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.

Test

Quality reports

Version 1.0 · Last updated 2026-05-27

Curated set of control questions and the answers you expect. Quality reports run the questions against the agent and score each answer.

Anecdotes tell you the agent is doing well or doing badly. Numbers tell you whether it is getting better or worse. Quality reports give you the numbers, with the same questions every time, so improvement is measurable.

Key concepts

Control questions

Questions you would expect any customer to ask, with the answer you would expect the agent to give. Build the list once, run it many times.

Control answers

The expected answers. Used as the benchmark when scoring.

Report runs

Each time you generate a report, the agent runs every control question. Scores compare each answer to the control answer.

Report score

Average of all question scores. Useful as a quick health indicator over time.

Per-question score

The signal you actually act on. Low-scoring questions point straight at the Source that needs work.

What you can do here

  • Add control questions, manually or pulled from top questions in Analyze
  • Set the expected answer for each question
  • Run a report and view per-question scores
  • Compare reports over time to track quality trends
  • Inspect which Sources the agent used for a low-scoring answer

When to use it

  • After any change to Living Knowledge, to confirm scores held or improved
  • On a weekly cadence, as a regular health check
  • Before showing the agent’s results to leadership or auditors

How it works

Each control question runs against the live agent. Scores compare the generated answer to the control answer using semantic similarity, not exact match. Small differences in wording get high scores. Real disagreements get low scores.

Frequently asked questions

How do I add a control question?

Open "Test > Quality reports > Control questions" and click "Add". Enter the question, the expected answer, and optionally a topic.

How do I pull questions from real customer activity?

Open "Analyze > Performance" and look at the top common questions. Click the plus icon next to a question to add it to your control set.

How do I run a report?

Open "Test > Quality reports > Reports" and click "Run report". The report appears in the list when it finishes.

What does a low score mean?

The agent's answer disagreed substantially with the control answer. Open the question to see the agent's answer, the Sources it used, and the control answer side by side.

How do I improve a low score?

Find the Source the agent used. Either fix that Source, add a new Source that has the right information, or update the control answer if the agent was actually correct.

How often should I run reports?

Once a week as a baseline. Plus on demand after any major change.

Simulations
Moments