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.

Train

Knowledge base

Sources Content library Help Center

Version 1.0 · Last updated 2026-05-27

Inputs that feed Living Knowledge. Website pages, FAQs, files, and content pulled in through integrations.

The Customer Agent is only as good as the Sources it can read. Quality and structure of Sources drive the quality of every answer the agent gives. Spend time here and the rest of the loop pays back.

Key concepts

Source types

The Knowledge base ingests pretty much anything your business already runs on. The main categories:

  • Website pages. Crawl a full site through sitemap.xml or add individual URLs. Include and exclude rules narrow the scope.

  • FAQ entries. Question-and-answer pairs you write directly or import as CSV. Best for content that does not already live on a page.

  • Files. PDF, DOCX, Markdown, CSV, and Google Drive files. Structure matters more than length: clear headings, short paragraphs, no dense tables.

  • Helpdesk content. Tickets and articles pulled directly from Zendesk, Freshdesk, Jira Service Management, Zoho Desk, and similar. Keeps Living Knowledge in sync with the support content your team already maintains.

  • Knowledge bases. Confluence, Google Drive, BookStack, Zenya, ClickHelp, Azure DevOps Wiki, WordPress, and similar.

  • Team collaboration. Support tickets and developer merge requests can feed Living Knowledge for cases where the most accurate institutional knowledge lives there.

  • MCP servers and custom connectors. For internal systems on a custom protocol. See Living Context.

Topics

Optional grouping that scopes Sources to a specific product, audience, or use case. The agent then answers using one topic at a time, preventing cross-product mix-ups.

Quality score

Indicator next to each Source showing how well it reads for the agent. Sort by Quality score from low to high and start with the worst.

Content optimizer

Add-on that improves Source formatting (chunking, headings) without changing the original content. Your account manager can enable it on request.

What you can do here

  • Add Sources from websites, FAQs, files, and integrations
  • Organize Sources into topics
  • Inspect indexed content to see exactly what the agent reads
  • Use the Quality score to find and improve weak Sources
  • Exclude documents, pages, or sections that should not feed the agent

When to use it

  • You are setting up Living Knowledge for the first time
  • You added new product documentation and want the agent to know about it
  • Customer feedback shows the agent is answering with stale or wrong information
  • You are expanding to a new product and need a new topic

When not to use it

  • You are looking for structured content like a product catalog. That belongs in the Content library.
  • You want to publish customer-facing help articles. The Help Center builds those for you.

How it works

Each Source you add gets scanned and indexed. The agent retrieves relevant chunks at conversation time and uses them to ground its answer. Retraining happens automatically when content changes, or manually when you trigger it.

User-generated content (community forums, old support tickets) is a poor Source. It carries noise and outdated context. Skip it.

Frequently asked questions

How do I add a website as a Source?

Open Train > Knowledge base > Sources, click Import sources, pick Website pages, and paste the URL or sitemap. Add include or exclude paths to skip outdated sections.

How do I improve a Source's Quality score?

Sort Sources by Quality. Click View content on a low-scoring Source. Fix the structure in the original (headings, short paragraphs, no dense tables) and retrain.

How do I import many FAQs at once?

Export your current FAQs as CSV from the Sources page. Edit the file with new rows for new entries. Rows with empty ID become new entries; rows with an existing ID get updated.

How do I keep Sources separate for two products?

Use topics. Create a topic per product, add the relevant Sources, and connect the topic to the component or starter button that the right customers see.

How do I see what the agent actually sees from a Source?

Open the Source's actions menu and pick Show indexed items. Click any item to view the exact content as the agent reads it. Useful for troubleshooting wrong answers.

Why is my newly added Source not being used?

Check three things. First, the Source is finished scanning. Second, it has a usable Quality score. Third, the topic or component the customer hit actually includes this Source.

Implementation
Knowledge base · Content library