Recently Added
3,528 documents
CLAUDE.md
Guides Claude Code to generate relevance judgments for product search queries using a three-phase agent architecture against the WANDS dataset.
LLM Eval Judge - REST API Documentation
Documents a Symfony-based REST API with CRUD endpoints for managing LLM evaluations, providers, models, test cases, metrics, prompts, results, benchmarks, and settings.
Essential tools setup
Outlines a 12-month solo development plan for an educational platform, including tech stack, sprint priorities, and billing-first architecture.
Common Standards Issues
Catalogues 20 common working group problems with symptoms, results, and 10 success factors to avoid or resolve them.
CLI PROTOCOL - Ananta Shesha (The 16-Word Shell)
Maps 16 words of the Hare Krishna mantra to 16 CLI commands with strict typing and GAD-000 compliance criteria.
Create model directory
Walks through setting up a local AI coding assistant with DeepSeek, Docker, and a VS Code extension for real-time code analysis.
Environment
Documents the judging and local development environment for an ICPC-style programming contest, including verdicts, allowed software, and compiler versions.
OTP Feature - Test Cases & Scenarios
Lists 40 manual test cases covering OTP generation, verification, login, UI, database, security, and error recovery flows.
LLM Integration Guide
Explains how to configure and integrate multiple LLM providers into a SaaS testing project for requirement parsing, test generation, and result analysis.
Agent Instructions: Execute TESTME.md Tests
Defines a Markdown-based test specification format and instructs an AI agent to discover, parse, and execute those tests in a codebase.
MCP Server Audit - TODO and Future Improvements
Lists over 100 planned features, improvements, and research items for an MCP server security audit tool, organised by priority and area.
Тест-кейси для мануального тестування UI
Defines 70+ manual UI test cases for event registration, payment, promo codes, responsive design, and error handling.
CI Test Cases (Sprint 1)
Documents 22 CI test cases for a Next.js project with Stripe and Supabase, covering build, linting, security, and file checks.
Multi-Workflow System — Product Requirements
Defines requirements for a demo web app unifying Estimates, Contracts, and a Copilot across both workflows.
RFC: Zones of Distrust (ZoD) v0.9
Proposes a layered security architecture for autonomous AI agents that separates reasoning from execution and enforces runtime governance of privileged actions.
October 1
Logs daily progress notes, code statistics, and design decisions for an AI-assisted VS Code extension project over several weeks.
Agentic Benchmark Checklist (ABC)
Lists 30+ criteria for evaluating the validity, outcome measurement, and reporting quality of agentic benchmarks.
Table of Contents
Lists 20+ sections of a SecureSphere AI agent development guide, including architecture, tutorials, and comparisons to Barrelfish.
Installing
[pytest-cases](https://smarie.github.io/python-pytest-cases/) is a pytest plugin
Comprehensive Test Cases
Lists 200+ test cases for TypedArray.prototype.search, searchLast, and contains, covering validation, matching, edge cases, and semantics.
User Acceptance Testing (UAT) - Certify-NFT Application
Documents 27 UAT test cases across 10 modules for a certificate NFT application, all marked as passed.
Aegra API 测试用例集
Provides 50+ curl-based API test cases for the Aegra Agent Protocol Server covering health, assistants, threads, runs, and store modules.
Unit02
Outlines a 9-hour academic unit on operations strategy with readings, lectures, and a graded writing activity.
🤖 AI-Powered Test Automation
Introduces AI and ML techniques for test automation, covering tools, self-healing tests, test generation, and predictive execution.