Kido Agentic Eval Harness — Deterministic Property Testing & Calibrated AI Judges
Enterprise-grade evaluation suite for LLM features, RAG pipelines, and autonomous agents. Combines programmatic assertion contracts, real-world failure taxonomy, calibrated multi-turn LLM judges with
Free
Works with the AI Agents you already use
About this skill
Kido Agentic Eval Harness — Deterministic Property Testing & Calibrated AI Judges
Enterprise-grade evaluation suite for LLM features, RAG pipelines, and autonomous agents. Combines programmatic assertion contracts, real-world failure taxonomy, calibrated multi-turn LLM judges with position-bias mitigation, and CI/CD regression gating by Dương Phúc Khánh (Duong Phuc Khanh · Kido — blog.khanhdp.com | khanhdp.com)
Key Capabilities
- Property-based test cases mined directly from production failure traces
- Programmatic contract assertions (regex, JSON-schema, AST parser) as first defense
- Calibrated LLM judges with position-bias mitigation and few-shot calibration anchors
- Automated CI/CD pull request regression gates with paired win-rate metrics
Author: Dương Phúc Khánh (Duong Phuc Khanh · Kido) — blog.khanhdp.com | khanhdp.com/about
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Free forever
No account required to browse
Trust & safety
Security scan
Security scan passed 1 day ago
- Free with an Agensi account
Permissions
No special permissions declared or detected