Wilco Kruijer

Seems like a compelling product, congrats on the launch! Do the scraping agents from the big labs all set a proper user agent? Or in other words, could they hide this data from you?

Has anyone gotten some good results with this they'd like to share? The generations feels pretty good, but still a bit slop-y.

Good idea! Would you consider adding an option to see videos as a slide show? Extracting the most important frames.

Looks beautiful! What are your plans for the AI mode? I just entered an API key and prompted something relatively simple and got a less-than-optimal result. Would be cool if I could back-and-forth with the AI to refine my result.

Having a working demo on the home page feels like a big plus over just some screenshots. Definitely cool!

Cool launch! Would there be some way to connect to databases behind a firewall?

Very useful! Could I somehow integrate this into a CI pipeline?

I really liked Composer 1 because of its speed and cost. When I have to get simple tasks done quickly I reach for it. This new model however seems super expensive. Apparently more expensive than Codex, which makes it a pretty bad value proposition. The direction seems valid though: quick models.

Seems interesting. What is a typical workflow with Axel? Would I be creating multiple tasks which are then spread over multiple agents? Or is it more a 1:1 workflow where I'm "baby sitting" an agent?

It was definitely time for Mistral to launch something SOTA! Awesome.

Love the design! Budgeting is something that I always want to be doing, but never end up being persistent enough on. How are you thinking about keeping people engaged?

Cute little app! Would you ever consider adding export functionality? Or what that go against the philosophy?

Awesome result on the DeepResearch Bench, congrats! Would you consider adding an option for BYOK (bring-your-own-key)?

Cool launch! How does this compare to Google's built-in `=AI` functionality?

Congrats on the launch! I'm a bit confused by the homepage, I don't see much of a focus on browser extensions there. Is that something new you're exploring? I think the browser extensions play is compelling, since there's no real deployment process. Extensions could just immediately be installed and available/useful to the end user. Would it be a "one install -> many extensions" approach or...

Sounds super useful. What kind of documentation platforms do you support? Do you need to have the documentation in Markdown files in the same repository?

I particularly like the idea of surfacing an AI bot to the user to help them fill in the form quickly, especially the voice part could convince me to fill in a form that I usually might not. I'm wondering: are all the questions shown at once in the AI mode? To me it would make the most sense if I can answer all the questions in a single voice note.

Looks useful! Does this handle multiple repositories and multiple checkouts of a single repository? I'm assuming so from reading the landing page. How do you use this, do you just make sure your laptop is on all the time? Could we deploy to a remote server?

Looks interesting, I feel like there are a couple good use cases for this. I'm wondering how flexible this is, do you have generic way of defining "patches". Could it also work for other domains and apps that are not Next.js? Is it / could it be combined with AI to automatically patch projects?

Congrats on 1.0! Looks like a lot of thought went into creating an API surface that makes sense. Now I just need a use case for this...