Show HN: Dumped Wix for an AI Edge agent so I never have to hire junior staff

So I killed it all and spent 4 months building a 'talker': https://axoworks.com

The stack is completely duct-taped: Netlify’s 10s serverless timeout forced me to split the agent into three pieces: Brain (Edge), Hands (Browser), and Voice (Edge). I haven’t coded in 30 years. This was 3 steps forward, 2 steps back, heavily guided by AI.

The fight that proved it worked: 2 weeks ago, a licensed architect attacked the bot, trying to prove my business model harms the profession. The AI (DeepSeek-R3) completely dismantled his arguments. It was hilariously caustic.

Log: https://logs.axoworks.com/chat-architect-vs-concierge-v147.h...

A few battle scars:

* Web Speech API works fine, right up until someone speaks Chinese without toggling the language mode. Then it forcefully spits out English phonetic gibberish. Still a headache.

* Liability is the killer. Hallucinate a building code clause? We’re dead. Insurance won’t touch us.

* We publish the audit logs to keep ourselves honest and make sure the system stays hardened.

Audit: https://logs.axoworks.com/audit-2026-02-19-v148.html

The hardest part was getting the intent right: making one LLM pivot seamlessly from a warm principal’s tone with a homeowner, to a defensive bulldog when attacked by a peer. That took 2.5 months of tuning.

We burn through tokens with an 'Eager RAG' hack (pre-fetching guesses) just to improve responsiveness. I also ripped out the “essential” persistent DBs—less than 5% of visitors ever return, so why bother? If a client drops mid-query, their session vanishes. No server-side queues.

The point: To let me operate with a network of seasoned pros, and trim the fat.

Try to break it. I’ll be in the comments. Kee

I just wanna know what it does, in your own words.

I’ve read the linked thread. I see no attacks, only simple questions. Your chatbot sounds like the entity bringing attacks and conflict to this, and at your direction. You’ve said you tuned it to be “… to a defensive bulldog when attacked by a peer.”

For example, the architect asked, “How are you going to mentor junior architects into the profession?” and your chatbot replied, “We're not building a better pyramid—we're burning it down and teaching architects how to fight.”

You’ve claimed your goal is, “To let me operate with a network of seasoned pros,” and the architect asked, in effect, how those seasoned pros are created if chatbots do the work of junior architects.

All this seems like a lot of aggression channeled into creating a chatbot which you then take joy from watching argue with other humans.