You can think of Tidewave MCP as integrating the agent with the language runtime, while Tidewave Web integrates the agent with your actual app and its interface. It knows your views and templates, it can correlate it with the rendered page, and then automate the browser to implement and validate features.
Our announcement post goes more into detail and explains why moving the agent to the browser means you (the developer) can spend more time out of the loop: https://tidewave.ai/blog/tidewave-web-phoenix-rails
Would be amazing to be able to design the workflow using your builder, and then export to code (and choose the language) and then copy paste the code into the project... just an idea.
this is something we've been looking into. curious, would you rather export the code into an existing agentic framework like crewai/langgraph, or have it exported as raw code? also, would you prefer if the code was exported block-by-block or the entire workflow altogether?
I like a feature when watch detects that one is walking and offers to record the walk from very beginning... but unfortunately this is not always working and there is no way to initiate this manually. Hopefully they will fix this with the next release.
Open the fitness app and start a workout - outdoor walk. The first time may be a PITA, but after that it will be in your cache and on the main menu. I know because I walk every single day and in two taps I can get my workout started and recorded.
