News for hackers. Stuff that matters.

while1

We're building AI testing tools at QA.tech and this matches my experience. Great post. The hard part was never generating code. It's figuring out if what came out is actually correct. Our team runs multiple AI agents in parallel writing code and honestly we spend way more time on verification than generation at this point. The ratio keeps getting worse as the models get better at producing plausible-looking stuff.

The codebase growth numbers feel right to me. Even conservative 2x productivity gains break most review processes. We ended up having to build our own internal review bot that checks the AI output because human review just doesn't keep up. But it has to be narrow and specific, not another general model doing vibes-based review.

We are using neo4j to power our agents at QA.tech.

Essentially to make it behave more like a human so that it learns and builds up an understanding of the pages it should test we map interactions into a knowledge graph stored in Neo4j. The consists of Pages and Actions on the page as well as links to documentation sections and other relevant info, together with descriptions, metadata and embeddings for search.

To make the agents better at planning and understanding the context of the page it can search the graph for relevant information and expand through the graph for more context.

This works remarkably well. I think our agents (when they have interacted a bit w the page) are some of the best browser agents I have tested.

I would highly recommend this but you need to put some effort into a nice ontology for the graph and making the tolling right for your use case. Its really not just plug and play. :)

Re:Show HN: Opper AI – Task-Completion API for LLMs on Tuesday July 15, 2025 @12:09PM (#44572638)
Really cool tool! Great job!
This is such a great tool for developing something quickly to visualize an idea you have to other ppl. So cool!
Loving this! Very surprising that the LLMs of today are so bad at understanding interfaces but it also makes it a very interesting case for finetuning!
Re:LaTeX Math in MS Office on Monday July 31, 2017 @04:05AM (#14890231)
Neither does markdown. Just put it in a git repo.
Re:King James Programming on Saturday December 14, 2013 @06:33AM (#6905396)
The global environment is chosen here, because this is the will of God.
Re:Show HN: Make your app handle going offline on Friday October 25, 2013 @07:40AM (#6610947)
Cool! This looks really nice and definitely useful!
Re:Visualise the structure of a spreadsheet on Monday October 21, 2013 @01:20PM (#6586875)
This looks awesome! I quite often stumble upon the task of automating or porting spreadsheets into code. This is always a pain as it might in some ways be hard to visualize the flow in a chart. This tool would greatly simplify the task. Looks really sweet!
Re:Gmail.com was down on Monday December 10, 2012 @12:08PM (#4900131)
Same for me as well.
Re:Codecademy now has Python lessons on Tuesday July 31, 2012 @05:05AM (#4316347)
Nice stuff, I've tried to get a few friends to try python and this is a great way to get them started.

A bit sad it is only Python 2 though. Some of the stuff thought is not compatible with Python 3.