Anthropic has released a new built-in prompt generator to test, evaluate and create prompts with the Claude 3.5 Sonnet AI model. The feature can be used within the Anthropic Console, like a test kitchen for developers and help them build products with Claude and includes a built-in prompt generator that Claude released in May.
Developers can use the Evaluate tab to understand how effective their AI prompts are in different situations. One can upload real-world examples to a test suite or ask Claude to generate different AI-generated test cases to do a side-by-side comparison of how efficient the prompts are and then event rate them on a scale.
While the tool may not entirely replace prompt engineers, Anthropic said that it would help new users and save time for experienced prompt engineers.
The company’s main goal it said was to streamline the process to achieve a “faster and more accessible way to improve model performance,” and attract more developers to build more enterprise solutions.
(For top technology news of the day, subscribe to our tech newsletter Today’s Cache)
Earlier this year, CEO and co-founder Dario Amodei said that prompt engineering was vital for adoption of GenAI in an interview at the Google Cloud Next. “It sounds simple, but 30 minutes with a prompt engineer can often make an application work when it wasn’t before,” he said.
Disclaimer: The copyright of this article belongs to the original author. Reposting this article is solely for the purpose of information dissemination and does not constitute any investment advice. If there is any infringement, please contact us immediately. We will make corrections or deletions as necessary. Thank you.
