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.
Qualify, convert, educate. 24/7 on your marketing site.
See churn coming. Act before it does, inside the customer's product.
Catch upsell signals early. Route them to the right owner.
Resolve, co-pilot, learn — across every helpdesk and channel.
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.
Twelve numbered measures keep sensitive identifiers home.
Three pillars — sovereignty, AI Act readiness, sector readiness.
Five EU-resident layers — touchpoints to LLM constellation.
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.
Norway's leading ERP — modernized self-service with Unless.
Patient self-service surged within weeks of deploying Unless.
Financial service Onguard powers their support operations with Unless.
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.
Get-started guides and advanced playbooks for the platform.
Privacy measures, security by design, and compliance guidelines.
Find reference documentation for the javascript API.
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.
Flex (€0.99 per outcome) or Fixed (€1,999/month). Equal weight.
Full platform on both — Living Knowledge, Memory, Context.
Productized add-ons. À la carte on Flex, bundled into Fixed.
What counts as an outcome, fair use, and switching mid-year.
Why Test
The wrong answer should never reach a real customer.
Most AI gets shipped without a way to audit it. The wrong answer reaches a real customer before anyone notices. Test changes the order. Every role, every skill, every language gets previewed and simulated against synthetic users first. Your auditor reads the trail. So do you.
How Test works
Preview, simulate, audit. Repeat.
01
Preview the role.
See what the agent will say, in every language, before you ship it.
02
Simulate the skill.
Run agentic skills against synthetic users to confirm they behave as defined. Catch the wrong answer before a real customer hears it.
03
Audit the decision.
Per-interaction trail with timestamp, decision path, model used, and source citation. Your auditor can read it. So can you.
Test before you ship. Audit after you ship. Stay in control either way.
Inside Test
Every answer points back to its source.
Read the decision behind any interaction in seconds. Source citation, decision path, model used, timestamp. The trail your regulator wants is ready before they ask.
Quality reports
| Report | Score | Passed | Actions |
|---|---|---|---|
| May 7, 2026 9:56 AM | 76% | 22 out of 29 | open report |
| May 7, 2026 9:52 AM | 21% | 6 out of 29 | open report |
| May 7, 2026 9:20 AM | 0% | 0 out of 29 | open report |
| May 6, 2026 6:14 PM | 72% | 21 out of 29 | open report |
| May 5, 2026 4:02 PM | 69% | 20 out of 29 | open report |
Next in the loop
Deploy
One agent. The whole journey. Memory across all of it.
Audit before your auditor does.
Preview every role. Simulate every skill. Read the trail before a customer ever sees it.