dimamik

Hello Hacker News, I'm a developer behind Mostra.

The problem is feedback being a bottleneck when code and prototyping became cheaper.

The solution Mostra suggests is that you add our OSS overlay script to your site, generate a link that embeds mostra project in query param, and share it with people whose feedback you care about.

These folks join the link and just talk while reviewing your feature or the whole site. Once they're done - their feedback is converted to comments that are pinned to the element they were talking about.

After the feedback is submitted, you can point your agent via MCP to fetch and act on it.

Please let me know what you think! I'd appreciate any feedback!

Good point, but the bigger the transcript (and recorded browser events) are - the bigger the amount of tokens to process this.

But I'm open to any suggestions on how to price this better!

I've been building with Elixir for the last 5 years, and comparing to Python or NodeJS - it's a breath of fresh air. Such decent developer experience, so easy to understand how your system works because of actors and well-defined primitives. If you haven't - you definitely should give it a try!

In an AI era I feel like the tiny amount of Elixir code in comparison with other languages, but all that code having higher signal to noise ration vastly contributed to how good LLM-written Elixir code is. Especially in a well-maintainted codebase that relies on a decent db schema and Oban.

Feedback on your live site, typed or spoken. Each point lands on the element it's about, ready for your team or your coding agent.

https://mostra.design

I like that we get far with just the Postgres. For an Elixir world, it's a job processing queue via Oban[1] and a search engine via Torus[2] now.

[1] https://oban.pro/ [2] https://www.dimamik.com/posts/bm25_search/