PromptEval vs PromptWizard

PromptEval is a web and API SaaS platform for evaluating and optimizing large-language-model prompts. It assigns a reproducible score from 0 to 100, with diagnostics covering clarity, specificity, structure and robustness, then identifies issues, warnings, strengths and targeted fixes. A token optimizer compresses prompts while preserving intent and reports the reduction percentage. Its versioned library keeps prompt history, score changes and diffs. The A/B Playground compares two prompts across as many as seven criteria using a user-provided API key. An official GitHub Action can fail pull requests after score drops, contradictions or production regressions. Pro and Team users can serve prompts by slug through an API endpoint, with changes taking effect in about 60 seconds. Plans include a free tier, Basic at $9 a month, Pro at $19 a month, and custom-priced Team.

PromptWizard is a free, MIT-licensed open-source framework for automated prompt and example optimization. It generates prompt variations, scores them, critiques their outcomes, and refines instructions over repeated rounds. It can also optimize in-context examples and synthesize examples suited to a task. The described workflows cover prompt optimization without examples, with generated examples, or with training data. Listed datasets include GSM8k, SVAMP, AQUARAT, and Instruction Induction (BBII). Custom datasets use JSONL samples with question and answer fields, and require task-specific answer extraction and evaluation functions, configuration, and data files. PromptWizard can generate chain-of-thought reasoning for in-context examples, with an option to turn that off to reduce prompt length. Installation uses the GitHub repository as a Python package in development mode, with instructions for Windows, macOS, and Linux. Model access setup supports OpenAI API keys and Azure OpenAI endpoints, so access requires credentials for those services. The README reports average optimization times of around 20–30 minutes in experiments on the listed datasets, with timing dependent on the dataset, and notes that human supervision can help tune outputs.