Skip to content

Agent

One agent. Every customer moment.

The customer-facing side of Unless — one AI Customer Agent across acquisition, retention, expansion, and support, with the Help Center it auto-generates as its public face. Browse a moment, or see the full overview.
Acquisition

Qualify, convert, educate. 24/7 on your marketing site.

Retention

See churn coming. Act before it does, inside the customer's product.

Expansion

Catch upsell signals early. Route them to the right owner.

Support

Resolve, co-pilot, learn — across every helpdesk and channel.

Engine

The platform underneath.

The back-of-house side of Unless — a Living Knowledge library that maintains itself, plus the Train → Test → Deploy → Analyze loop that keeps every Customer Agent sharper after every conversation. See how the engine compounds.
Train

Always current. Always ready. Living Knowledge + Living Context.

Test

Before a customer sees it. Preview, simulate, audit.

Deploy

One agent. The whole journey. Memory across all of it.

Analyze

Performance, value, AI maturity. All visible. All live.

Trust

Built for the EU from day one

The architecture that lets your DPO, security, and procurement teams sign off without slowing your team down. Browse the page, or jump straight to a section.
Privacy Vault

Twelve numbered measures keep sensitive identifiers home.

Compliance posture

Three pillars — sovereignty, AI Act readiness, sector readiness.

Architecture

Five EU-resident layers — touchpoints to LLM constellation.

Frameworks

EU AI Act, GDPR, DORA, OWASP — built into the platform, not bolted on.

Customers

Trusted by leaders

How regulated-Europe brands — from Visma to Onguard — turned customer success into a revenue engine with Unless.
Visma Enterprise AS

Norway's leading ERP — modernized self-service with Unless.

Helping patients

Patient self-service surged within weeks of deploying Unless.

Enhancing credit software

Financial service Onguard powers their support operations with Unless.

Ticket deflection at scale

Meet Sally, Kontek’s AI support colleague in regulated finance.

Resources

Search resources and support articles

Documentation, articles, and recipes for getting the most out of your Unless deployment — plus a help desk when you need a human.
Help center

Get-started guides and advanced playbooks for the platform.

Security and compliance

Privacy measures, security by design, and compliance guidelines.

Developer documentation

Find reference documentation for the javascript API.

The Unless cookbook

Bite-sized examples for every stage of the customer lifecycle.

Pricing

Pay per outcome. You choose.

Two equal-weight plans, both built around outcomes. Browse the page, or jump straight to a section.
The two plans

Flex (€0.99 per outcome) or Fixed (€1,999/month). Equal weight.

What's included

Full platform on both — Living Knowledge, Memory, Context.

Flex modules

Productized add-ons. À la carte on Flex, bundled into Fixed.

Frequently asked

What counts as an outcome, fair use, and switching mid-year.

Analyze

Conversations

Version 1.0 · Last updated 2026-05-27

Conversation log with the Customer Agent. Filter, inspect, flag, and feed insights back into Living Knowledge.

Aggregate metrics tell you what is happening. Individual conversations tell you why. Conversations are where you go when Performance shows a number you do not like and you need to find the cause.

Key concepts

List view

Conversations from the last 30 days by default, with date, response count, customer rating, and status. Filter by rating, length, Moment, surface, or Audience.

Detail view

Full transcript of one conversation. Each agent answer shows Sources used and any thumbs feedback. Procedure runs and Signal triggers are visible.

Flagging

Mark a conversation for team review, or report a suspected bug to the Unless team. Add a note for context.

Add to Quality reports

Promote a question from a real conversation into your Quality reports control set. One click.

What you can do here

  • Filter conversations across Moments, surfaces, and Audiences
  • Open any conversation to read the full transcript
  • See which Sources the agent used for each answer
  • Flag conversations for team review
  • Promote a question into Quality reports
  • Export conversation data for offline analysis

When to use it

  • Performance metrics moved unexpectedly and you need to find the cause
  • A customer complained about an agent answer and you want to read what happened
  • You are building your Quality reports control set from real questions
  • You are auditing the agent’s behavior for a compliance review

How it works

Every conversation is logged in full with every answer, every Source used, every Procedure run, every Signal triggered. Logs feed Analyze but also serve as the audit trail for Accountability.

Frequently asked questions

How do I find conversations with negative feedback?

Open "Analyze > Conversations" and filter by rating. Negative-rated conversations are the most useful place to start improvements.

How do I see which Sources the agent used in a conversation?

Open the conversation detail view. Each agent answer lists the Sources it pulled from. Click any Source to inspect it.

How do I promote a question into Quality reports?

On any conversation, click "Add to Quality reports" on a specific question. Edit the question and the control answer, then save.

How do I report a suspected bug?

Flag the conversation as a bug and add a note. The flag goes to your dashboard and optionally to Unless support.

Can I export raw conversation data?

Yes. Use the export button on the Conversations view. CSV includes timestamps, transcripts, ratings, Sources, and Procedures.

How long are conversations stored?

Retention depends on your settings. Defaults follow GDPR data minimization - currently 365 days.

Performance
Business impact · Cost reduction