Skip to content
TQT
AI evaluation 2025

APIT: Agent Programmatic Integration Testing.

An AI-assisted API testing application that generates structured test scenarios from API documentation.

What's in the name? The project name is a strategic play on words: while the immediate scope executes API Testing, the system architecture establishes a foundation for Agent Programmatic Integration Testing.

Problem

Manual API test design does not scale.

Execution tools like Postman and JMeter still depend on manually designed test cases. APIT demonstrates LLM-based test generation: it reads API documentation, defines test scope, generates structured test cases, executes them, and reports pass/fail outcomes.

What I built

Controlled data synthesis and small-model fine-tuning pipeline.

Manual API documents were distilled into prompts, used to generate 1,258 bilingual English/Vietnamese samples, and converted into structured test-case outputs with reasoning. Qwen-2.5-3B and Llama-3.2-3B were fine-tuned with LoRA/4-bit training under identical hyperparameters.

Document preprocessingStandardize API docs from OpenAPI, Swagger, PDF, or structured text.
Test scopeSelect requirements, endpoints, and value/risk boundaries for generation.
LLM generationFine-tuned model + RAG generates structured test cases and reasoning.
Execution/reportRun requests, classify pass/fail/exception, and present results.

Evaluation

Structured output quality measured with reference-based metrics.

Generated test cases were evaluated with precision, recall, and F1 using fuzzy string similarity, numeric tolerance, and categorical matching. Qwen-2.5-3B LoRA achieved 0.655 macro-F1, outperforming the Llama-3.2-3B baseline.

Reasoning quality was assessed through logical validity, coherence, and groundedness, aligning with the agent evaluation direction.

Agent Testing Connection

APIT as evidence for the Agent Testing / Evaluation direction.

APIT demonstrates the evaluation methodology behind ATA. The same LLM-as-a-Judge patterns, structured output evaluation, and fine-tuning experiments used in APIT inform how RAG and agent workflows should be tested and validated at scale.

The APIT pipeline — document understanding → test generation → automated evaluation → regression reporting — mirrors the evaluation loops that ATA applies to RAG and agent workflows as a completed standalone validation platform.

Stack

LLM fine-tuningLoRAQwenRAGAPI TestingEvaluation