aif-grounded

Classify user requests and enforce evidence-based confidence gates for verified answers.

83|5|Updated Oct 17, 2025

Search Tags:#reliability #uncertainty #confidence #evidence-based #ai-safety #grounded

Ready to run

npx skills add https://github.com/ArtemYurov/TomoBar --skill aif-grounded-artemyurov

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: aif-grounded
Source: https://github.com/ArtemYurov/TomoBar/tree/main/.claude/skills/aif-grounded
Command: npx skills add https://github.com/ArtemYurov/TomoBar --skill aif-grounded-artemyurov

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Reliability gate for answers. Forces evidence-based reasoning, explicit uncertainty, and “insufficient information” instead of guesses. Use when user says “be 100% sure”, “no hallucinations”, “only if verified”, “grounded answer”, or when stakes are high.

Core Features & Use Cases

Step 1: Classify the request
Step 2: Define evidence and unknowns
Step 3: Mandatory verification for changeable facts
Step 4: Confidence gate
Step 5: Output format
Use Case: Applicable to high-stakes domains (security, legal, medical, finance) where verified conclusions are critical and context may be incomplete.

Quick Start

Apply the gate to a high-stakes question by evaluating evidence, listing unknowns, verifying changeable facts, and returning a 100/100 answer or an INSUFFICIENT INFORMATION prompt.

Frequently Asked Questions about aif-grounded

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I prevent AI guessing and get evidence-based answers for high-stakes queries?▼

To prevent AI guessing and ensure evidence-based answers, a grounded reasoning workflow classifies requests, lists evidence and unknowns, verifies changeable facts, and applies a 0–100 confidence gate to output a 100/100 answer or an INSUFFICIENT INFORMATION response.

How does a confidence gate work for verified outputs in incomplete contexts?▼

A confidence gate works by enforcing a 0–100 scale evaluation for verified outputs. If evidence meets the 100/100 threshold, the system provides a grounded answer; otherwise, it explicitly returns an INSUFFICIENT INFORMATION response instead of guessing.

When do I need grounded reasoning for AI safety in medical, legal, or financial domains?▼

You need grounded reasoning for AI safety in medical, legal, or financial domains when stakes are high and context may be incomplete. It forces explicit uncertainty, mandatory fact verification, and evidence-based conclusions rather than hallucinated outputs.

Can I force an LLM to return insufficient information instead of hallucinating facts?▼

Yes, you can force an LLM to return insufficient information instead of hallucinating by applying a strict confidence gate. This workflow requires listing unknowns and verifying changeable facts, blocking any output that does not achieve 100/100 confidence.

What is the step-by-step process for producing evidence-based conclusions from AI?▼

The step-by-step process for evidence-based conclusions involves classifying the request, defining evidence and unknowns, performing mandatory verification for changeable facts, applying a confidence gate, and formatting the output as either a verified answer or an insufficient information prompt.

Are there limitations to using a strict 100/100 confidence gate for AI outputs?▼

A limitation of a strict 100/100 confidence gate for AI outputs is that it will frequently return an INSUFFICIENT INFORMATION response when context is incomplete, intentionally blocking answers in high-stakes domains where verified facts are unavailable.