Typewise is an AI-first customer service platform where orchestrated agents resolve requests end-to-end by taking real actions across your stack. Teams describe outcomes in natural language and the platform compiles them into working automations. No flowcharts, no code. Hybrid intelligence keeps humans in control through seamless AI-human handoffs and rich policy controls. It's the AI Agent Platform that gets things done.
This is the 6th launch from Typewise. View more
Typewise AI Customer Service
Launching today
Typewise is an AI-first customer service platform where orchestrated agents resolve requests end-to-end by taking real actions across your stack.
Teams describe outcomes in natural language and the platform compiles them into working automations. No flowcharts, no code. Hybrid intelligence keeps humans in control through seamless AI-human handoffs and rich policy controls.
It's the AI Agent Platform that gets things done.
Free Options
Launch Team / Built With
A persistent conversation object with channel-agnostic events turned out to be the right abstraction for cross-channel context, rather than a thread-per-channel stitched at read time. Took a few iterations to land on, and most of that work isn't visible from the outside, which is exactly the bar we set on the engineering side. A customer moving from WhatsApp to email shouldn't have to notice the platform at all.
Typewise
@sebbmn Exactly. Not only should the customer be unaware of the switch but human agents handling a ticket should not notice it either.
Typewise
@sebbmn This was one of those architecture decisions that sounds obvious in hindsight but took real conviction to get right. The "thread-per-channel stitched at read time" approach is what most platforms default to, and it always leaks. Glad we pushed through the iterations. The best infrastructure is the kind customers never think about.
Could be very useful! Honestly, I am so frustrated with some chatbots at many companies that provide no resolution at all. One question though if users don’t define flows then where does control actually live like in prompts, policies or learned behavior??
Typewise
@lak7 Thanks, and yeah, totally feel you on the bad chatbot experiences 😅
Short answer: the AI is smart out of the box, no flows required. You connect your knowledge base, upload docs, plug in your systems, and it uses that automatically to answer.
On top of that, you can add instructions at three levels:
• Company-wide: general rules that apply everywhere
• Per channel: specific guidance for chat, email, etc.
• Per AI specialist: tailored to specific types of requests
So no rigid flows to define. You can start simple and layer in more instructions as you learn what works.
Typewise
@lak7 in addition, the benefit is also that the AI supervisor can switch between specialists, which is difficult for flow-based systems, say you first have a support query (support) and then need an upgrade to my account (sales)
@davideberle Woah, thats pretty cool! I don't think any other product provides that. Btw do you think Typewise is better than Chatbase or pls correct me if I am wrong and both are not competitors
Typewise
@lak7 Sure! Chatbase is great for building chatbots on top of your knowledge base, solid for simpler use cases. Typewise is a different animal: it's a full AI agent platform that doesn't just answer questions but actually takes actions across your systems (CRM, billing, logistics, etc.) to resolve issues end-to-end. Plus the AI sets itself up: you describe what you want in plain English, no flow building needed. So less competitors, more different categories. Think chatbot builder vs. autonomous AI workforce for customer service.
Going MCP-native from day one saved us from the usual “we’ll add that integration next quarter” loop. And with 6000+ connectors most customer requests are just a quick config change instead of something we have to slot into the roadmap.
From the engineering side, that’s what made this launch feel steady instead of a sprint we’d regret later.
Typewise
@peeckdann yes and it's also nice to speak to customers about that; before I had a meeting for a booking integration, and since that platform (etermin) has an MCP, integration is easy, and that also alleviates "this will be expensive" concerns.
Typewise
@peeckdann Yes, being able to connect all your services that easily is definitely a game changer. And technical teams can even easily build their own MCP servers if they want to.
minimalist phone: creating folders
What about initiating refunds, e.g. we need to make them via Postman or in the Google Play Order management. Can it handle? Operate on cross-platforms?
Typewise
@busmark_w_nika Yes! Typewise can connect to Postman or Google Play through MCP allowing Typewise to autonomously trigger refunds.
For added security, human approval can be turned on so that Typewise asks a human agent for approval before processing the refund. This lets Typewise handle the entire conversation but still have humans review important decisions.
minimalist phone: creating folders
@davideberle That's cool!
Typewise
@busmark_w_nika In the past every new integration used to mean a custom connector, now it's much more "point at the system, describe what you want, done" through MCPs. Refunds are a good example of where the human approval layer truly proves its value. Since these are high-stakes situations, allowing the AI to handle the whole conversation while pausing for a quick human review before the actual refund is processed hits the ideal balance. But it's totally up to you when you want human approval.
Typewise
Hey Product Hunt 👋
I'm Janis, CTO at Typewise, and it honestly feels a bit surreal to finally put this out into the world.
One of the things I'm most proud of is the UX. We didn't want another tool that requires a week of onboarding and a 40-page manual. Setting up Typewise should feel closer to onboarding a new team member than configuring enterprise software, you tell it what it should and shouldn't do, point it at the systems it needs, and it gets to work.
The hard part was making that feel effortless without cutting corners on safety. We spent a huge amount of time on the layers underneath: what the AI is allowed to know, what it's allowed to do, where a human needs to stay in the loop. That interplay between AI and human was the real design challenge for us, not the model itself.
I genuinely believe customer service is one of the clearest cases where AI can take the grind out of the job without replacing the people who care about it. And seeing it actually land with real teams is the part I still can't quite get used to.
After such a long build, I'm really curious to hear what you think of it. Honest first impressions, what stands out, what feels off, all of it very welcome.
Typewise
Hey PH! I'm David, co-founder of Typewise. Here's a hot take: most "AI customer service" tools are just glorified chatbots with better marketing. They still need you to build flows, write rules, and babysit them.
We built Typewise to be fundamentally different. It's an AI agent system that builds your AI customer service for you. Describe your goals in natural language, and our platform creates specialist agents, connects to your systems, and starts resolving tickets autonomously.
But it also knows its limits. The AI supervisor detects when a human should step in and hands off seamlessly with full context. Your team picks up in a clean, beautiful UI that makes customer service actually enjoyable.
No flowcharts. No code. No manual tuning. The AI manages itself.
We're already live with enterprises and YC startups across Europe & US, and the early results speak for themselves. Excited to share this with the PH community. Would love to hear what you think!
Response-quality grading on its own never catches the interesting failures. Action-sequence validation against an expected workflow, invariants on which tools get called for a given intent, custom policies beyond simple output checks; that's where the real agent bugs live.
Getting that into the harness as a proper API rather than a checkbox was the thing we kept pushing for on the QA side.
Typewise
@edib_imamovic Yes, being able to simulate cases is very important because even conversations about the same topic can go in many different paths.
Typewise
@edib_imamovic Exactly. Output grading catches maybe 20% of what actually goes wrong with agents in production. The real failures are silent: wrong tool called, correct-looking response but skipped a step, policy followed in letter but not in spirit. This is the layer most agent platforms don't even attempt. Glad you're calling it out.