Prompt injection prevention
- Enforce privilege control
- Validate user input
- Cleanse untrusted user input
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.
Features
Data and privacy
Find out how we deal with privacy when you visit our website or when you and your users interact with our platform.
GDPR EU AI Act DORA OWASP AWS Well-Architected
Here for the first time?
Find out how we deal with privacy when you visit our website or use our applications as a visitor, and how we deal with cookies in our system.
Read more
For our customers
Read our terms and conditions, find the Data Processing Addendum, a security addendum, and other privacy resources.
Read more
General compliance
For our code of conduct and compliance controls, check out this section.
Read more
Trust is our number one concern
Privacy protection overview
As a quick introduction, here are some of the key concepts that we handle when dealing with privacy.
- Cookieless by default.
- By default, our system doesn't use cookies. However, for audience segmentation, personalization, and A/B testing, cookies may be required. In that case, you should connect your consent mechanism to our Consent API.
- Separation of personal data and system data.
- By default, Unless filters all Personally Identifiable Data from user input and AI training data. However, after consent or with legitimate interest, some customers may submit third-party data. We store this data in Europe only, in a protected "privacy vault".
- Privacy vault.
- Our data privacy vault technology isolates, protects, and governs sensitive customer data. Tokenization replaces sensitive data with tokens, providing an extra layer of security. Sensitive data is stored in the vault, while de-identified data is used in other cloud storage and downstream services like the AI models.
unless.com/en/dashboard/trust/security
Security
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
Frequently asked questions
How does Unless protect customer data?
UNLESS keeps every personal record for EU and EEA end users inside EU infrastructure. Data is encrypted in transit and at rest, access is role-based, and sensitive identifiers stay in the Privacy Vault. You decide which fields the agent can see at each moment, and you can change that decision at any time.
How does Unless help us meet GDPR, DORA, and the EU AI Act?
Unless is configurable for the requirements of GDPR, DORA, ISO 42001, EU AI Act, and entities supervised by BaFin and AFM. EU data residency, per-decision audit trails, and model controls are built into the architecture. You can demonstrate control over training data, agent behavior, and risk mitigation without bolting on a second tool.
Is our data ever used to train public models?
No. Customer data is not used to train any public model. Prompts and outputs go through model providers under contracts that forbid reuse for general training. Your Living Knowledge stays your Living Knowledge.
What is the Privacy Vault?
The Privacy Vault is the data-protection layer at the edge of Unless. Sensitive identifiers - names, emails, account numbers, anything that could re-identify a person - are tokenized at the boundary and only de-tokenized when an authorized component needs them. Model providers never see the raw values.
Who controls which data the agent can access?
You do. Source selection, topic-level separation, audience rules, and role-based access are all configured in the dashboard. You can grant the Acquisition agent access to product docs but not to billing, and the Support agent access to tickets but not to internal Slack.
How do we run a security or DPIA review of Unless?
We provide a security addendum, DPIA inputs, sub-processor list, data flow diagrams, and a description of technical and organizational measures. Your security, risk, and compliance teams can run a full review before a single customer sees the agent. Most reviews close inside two weeks.
We're here to help
Quick responses if you have an issue. Feel free to ask us anything — or ask our conversational AI a question.