NINA - Guide users step by step inside your product.
by•
NINA lives inside your product and helps users exactly where they get stuck. They ask “How do I…?” by voice or text, and NINA guides them step by step on the live interface before they open a ticket, search documentation, or message support. It is not a scripted tour, chatbot, or FAQ. NINA is built for B2B SaaS teams still relying on onboarding calls, product videos, Slack channels, and repeated support answers.
Replies
Congrats on the launch! Does the assistant mostly work in a chat-like manner, guiding you through, or can it act as a fallback to a more interactive onboarding?
NINA
@mateuszkonik This is real time walk-through , like GPS , it shows you UI in real time...think like someone if giving you real time demo or showing how to work ,rather than just 20 steps like product manual
NINA
@mateuszkonik Not chat, this is like any Human expert is giving you training and walk through.....Like GPS
The part I would ask about is the handoff. When NINA cannot finish something, whoever picks it up next needs the transcript and the steps already tried, otherwise the person types it all again and the deflection becomes a tax on the customer.
The other half is which questions guidance can reach at all. How do I is a UI question and you can walk someone through it. Why did this happen to my order is a record question, and pointing at the screen does not answer it. Deflection rate looks great on the first kind and never touches the second.
When NINA gives up, what does support receive?
NINA
@jernej_jan_kocica That is exactly the problem we are trying to avoid.
When NINA cannot complete the request, support receives the full transcript along with the steps NINA already tried. The user should not have to repeat the problem from the beginning.
You are also right about the boundary. “How do I complete this workflow?” is a product-guidance question, and NINA can walk the user through it. “Why did this happen to my order?” requires access to the customer’s actual records and business data.
Without that integration, NINA should not pretend it can answer. It should hand the case to support with the full context. With the right API or system integration, we can extend it to those record-specific questions as well.
So for us, the goal is not just deflection. It is either resolving the issue or making the handoff much better.
@varun1jan Then the headline number should not be deflection. If the goal is resolve or hand off better, the honest metric is what share of handed-off cases support closed without asking the customer anything again. That is exactly what the transcript is supposed to buy, and it is measurable from day one.
One caution from the support side. A transcript of a failed guidance session can be long and still not say what the person was trying to do. What saves the agent is the intent, not the list of steps.
Do you report that handoff number to customers, or only deflection?
NINA
@jernej_jan_kocica This is good point, we are still very young.. our focus is to help user to perform key workflows without any drop and support...but ur point has weight....
@varun1jan Fair, and getting people through the workflow without dropping is the right thing to be good at first.
The only part I would do early is record it, even if nobody reports it. A flag on the conversations that got handed off, and whether support had to ask the person anything again. Costs nothing now and gives you the number later, when you want to make the claim.
Good luck with the rest of the launch.
the voice side is what i want to know more about - is the TTS running locally or a cloud round trip, and does that add noticeable lag when someone's mid-flow waiting for the next step? that gap is the difference between feeling like a live guide and a chatbot with a delay
NINA
@sabber_ahamed We are using AWS, but we have plan to put on device too.... currently the focus on workflow execution , rather than voice.. business user are more focused on getting the right workflow..vocie make is easy bit...
Treblle
damm, this is the right use of AI inside product we all wanted. Congratulations on the launch.
NINA
@savan_kharod1 thanks..
NINA
@savan_kharod1 Yeah..in deed
Pythagora
NINA looks genuinely exciting. Guide users step by step inside your product. is a strong problem to tackle—congrats on the launch! 🚀
NINA
@leon_ostrez thanks..In deed
Congrats congrats! Just wanted to check if NINA works with both web and desktop applications? Kudos again!
NINA
@kushagra_jajoo Thanks. It works for Web for now....
As someone just starting to build products, this looks really useful. Just in my testing so far I have seen the amount repetition that comes from user questions.
NINA
@d_jamison_cantrell Yes, ppl ask same questions again and again, because we can remember only certain amount....
PRISM by Block Convey
Hi @varun1jan
Great product, when I logged in. To hear Nina was something else. But I got stuck while creating the workflow, asked Nina but I guess I already started the process and NINA could not help much.
Do you have some instructions there?
NINA
@arun_prasad06 let me reach out to you directly..
Pazi
This looks super exciting - congrats on the launch! Real-time in-product guidance is exactly what users need.
NINA
@zvonimir_sabljic1 In deed..thanks ...
NINA
@zvonimir_sabljic1 Thanks..Yes for sure...
since voice input works too, does it pick up on tone at all, like frustrated vs just curious, or is it purely speech-to-text into the same guidance flow either way?
NINA
@sabber_ahamed No... as focus in on workflow UI and less of converstaion... like like you wanted to create pipeline in hubspot( or any CRM) , you will ask, and NINA will guide you or will do on behalf of you