Version updated for https://github.com/SyntheticSynaptic/agentura to version v0.7.0. This action is used across all versions by 0 repositories. Action Type This is a Composite action. Go to the GitHub Marketplace to find the latest changes. Action Summary Agentura is a GitHub Action designed to automatically test and validate the behavior of AI agents during development. It identifies regressions or improvements in the agent’s performance by comparing its behavior against predefined baselines after every code change, ensuring issues like accuracy drops, behavior changes, or performance regressions are caught before merging. The action supports various evaluation strategies, such as semantic similarity, conversational consistency, and performance monitoring, and provides detailed results directly in pull requests to streamline testing and maintain AI reliability.

Version updated for https://github.com/SyntheticSynaptic/agentura to version v0.6.0. This action is used across all versions by 0 repositories. Action Type This is a Composite action. Go to the GitHub Marketplace to find the latest changes. Action Summary Agentura is a GitHub Action designed to test and validate AI agent behavior by comparing expected outputs to actual performance on every pull request. It automates the detection of regressions, improvements, and other changes in areas like accuracy, quality, tool usage, and performance before merging, ensuring reliable updates and reducing the risk of unnoticed issues. Key capabilities include baseline comparisons, multi-turn conversation testing, and support for various evaluation strategies such as semantic similarity, LLM-based judgments, and cost/latency guardrails.

Version updated for https://github.com/SyntheticSynaptic/agentura to version v0.5.0. This action is used across all versions by 0 repositories. Action Type This is a Composite action. Go to the GitHub Marketplace to find the latest changes. Action Summary Agentura is a GitHub Action designed to test and validate the performance of AI agents by comparing their behavior against predefined baselines during each pull request. It automates the detection of regressions, improvements, and deviations in areas like accuracy, tone, tool usage, and performance, ensuring that changes to code, prompts, or model updates do not negatively impact the agent’s behavior. Key capabilities include customizable evaluation strategies, multi-turn conversational testing, and integration with GitHub for seamless feedback on pull requests.

Version updated for https://github.com/SyntheticSynaptic/agentura to version v0.4.0. This action is used across all versions by 0 repositories. Action Type This is a Composite action. Go to the GitHub Marketplace to find the latest changes. Action Summary Agentura is a GitHub Action designed to automate testing of AI agents by comparing their behavior against predefined baselines. It ensures that changes to the agent—such as updates to prompts, tools, or model providers—do not introduce regressions or degrade performance. By running tests on every pull request, it identifies issues like accuracy drops, behavioral inconsistencies, or cost inefficiencies before merging, providing actionable feedback directly in your workflow.