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.
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.
The engine your team runs on.
A team-facing AI assistant inside your helpdesk, and a Living Knowledge library that maintains itself from every accepted draft, override, and edit. Documentation ops drop to near-zero.
Feature 01 — Living Knowledge
A library that maintains itself.
Every source your business runs on - tickets, internal docs, Slack, Confluence, Google Drive, support recordings, websites - pulled into one self-maintaining library. Non-ambiguous. Always current.
Documentation ops drop to near-zero. The Library is what the Customer Agent answers from, what the Team Assistant drafts from, and what the Help Center is generated from - one source of truth, three surfaces.
The system
Three senses, running underneath every feature.
Three senses give the agent everything a human needs to hold a relationship with another human - what you know, who you're talking to, where they are.
01
Living Knowledge
What the agent knows. Your business, organised into one non-ambiguous Library - the same one that feeds the Help Center and the Team Assistant.
02
Living Memory
Who the agent is talking to. Preferences, history, sentiment, goals - private per customer.
03
Living Context
Where the agent is acting. CRM, billing, ERP, support tools, custom APIs - connected and aware.
Inbox
What to do, when.
You don't watch the dashboards. The Inbox watches them for you and surfaces what needs human judgment.
- If a signal fires
-
Take action.
A drop in usage, a retention risk, an upsell trigger - the Inbox routes the play to the right operator the moment the signal fires.
- If content needs your judgment
-
We tell you.
Knowledge conflicts, draft articles, tone rephrases - they queue up for one click of Accept or Deny. No content ops, no email chain.
- If your next maturity step is in reach
-
We point it out.
A cell on the AI-maturity matrix closes - Automated for Retention, AI-First for Acquisition - and the Inbox names what to ship next.
unless.com/en/dashboard/inbox
Today's briefing
6 messages · open · routed to you
-
Knowledge suggestion New article ready: "How to set up live chat triggers"
13:09 -
Save play queued Anna K. (Visma) — usage drop, day 12 of trial
11:42 -
Upsell signal Onguard · 14 seats in use of 10 included
09:15 -
Hand-off pending Tax & VAT — refund eligibility, policy unclear
13 May -
Procedure update Refund flow rewritten from 6 accepted overrides
12 May -
Knowledge suggestion Conflict detected: "Eligible regions" appears in 3 articles
11 May
The loop
Four phases that close it.
Each phase is its own dashboard. Train fills the library, Test rehearses every role before a customer sees it, Deploy ships behind one agent across every moment, Analyze proves the value - and feeds the next round of training.
01
Train
Your knowledge, always current. Your procedures, always ready.
02
Test
Every role, every skill, before a customer sees it.
03
Deploy
One agent. The whole journey. Memory across all of it.
04
Analyze
Performance. Value. Maturity. All visible. All live.
Most AI tools sell features. Unless sells a system that maintains itself.
Compliance
Built for regulated Europe.
EU data residency by default. No PII reaches model providers. Per-decision audit trail.
GDPR EU AI Act DORA
unless.com/en/dashboard/test/quality
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 |
unless.com/en/dashboard/deploy/retention
Retention
-
Churn risk language
ActiveCancellation intent, comparison shopping, escalating frustration in conversation.
28 live last 4m ago -
Pricing pushback
ActiveCustomer questions value, asks for discounts, or compares to competitor pricing.
14 live last 22m ago -
Reduced usage
ActiveLogin frequency or feature use drops below the customer’s 30-day baseline.
9 live last 1h ago -
Renewal approaching
ActiveContract end date within 60 days; surface renewal pricing and account health.
73 live last 8m ago -
Competitor mention
DraftNamed competitor referenced in a customer-facing exchange.
Not yet enabled - Add signal From library
unless.com/en/dashboard/deploy/support
unless.com/en/dashboard/trust/security
Security
Prompt injection prevention
- Enforce privilege control
- Validate user input
- Cleanse untrusted user input
Secure output handling
- Enforce strict validation for LLM responses
- Apply LLM output sanitization
Avoiding training data poisoning
- Anomaly detection
Denial of Service (DoS) prevention
- Limit context window
- Enforce API rate limit
Supply Chain Security
- Use Content Security Policy (CSP)
Sensitive information protection
- Apply data sanitization filters
- Limit external data access for the LLM
Secure Plugin Design
- Enforce parameterized inputs
- Apply plugin authentication
Limited Agency
- Enforce user approval for new action categories
Limited reliance on LLMs
- Enforce a disclaimer in all AI assistants
- Limit functional purpose of LLMs
unless.com/en/dashboard/inbox
Today's briefing
6 messages · open · routed to you
-
Knowledge suggestion New article ready: "How to set up live chat triggers"
13:09 -
Save play queued Anna K. (Visma) — usage drop, day 12 of trial
11:42 -
Upsell signal Onguard · 14 seats in use of 10 included
09:15 -
Hand-off pending Tax & VAT — refund eligibility, policy unclear
13 May -
Procedure update Refund flow rewritten from 6 accepted overrides
12 May -
Knowledge suggestion Conflict detected: "Eligible regions" appears in 3 articles
11 May
Frequently asked questions
What is the Engine?
UNLESS Engine is the platform side of Unless. It is the system the Customer Agent and the Team Assistant run on: three senses that ground the agent and four phases that close the loop. The Engine is what makes the agent learn on a loop instead of just answering one question at a time.
What are the three senses?
Living Knowledge, Living Memory, and Living Context. Living Knowledge is what the agent knows about your business - your tickets, docs, Slack, Confluence, Drive, recordings, all pulled into one non-ambiguous library. Living Memory is who the agent is talking to: preferences, history, sentiment, goals. Living Context is where the agent is acting: CRM, billing, ERP, support tools, custom APIs.
What are the four phases of the loop?
Train, Test, Deploy, Analyze. Train turns your content into Living Knowledge and Living Context. Test previews every role and simulates every skill before a customer sees it. Deploy puts the agent in front of customers across all four moments. Analyze closes the loop with performance, business value, and AI maturity, then feeds Train.
What does Train do?
Train builds Living Knowledge and Living Context from the sources you already have. Help center articles, ticket logs, product docs, Slack channels, recordings, CRM fields - all of it pulled into one library the agent can read without ambiguity. You stop maintaining duplicate content ops; the system maintains itself.
What does Test do?
Test lets you preview every role, simulate every skill, and audit every decision before a customer or auditor ever sees it. Run a control set of questions, replay real conversations, and read the audit trail in plain language. Your DPO and your auditor see the same thing you do.
What does Deploy do?
Deploy puts one agent in front of customers across all four moments. The agent carries Living Memory and Living Context from one moment to the next, so a visitor who became a customer never has to introduce themselves again. No cold opens, no four separate bots.
What does Analyze show?
Analyze shows performance, business value, and AI maturity in one view. You can see deflection, resolution time, CSAT, and revenue impact by moment, by topic, and by segment. The same dashboard tells your CFO and your DPO what they each need to hear, with the numbers backed by the audit trail.
What is the Team Assistant?
The Team Assistant is the team-facing side of the agent. It works inside the helpdesk your team already uses, drafts replies, summarizes accounts, and surfaces the next-best action. Every accepted draft, edit, and override feeds Living Knowledge back, so the loop tightens with every ticket.
How does Living Knowledge stay current?
Living Knowledge maintains itself. It re-reads the sources you connected, picks up new tickets and conversations as your team handles them, and rewrites or restructures content when the underlying truth changes. Documentation ops drop to near-zero. Nobody is paid to keep a wiki tidy anymore.
Which AI models does Unless use?
Unless runs a constellation of models from providers like Mistral, OpenAI, Google, and Anthropic, rather than betting the platform on one. The constellation lets us pick the right model for the job and switch quickly if regulation or vendor terms change. Customer data is never used to train public models.
See the loop in your data.
Walk the same four phases with your own knowledge, your own customers, your own numbers.