To help the agents understand the codebase, we indexed our code into a graph database using an AST, allowing the agent to easily find linked pages, features, databases, tests, etc from any one point in the code, which helped it produce much more accurate plans with less human intervention and guidance. This is combined with semantic search, where we've indexed the code based on our application's terminology, so when an agent is asked to investigate a task or bug for a specific feature, it'll find the place in the code that implements that feature, and can navigate the graph of dependencies from there to get the big picture.

We provide these tools to the coding agents via MCP and it has worked really well for us. Devs and QAs can find the blast radius of bugs and critical changes very quickly, and the first draft quality of AI generated plans requires much less feedback and corrections for larger changes.

In our case, I doubt that a general purpose AST would work as well. It might be better than a simple grep, especially for indirect dependencies or relationships. But IMO, it'd be far more interesting to start looking at application frameworks or even programming languages that provide this direct traversability out of the box. I remember when reading about Wasp[0] that I thought it would be interesting to see it go this way, and provide tooling specifically for AI agents.

[0] https://wasp.sh/

Comments URL: https://news.ycombinator.com/item?id=45525923

Points: 3

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=45369687

Points: 39

# Comments: 46

Comments URL: https://news.ycombinator.com/item?id=44296239

Points: 3

# Comments: 0

Now I only wish for an Product Manager model that can render the code and provide feedback on the UI issues. Using Cursor and Gemini, we were able to get a impressively polished UI, but it needed a lot of guidance.

> I haven’t yet come across an agent that can write beautiful code.

Yes, the AI don't mind hundreds of lines of if statements, as long as it works it's happy. It's another thing that needs several rounds of feedback and adjustments to make it human-friendly. I guess you could argue that human-friendly code is soon a thing of the past, so maybe there's no point fixing that part.

I think improving the feedback loops and reducing the frequency of "obvious" issues would do a lot to increase the one-shot quality and raise the productivity gains even further.

A visual queue of reaching within the success range would do a lot too. Was a bit confused whether I was right or not after submitting the answer.

[0] https://arxiv.org/abs/2310.06816

It's a simplification, since 100% of an individual's subscription doesn't go to directly to royalties, it's after expenses.

Smaller artists are frustrated with this model as it favours the big artists.

[1] https://support.spotify.com/us/artists/article/royalties/

Edit: added the link.

Comments URL: https://news.ycombinator.com/item?id=40813126

Points: 2

# Comments: 0

At Delogue, we are on a mission to make fashion and lifestyle product developers' lives easier and make them work smarter and more sustainably. Since 2011, we have developed a collaboration platform for brands and their suppliers so that they can manage their product life cycle more efficiently and with full transparency.

We're hiring two senior technical roles, who'll have significant impact on the future technical architecture of our core SaaS product.

1) Solution Architect https://thehub.io/jobs/65c0eda8102205f5c74c7230

2) Cloud Engineer / DevOps https://thehub.io/jobs/65c0e7d1102205f5c74b28ed

You'll be joining the technical leadership team in our main office in Copenhagen. We're a family-first company with flexible hybrid WFH, great benefits, and a diverse team from (almost) all corners of the world.