Cesurhan Uygun

Hey Sohaib, love that you extracted this from 3 real deployments instead of building in a vacuum. That embassy→university→telecom path is a great validation arc. One question: when you pitch agencies or consultancies, are they reselling Nexus under their own brand, or is white-labeling off the table for now? Running into the same question on our side (AI chatbots for agencies) and how you...

Hey, this is right next to what I'm building at TalkBuildr so I've been thinking about this exact problem for a while. Script tag install plus booking + product discovery in one widget is a solid combo, most tools split those into separate products. One thing I kept hitting: when the site changes and you re-sync the knowledge base, do you handle dedup or does the bot start seeing old + new...

Congrats on the launch Amir. Building in the same space with TalkBuildr so this hits close to home. Quick question on the $249 Agency plan, how are you handling per-client KB isolation and white-label billing pass-through, those are the two things my agency users ask about the most. Curious what you landed on.

Nice pivot from rule-based to agents, we made the same call at TalkBuildr last year. Quick q for you: how are you handling KB freshness when a client's site content changes? We're still wrestling with dedup on re-sync so the bot doesn't answer from stale chunks. What did you land on?

Nice, the "no signup for clients" thing is the one feature most portal tools get wrong quick q: any plans to let freelancers drop in an AI assistant inside the portal so clients can ask "where are we on invoice X" or "what's the latest mockup" without pinging? Building Talkbuildr (chatbot for agencies) and every designer I talk to asks for something like this

Hey Talha, visual flow editor over "one giant system prompt" is exactly the right call, I've been building TalkBuildr (text chatbot side) and we hit the same wall with branching and post-call actions. How are you handling knowledge base freshness when docs change mid-flow, do you re-embed on upload or batch it? Also the built-in jailbreak blocking is a smart angle for agencies selling to...

Really cool you shipped an MCP server for content management, that's a smart move. I'm building TalkBuildr (AI chatbots for agencies) and the multi-tenant workspace bit resonates a lot, same pain point we hit with client isolation. How are you handling content versioning when AI agents make autonomous edits? Is there rollback story or if it's fire-and-forget.

Very nice to see another builder tackling multi-channel chatbots. I'm building TalkBuildr (AI chatbots for agencies to white-label and resell) so we're in a similar space but different angle. About the USSD side, how do you handle the character limits when the AI wants to give a longer answer? Does it paginate or summarize?

Nice that you built this from your own agency pain, the 'leads ghost you by morning' problem is I think why agencies need AI on their client channels. Skipping the Meta Business API approval dance is a smart call, that onboarding is brutal. Do you see agencies reselling Ziggy to their own clients, or is it mostly self-serve so far?

Interesting angle, MCP as the embed surface instead of a chat widget. How are you're handling auth scoping when an agent hits a logged-in area, that's the bit we kept hitting walls on with our chatbot embed at TalkBuildr. Are you exposing actions read-only at first or full RPC?

The client view-only seat with Quanta access is a smart call, we're building something similar at TalkBuildr where agencies manage AI chatbots for clients and the biggest ask is always 'how do I let my client see what's happening without breaking things.' How are you handling the handoff when a client wants to go from view-only to actually tweaking agent behavior?

Nice approach to the RAG lifecycle problem, that's the part everyone underestimates. we built something similar at TalkBuildr but focused on agencies white-labeling chatbots for their clients. How do you handle knowledge base updates when the source content changes, do you do incremental syncs or full re-index?

Awesome to see someone tackling the commission problem for restaurants via WhatsApp. We're building something adjacent at TalkBuildr, AI chatbots that restaurants embed on their website for reservations and menu questions. How do you handle multi-language menus? Our restaurant clients in Amsterdam keep asking for that.

Great angle targeting trades specifically. We're building something similar for web agencies (AI chatbots they can white-label for their clients) and the biggest challenge has been making the AI sound like it actually knows the business, not just generic responses. How are you handling the knowledge training part, do clients upload docs or is it more structured setup?

The 'dead landing page' problem is real, we dealt with the same thing building TalkBuildr. Our chat widget is also a single script tag embed so the distribution model is similar. I would like to know how you handle the cold start, what do the notifications show before you have any real signups?

Smart angle, turning audits into client-ready pitches instead of just reports. We build TalkBuildr for the same audience (agencies) but on the support side, AI chatbots they deploy on client sites. Would like to know how agencies respond when the pitch is AI-generated vs hand-built, do they care or just want the close faster?

The commission math is brutal, $3.78M/year for a 50-location brand is insane. We see the same thing from the support side building TalkBuildr, restaurants spending staff time answering the same menu and hours questions that a chatbot could handle for €24/month. How are you handling the customer support layer once orders come through your platform, do restaurants still field calls directly?

Next.js + Supabase gang. We built TalkBuildr on the same stack for AI chatbots as a service. The client portal being included on every plan is smart, we learned the hard way that agencies will pay for the tool but churn if the client-facing piece costs extra. About the AI layer you mentioned building last, what made you sequence it that way?

Really cool to see this, we ran into the exact same scaling problem building TalkBuildr (AI chatbots as a service for agencies). The white-label portal + billing combo is where it gets tricky. How are you handling the credential handoff when clients need to swap their own API keys mid-deployment?

Planning by vibe is a fun angle. I'm working with a travel community that wants something similar but powered by local insider knowledge instead of generic AI. Where does your travel data come from, scraped reviews or something more curated?