AI for customer support

AI customer support that resolves problems instead of just replying.

Pronomy handles recurring product questions, cancellations and refunds.

It uses your knowledge, policies, flows and customer state to answer or take approved actions.

When a person is needed, it hands off the reason and work so far.

Book a call → See the platform
Pronomy organises different support requests and follows a cancellation from request to confirmed result.

Pronomy — Support in action. A cancellation workflow: identify the request, check company policy, confirm the action before replying, and review the evidence. Music only.

Trusted by teams at

SKELARGenesis

Growth partners

8reachLoogo Labs

Funded by

UMAEF

Grant funding

Supported by

AWS ActivateMission Possible

Startup & accelerator support

Ask about customer references →
One platform, three jobs

The Agent does the work.

Free your team from repetitive requests. Keep judgment-heavy work with people.

Execute

AI Agent

Handle repeating requests with your knowledge, policies, flows and customer state. Answer the question, confirm an approved action, or hand off the reason and work so far.

Explore the Agent →

Check the work. Improve what comes next.

Scorecards · support QA

Judge human and AI conversations by one agreed quality standard. Tone, a correct and complete response, required actions and tags, and reply and follow-up timing combine into one result—so your team knows what needs attention.

We set it up together from your flows, policies and agreed criteria.

Explore Scorecards →

Analytics · find the cause

Find why customers keep asking, so your team can fix the guide, product or process behind the repeat requests.

Explore Analytics →

Inside Pronomy

Guide the agent. Check the work.

Your instructions, your voice, your quality standard. See how the pieces fit together.

Refund instruction proposal: confirm the payment result before promising completion.

How do I change what it says?

Describe the change. Review the steps.

Tell Pronomy what you want the agent to do differently. See the proposed instructions beside the steps that stay the same, then approve or decline.

Your request becomes a proposal you can inspect.

Review reply instructions before applying them. Routing and actions stay under your control.

Explore AI Agent →

When should a person take over?

Give the agent a path. And a clear handoff.

Build the steps, conditions and actions for a recurring request. In this delivery flow, the agent explains available tracking or passes missing tracking to a person.

Handle the expected path. Keep exceptions human.

Shown: the tracking and handoff steps from the delivery Canvas.

Explore the flow builder →

Can it sound like our team?

Your voice. In every reply.

Choose a starting tone, then add your brand’s voice instructions. Agent settings also give your team a place to manage languages and escalation rules.

Set the style instead of correcting every answer.

Shown: Friendly tone selected. Add brand-specific instructions in Agent settings.

Explore Agent settings →

Was that actually a good answer?

One quality standard. For people and AI.

Evaluate tone, response completeness, required actions and tags, and reply timing. See the criteria behind the result—not just a single score.

Check what was said against what happened.

See the assessment alongside the conversation and the action receipt.

Explore Scorecards →

What’s happening in support?

See the volume. Track the handoffs.

Choose a period and track interactions, human handoffs and system errors. Follow request volume over time to see where your team needs to look next.

Know what your support operation is handling.

A handoff can be the right outcome. No handoff alone does not mean a request was resolved.

Explore Analytics →
In the customer's words

Different requests.
The right next step.

An answer, a follow-up, an action or a person. Choose a request to see the difference.

Customer conversation#PRN-50340
CustomerHow do I export our project list? The guide shows a menu I don't have.
PronomyIt moved. Open Settings → Data → Export, choose Projects, then CSV. The older guide shows it under Account. Your plan already includes export; no upgrade needed.
Resolved
Answer foundThe customer has the steps for their version of the product.
See the checks behind this reply

What the agent checked

  • ✓Knowledge searched
    Current export guide
  • ✓Plan checked
    Project export included
  • ✓UI version checked
    New Settings layout
  • ✓Steps matched to this version
    Settings → Data → Export
  • ✓Old guide identified
    Outdated menu location
  • ✓Ticket tagged
    how-to · project-export

Scorecard

Tone of voice95
Right actions100
Right response97
Right timing100
What to investigateRepeated questions about the new Settings layout suggest a guide update.

Interactive walkthrough. Actions depend on your connected tools and approved flows.

How answers use your knowledge → · How refund rules work →

Works where you work

Keep your helpdesk.Pronomy meets your team where the work already happens.

Zendesk, Intercom and Slack are native integrations. Connect other systems through APIs, webhooks or MCP when the required access is available. We check each workflow’s permissions with you.

What connects, and how →

Pricing

Pay for resolved requests.

Scale
$0.33

per resolved request

With a monthly volume commitment agreed with you.

Launch
$0.39

per resolved request

Pay as you go. No monthly volume commitment.

A billable resolution4 of 4 required
  1. Request completed within policy.
  2. Every promised action confirmed.
  3. No human takeover.
  4. Agreed scorecard passed.

No seat fees. Scale also includes Analytics and Scorecards for AI conversations.

Calculate my cost →What counts as resolved?
From the founder

"I'm not going to sell you a chatbot. I'm going to take the five questions your team answers a thousand times a week, and actually solve them."

Oleksii Liaskovskyi, founder. Start with one recurring request your team knows well. We can work through where the software helps and where a person should stay involved.

Talk to Oleksii →Why we built this

Email Oleksii · LinkedIn

Straight answers

Fair questions.Answered by a person who has to stand behind them.

Will customers know they're talking to AI?
They should, and in many places the law says they must. We label the agent as AI by default and you choose how it introduces itself. We don't think hiding it is what makes support good. Fixing the problem is.
How do we control what the agent does?
You choose the knowledge, workflows and actions the agent can use. Set approval limits, review conversations in shadow mode and check the work log. Scorecards evaluate the conversation against your agreed rules. Your team decides what goes live.
How long until it's live?
It depends on the systems, permissions and flow involved. We connect the helpdesk first, map the rules with you, then run shadow mode before one approved flow goes live. Onboarding is free.
Do you train AI on our data?
No. Your customer data is never used to train models. A DPA is available before data access. Read exactly what we do.
Can I see a case study?
Not publicly yet. We don't publish a customer's name or results without written permission. Ask Oleksii what evidence is available for your use case today.
Bring one real ticket

Bring one real ticket.We’ll work through it together.

A switchboard operator at work, 1945
Switchboard operator, 1945. Different tools. Same obligation to answer the person.
  • 01You talk to Oleksii, the founder.
  • 02Bring your three worst flows. We'll tell you which ones we'd automate, and which ones we wouldn't.
  • 03Not a fit? You still leave with notes on those flows.
Book 20 minutes → Or write to us