Search Results for "tests"

...Instead of putting everything in README or doc files (which are more human-oriented and might mix high-level narrative), AGENTS.md is intended to surface agent-relevant details that help them “do the right thing” (tests, style, project structure, tooling).

AIPex is an AI-augmented development toolkit and workflow platform that aims to accelerate software productivity by integrating intelligent assistants, code generation tools, and customizable automation patterns directly into developer workflows. Rather than treating AI as a separate helper, AIPex embeds AI capabilities into common tasks like scaffolding components, generating tests, analyzing code quality, and performing refactors, allowing developers to stay in flow while benefiting from model-assisted insights. It supports modular plugin architecture so teams can extend or customize how assistants behave based on project conventions, code standards, or tooling preferences. AIPex also includes orchestration pipelines that let teams define multi-step AI-driven transformations — for example, generating code then running validation, producing documentation, and opening change requests — all within a unified pattern.

...The system is organized into multiple domains such as growth experimentation, sales pipeline generation, content production, outbound marketing, SEO optimization, and financial analysis, effectively covering the entire revenue lifecycle of a business. Each skill functions as an executable capability that can be invoked on demand, enabling users to perform tasks like running A/B tests, generating high-quality content, or analyzing conversion funnels with minimal manual effort.

ASSERT is a requirement-driven evaluation harness for AI agents and LLM applications. It turns natural-language specifications, policies, product requirements, and launch criteria into structured tests that can be reviewed, executed, scored, and improved. The pipeline derives behavior categories, generates single-turn and multi-turn test cases, runs them against a target system, and uses an LLM judge to score conversations against the stated policies. It can evaluate hosted models, custom agents, multi-agent systems, REST clients, and frameworks such as LangGraph, CrewAI, AutoGen, DSPy, LlamaIndex, and OpenAI Agents SDK. ...

...The platform is optimized for research tasks such as financial forecasting, knowledge discovery, and large-scale information synthesis. MiroThinker has been evaluated on several agent benchmarks and has demonstrated strong performance on tests designed to measure deep research capabilities.

OSS-Fuzz-Gen is a companion project that helps automatically create or improve fuzz targets for open-source codebases, aiming to increase coverage in OSS-Fuzz with minimal maintainer effort. It analyses a library’s APIs, examples, and tests to propose harnesses that exercise parsers, decoders, or protocol handlers—precisely the code where fuzzing pays off. The system integrates with modern LLM-assisted workflows to draft harness code and then iterates based on build errors or low coverage signals. Importantly, it aligns with OSS-Fuzz conventions, generating corpus seeds, build rules, and sanitizer settings so projects can plug in quickly. ...