AgentEval documentation.instructions.md

AgentEval Documentation Guidelines

🎯 Core Principles

1. Evaluation First, Testing Second

• Lead with evaluation capabilities (quality metrics, LLM-as-judge)
• Follow with testing infrastructure (assertions, CI/CD)
• Frame testing as "automation of evaluation results"

2. Never Reveal Future Plans

Unless explicitly asked:

• Do NOT discuss upcoming features or planned changes
• Do NOT reference strategic direction or internal plans
• Do NOT mention /strategy folder content
• Focus on what IS available, not what WILL BE

3. No Redundancy - Point to Documents

• Never repeat detailed information already in another document
• Link to specific documents: "See assertions.md for details"
• Only repeat key principles or critical safety information

4. No Specific Numbers or Versions

❌ Don't Use	✅ Use Instead
"3,015+ tests"	"comprehensive test suite"
"21 samples"	"detailed examples"
"v0.2.0-beta"	"current version"

---

🏷️ Brand Identity

Primary Tagline: "The .NET Evaluation Toolkit for AI Agents"

AgentEval IS:

• The .NET equivalent of RAGAS and DeepEval for Python
• Built first for Microsoft Agent Framework (MAF)
• An evaluation framework that also does testing

AgentEval is NOT:

• Just a testing framework
• A Python port or wrapper
• A simple assertion library

Terminology Standards

✅ Preferred	❌ Avoid	Context
evaluation	testing	Core purpose description
evaluate	test	When describing metrics
evaluation run	test run	Metric execution
evaluation result	test result	Metric outputs

Exception: "Testing" is acceptable when discussing xUnit/NUnit/MSTest or CI/CD.

---

📚 Documentation Structure

Folder Layout

• docs/ - Main documentation folder
• docs/adr/ - Architecture Decision Records
• docs/api/ - Generated API reference
• docs/showcase/ - Examples and case studies
• README.md - Project overview
• CONTRIBUTING.md - Contribution guidelines