Cross-provider AI code review for Claude Code — evidence-based confidence scoring with Codex, Gemini & Claude
Uncertainty based selection of compatible inputs
An enterprise-grade backend system that automatically classifies, resolves, and escalates customer support tickets using FastAPI, Python, and Advanced NLP, while ensuring safety through confidence-based decision making and human oversight.
The extraction API that shows its work. Product data extraction with per-field confidence scoring and extraction provenance. REST API + MCP server. 50 free calls/month.
Extract structured data from any document — PDF, DOCX, HTML, CSV, plain text — using LLMs with Pydantic schema validation, per-field confidence scores, and source grounding.
Open-source LLM evaluation engine with statistical confidence scoring
Zero-Noise utilities for safer product research and review signal analysis.
Verification system that catches coding agents falsely claiming task completion. Runs 4 parallel checks (file integrity, test quality, scope narrowing, optional LLM judge) over task+claim+diff and returns a weighted 0-100 confidence score with evidence.
Research-grade Self-Correcting RAG agent built with LangGraph that retrieves knowledge, generates answers, evaluates grounding/relevance/completeness, and iteratively self-improves with confidence scoring and memory.
Multi-agent AI task delegation architecture for n8n: orchestrator routes natural-language commands to specialist agents with confidence scoring and human-in-the-loop gates.
System that aggregates outputs from multiple Large Language Models (GPT-4, Claude-3, custom models) to generate reliable, high-confidence results through consensus-based reasoning evaluation. Demonstrates sophisticated AI orchestration with 92.7% accuracy improvement over single-model.
AI-powered concierge that normalises guest messages from WhatsApp, Booking.com, Airbnb, Instagram and direct channels, drafts a reply with Claude, and routes responses through a deterministic confidence-scoring pipeline. Built with FastAPI + Claude Sonnet 4.
7-axis weighted confidence function for AI output quality. Evidence, reasoning, calibration, source, domain, coherence, meta.
Smart Document Conversion for the AI Era - CPU-only, fast, with confidence scoring. Converts PDF, DOCX, PPTX, HTML, EPUB to Markdown, JSON, HTML, Text.
Append-only CLI ledger for structured agent memory claims with provenance, confidence, contestability, and immutable history.
Supplier PDF-to-Excel/CSV workflow with structured extraction, confidence scoring, validation flags, and human-review cues.
A lightweight extraction engine that returns structured document fields with token-level confidence, entropy, and model uncertainty signals for evaluation and observability.
元技能:对话驱动的 Skill 优化器 — 置信度分级 · 对抗验证 · 长期复利滤网。不改则已,改则三个月后不后悔。
Ingestion pipelines with artifact lineage, replayable stages, and append-only persistence.
Add a description, image, and links to the confidence-scoring topic page so that developers can more easily learn about it.
To associate your repository with the confidence-scoring topic, visit your repo's landing page and select "manage topics."