Ben Lang

Typewise AI Customer Service - Automate customer support across systems with AI agents

by
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.

Add a comment

Replies

Best
Ivan Djordjevic

Proud of the team for getting this out. The simulator does both: historical replay against new instruction versions for regression coverage, and synthetic generation for the long tail.
We argued on the engineering side about which to build first, and eventually decided neither one on its own makes the evaluation loop useful rather than theatrical. Both landing cleanly is the part I'm most invested in.

David Eberle

@ivander That debate was worth having. Replay without generation gives you confidence on known cases but zero coverage on edge cases. Generation without replay gives you breadth but no regression safety. Both together is what makes it an actual evaluation loop instead of a demo checkbox.

Dominic

A defensible ROI estimate in 60 seconds shortens discovery by a full call when you're running against an incumbent.

Saw it during a live demo last month, which is not something calculator widgets usually pull off. Small feature, outsized impact, and a detail I kept advocating for from the GTM side. A proper end to end solution for once!

David Eberle

@dominic_bahmani_fard You were right to push for this. A calculator widget sounds like a "nice to have" until you see a prospect skip a 30-minute discovery call because they already know the numbers. That's the kind of detail that compounds across hundreds of deals. Small feature, outsized impact, exactly!

Ali Johnson
We are actually dealing with our own AI-to-human handoff logic today with our launch (flagging physical hazards and routing to human professionals), so your 'hybrid intelligence' feature immediately caught my eye. How does Typewise determine the exact threshold for when an agent needs to hand a ticket over to a human rep? Is it based on sentiment analysis or strict policy rules? Love the clean UI!