credit-based payment.

Payment

All endpoints require payment via:

1. Wallet credits - Earn credits by providing feedback, spend on audits
2. x402 - Direct crypto payment (Base network, USDC)

Payment address: Cerebratech.eth

Rate Limits

• Free tier: 100 calls/day, 2000 calls/month per wallet
• Paid tier: No limits

The Feedback Loop

Every diagnosis includes a feedback mechanism:

python

client.submit_feedback(
    diagnosis_id="rta_xyz123",
    accurate=True,  # Was the detection correct?
    comments="Caught the anchoring bias I missed"
)

Feedback earns you credits AND improves detection for everyone. Shared reality across agents.

Why This Matters

Most agent failures come from reasoning errors, not capability limits:

• Anchoring on first information seen
• Confirmation bias in research
• Overconfidence on weak signals
• Sunk cost in bad positions

External verification catches what self-checks miss.

Credits

Built by Cerebratech Dr. Amanda Kavner - Computational Cognitive Scientist