We've added new features to the Anthropic Console: https://lnkd.in/ertrbfcU. Claude can generate prompts, create test variables, and show you the outputs of prompts side by side. Use Claude to generate input variables for your prompt. Then run the prompt to see Claude’s response. The new Evaluate tab enables you to automatically create test cases to evaluate your prompt against real-world inputs. Modify your test cases as needed, then run all of them in one click. We’ve also added the ability to compare the outputs of two or more prompts side by side. As you iterate on different versions of the prompt, your subject matter experts can compare responses and grade them on a 5-point scale. Test case generation and output comparison features are available to all users today.
Perhaps ‘prompt engineering’ won’t be the long-term career cert some were selling it as, just months ago…
Good morning, I followed the procedure to receive the 5 credits to try it but after providing the Italian number it didn't work. Is this feature available in Italy? Is it possible to use this tool unlimitedly in the paid version?? Thank you very much and congratulations for the hard work and results you bring us.
The Evaluate tab for creating and modifying test cases is a game-changer. Excited to see how these features elevate user experience!
Great, but now Im getting content generation warnings for a simple breakout game
#UX matters when using prompt based data & enlightment engineering. #insight and having a personal repository of your research history (#prompts and #result evalulation) is a rare feature in current mainstream interface implementations (there is too much #play and often no #ground) so this may end up in the demand for more #playground …
I just shared an exciting idea about a significant technological advancement for chatbots, which could be implemented in either Claude or GPT. Now, I'm anxiously waiting to see which platform will adopt the concept first. The revelation actually came to me while using Claude, and I'm eager to see it in action during my daily AI tasks. However, I can't shake the feeling that it's already being developed somewhere else.
A great way to democratize the prompting process for those who aren't as familiar with prompt engineering techniques. Even beyond this, "Evaluate" is a very good tool to have
This is very useful. I was doing something similar in python with API access but making it available in the interface directly is great.
The console ( particularly the prompt gen ) has been really useful
AI-powered HR Innovation Consultant, HRTech Product Manager & Fractional CHRO, helping orgs conquer people, product, process, and tech challenges. AI for HR. productizehr.substack.com. Remote work expert.
3wI think we're starting to see a change in the tide with GenAI tools, where things are evolving from tools to PLAY with AI, into tools that are more clearly designed to WORK with AI. As value creation opportunities are more clearly understood and use cases are more clearly articulated, tools evolve to become more useful and usable. Less magical AI, more explainable AI.