Jared Salois

For more than 3 years, I ve always been getting that one request in my DMs: Will you hunt us?

And I think it s great that founders realise launching on Product Hunt can bring publicity.

I've been working with LineageLens and just added a custom agent adapter so our internal CLI tool is attributed with prompts, model metadata, and confidence evidence. The registry design makes this surprisingly low-friction: implement a detect(input) that returns a NormalizedAgentContext (tool name, model, session ids, confidence, and evidence), register the adapter, then run the quickstart proxy to validate captures.

Why this matters: your team can capture private or bespoke tools without sending data to a vendor, and you get prompt code linkage in PR reviews and dashboards. I followed the recent repo changes (custom agents landed in late May) and found the adapter API predictable: detection should be conservative, emit evidence items, and choose appropriate ordering so your specialist adapter wins over the fallback.

If you ve extended LineageLens for an internal tool, what heuristics did you use to build confidence and avoid false positives?

While launching your product, one of the most important part of the marketing process is finding the right audience. Getting good reach does not necessarily mean that you have been a good person in marketing your product. For https://bitgrain.app I got a huge influx of audience, but that was very wrongly justified as a AI first tool. So even though a huge chunk of people came to use my product, they were disappointed that it was not an AI first tool. This caused the SEO to even hamper I guess. So even after getting a huge reach, it did not bring in much fruitful results. Currently I have focused a lot on making corrections so that the SEO picks it up correctly as what exactly the tool is used for and I am getting Users who actually need the platform.