Jack Andrews

The source traceability is the key differentiator here. I've used tools that summarize documents well but can't point you back to where a specific claim came from, which makes them useless for anything where accuracy matters (legal, compliance, research). What's the latency like on a run of, say, 500 PDFs? And is there a way to set up incremental runs where you add new documents to an existing...

The spend cap and Slack notifications are almost more valuable than the compression itself. Running Claude Code on a large codebase without any spending guardrails is genuinely stressful. You check back after 20 minutes and it's burned through $40 on a rabbit hole. Is the compression lossy in practice? I've seen context window summaries drop important details (like specific variable names or...

Running this on the listener side is a smart design choice. The speaker doesn't have to install anything or feel like they're being "corrected," which would kill adoption immediately. One thing I'm wondering about: does the conversion affect the emotional register of speech? Accents carry a lot of tonal information beyond just phonemes. If someone is frustrated or excited, does that come...

The compare feature is what makes this interesting to me. Individual personality tests are everywhere, but seeing how two profiles interact (and predicting friction points) is a different thing entirely. Curious about the clinical validation behind the "top 5 most likely fights" prediction. Is that based on published attachment research, or is it a proprietary model trained on your own data?...

The "generative UX" framing is interesting. The observation that a travel question should look different from a health question is something most AI interfaces completely ignore. Everything gets the same text-wall treatment regardless of what you're actually trying to do. How do you handle questions where the best answer is "it depends on your situation"? Health questions especially tend to...