1
I’m Bohdan, building Lenzy - product analytics for conversational AI.
With traditional Web/Mobile UIs, we know exactly how users interact with our buttons and screens thanks to tools like Amplitude or PostHog. In conversations with AI, users literally say what they want and what frustrates them. Yet most teams building AI agents are flying blind, relying on intuition and occasional user feedback.
Lenzy fills this gap. It plugs into any AI conversation and tells you exactly what users struggle with and what they actually use your agent for. Fix the most painful problems (and verify they're fixed), double down on features that resonate.
And we just launched a free Discovery plan: plug in the Lenzy SDK (~10 minutes), collect a week of data and get a full report. No credit card required™
You get an actionable snapshot of what's happening in your chats. All we ask in return is feedback! What’s missing? What would make this useful for your team? Do you already solve this problem in any way?
All the media entrepreneurs I followed were flexing their perfect discipline and healthy lifestyles. I thought it was an integral part of success. So for half a year, I maintained perfect sleep, worked out 6-7 days a week, ate clean, and completely quit alcohol.
Have I succeeded yet?
Not yet. I substituted the hard work - building and getting customers - with something easier that felt like progress - endless preparation.
It sounds like complete nonsense now, but I genuinely believed that if I got good enough, entrepreneurship would just happen on its own. I was still working full time and trying different projects, partnerships, but I was definitely not realizing that it's me who is responsible for making it happen. And I see so many friends falling into the same trap. Self-improvement feels like progress without the risk of actually failing.
Since summer, I've significantly deprioritized self-improvement. I allow myself junk food when I want it, beers with friends, and skipping gym when I don't feel like it. But now I focus all my effort on one thing - building and getting customers.
Here's what I've built so far:
embedex.io - Turns out bloggers don't want it. Spent around 8 weeks but learned a hard lesson: don't build in isolation.
lenzy.ai - This looks promising. Already found a few early adopters, making sure I make them happy.
I don't mean that living healthy or improving your habits doesn't matter. But it's not the work itself - it's just making the work easier.
Yesterday, a friend asked me this question; he would like to know things like "What users ask that my agent can't accomplish?", "What users hate?", "What do they love?".
A quick insight from another small startup - they are quite small so they just copied all the conversations from their database and asked ChatGPT to analyze them. They found out that the most requested missing feature was being able to use URLs in messages.
I also found an attempt to build a product around this but it looks like the project has been abandoned: https://web.archive.org/web/20240307011502/https://simplyanalyze.ai/
If there's indeed no solution to this and there are more people other than my friends who want this, I'd be happy to build an open-source tool for this.
Turns out he's dropping $2,000/month on Cursor for AI coding. It's honestly the craziest thing I've heard in a while.
I told him to switch to Claude Code, which handles all my AI coding needs for around $20/month. I'm an experienced dev so I don't need AI for every little thing, but even if he's a heavy user, $200/month should easily cover his needs.
Just like that, I saved him at least $1,800/month.
Had to share this because apparently we're living in a world where you can accidentally spend more on AI coding tools than on your rent.
Do many people find Cursor/Windsurf obsolete when there's Claude Code?