Customer perspectives you can talk to.
Profiles built on selected source material. The Mosaic option has 600+ data points per profile. Your own data gives the perspectives local relevance.
Platform
Four layers. One workspace.
Customer profiles built on your own data, licensed segmentation data or both. Four expert agents help you choose perspectives, understand needs, test material and develop ideas in one shared workspace.
Your data, on top of the profiles.
Geography, CRM, campaign response and satisfaction studies can form the profiles’ foundation. If you also use segmentation data, your own data is layered on top.
Four expert agents, four verbs.
The Profile Selector, In-depth Interviewer, Focus Group Leader and Workshop Facilitator lead the processes. The profiles are the perspectives they engage.
Every conclusion, linked to its source.
Review a conclusion alongside the profile answers and the data points linked to them.
What Svava is built for
Built for customer understanding, alongside your existing tools.
Svava works alongside your CRM, marketing automation tools and analytics platforms. It specialises in exploring how customers think, react and make decisions before you act.
Svava helps you
Understand customers systematically.
- Explore and test positioning, messages and brand directions
- Review campaigns, sends and copy before they go live
- Reason with customer perspectives in strategy and innovation work
- Explore qualitative perspectives without recruiting respondents
- Make segmentation data accessible beyond the specialists
Outside Svava’s scope
A focused workspace.
- A general-purpose AI assistant or chatbot
- A replacement for CRM, marketing automation or analytics
- A replacement for real customer conversations; it helps you prepare for them
- A self-service tool purchased without a conversation
Platform
Five surfaces. One reasoning environment.
Everything happens within a project. Build audiences once and use them throughout the workflow, from the first question to the final synthesis.
Audience builder12 / 12
Amira
Johan
Lina
Sara
Erik
Anna
Per
+ 5
Build perspectives with real motivations.
Profiles built on your own data. Reuse the same profile source material across conversations to compare perspectives over time.
Message simulationIllustrative example · 04 reactions
“We are changing leadership, but not direction.”
Amira+78
Johan+42
Sara+88
Erik−31
Test ideas in minutes.
Paste a message, campaign line or full concept. Get structured reactions from each perspective: what they take in, what they object to and why.
Tension map2 conflicts
ChangeTraditionIndividualCollective
See where audiences diverge.
Place perspectives on axes you define. Conflict zones are highlighted to help you spot tensions before the campaign goes live.
Synthesis & decisionsIllustrative example · Confidence 0.82
Illustrative decision brief · Q3 campaignv.04 · example
01The message resonates with pragmatic parents (+82) but is misinterpreted by a younger urban audience.0.86
02Conflict 01: identity versus change. May prompt loyal customers to leave.0.74
03Recommendation: keep the message and add another layer for ages 27 to 35 in a secondary channel.0.81
Structured insights beyond a report.
The synthesis brings perspectives, reactions and tensions into a short decision brief. Each point is linked to the profile it came from.
Chrome extensionIllustrative example
Your own draftWhat might the profiles question?
SAsk the profiles what they see→
Your profiles, on any page.
Open a Figma file, your own draft, a landing page or a competitor’s site and ask the profiles what they see, what they question and what might influence their choice. Use the same profiles as elsewhere in Svava, alongside the material you are working on.
Experts & profiles
Experts who lead, profiles who participate.
Svava has two kinds of agents. Four expert agents lead the work and guide a process. Profiles are the data-grounded perspectives those processes engage. Choose an expert for your task, bring in the profiles you want to understand and explore the question.
| Verb | Expert | What it does |
|---|---|---|
| Select | ProfileSelector | Helps you choose profiles based on your business scenario, audience or research question. Starts with your need rather than a list. |
| Understand | In-depthInterviewer | Explores one profile in depth to examine attitudes, behaviours and needs. |
| Test | FocusGroup Leader | Leads a focus group with several profiles to explore different reactions and discuss a topic. You can upload material to test. |
| Co-create | WorkshopFacilitator | Facilitates creative workshops where new ideas are generated, evaluated and developed together with the profiles. |
Mosaic group H · Security-oriented families
Profile compass
Purchasing power0.62
Price focus0.78
Social responsiveness0.54
Digital curiosity0.34
Online shopping0.46
Sustainability values0.58
Channels · receptive to
Direct mailLocal mediaEmailSMSSocial media
Messages · resonate
SecurityFamilyLong-term thinkingFrugalityAspirationStatus
1.7×
over-indexing · house ownership
1.4×
over-indexing · gardening
0.6×
under-indexing · major cities
Compare a three-line persona with a perspective supported by 600+ data points behind it.
Tension map
Where customer groups diverge.
Audience analysis helps you explore where perspectives diverge. The tension map places profiles on axes you define and highlights conflict zones.
AspirationEveryday prioritiesPredictabilityControl
Anders
Lars
Maja
Sara
Erik
Ingrid
Strategic implication
No shared message territory.
The two quadrants containing your core groups do not overlap. A campaign that resonates with one may alienate the other.
Different messages may be needed to address these contrasting priorities.
Constructed example. The profiles are illustrative.
Traceability
Every conclusion, linked to its source.
Follow a conclusion back to the profile answers and the data points linked to them. Review the source material and assess which assumptions need further investigation.
A readable explanation, linked to source material.
For each profile answer, you can open a report showing which data points in the source material have been linked to the answer. This gives you a concrete starting point for reviewing the interpretation.
The report shows the connection to the source material. It does not reveal the model’s internal reasoning or prove that an interpretation or behavioural prediction is correct.
“Visible source material makes a conclusion reviewable. You assess what it supports and what needs to be tested with real customers.”
H
Mosaic group H
“For us, culture comes alive when we travel together, to a city in southern Europe, a museum or a market. But also at home around the kitchen table, discussing history or cooking the food we brought back.”
Traceability reportIllustrative example · 6 data points
Over-indexesHolidays abroad, a prominent travel pattern1.4×
Over-indexesCultural trips, self-directed activities beyond sunshine1.7×
InterestHistory, prominent in leisure surveysprominent
InterestFood culture, prominent in cooking habitsprominent
ValueFamily, central to the group’s self-descriptioncentral
Language choice“We” phrasing: the profile represents a Mosaic group rather than an individualstyle choice
Four data layers
An answer grounded in source material.
The AI model contributes language and reasoning capabilities. Profiles are grounded in your own customer data, licensed segmentation data or both. When both are used, your own data is layered on top of the segmentation data. What you supply in the conversation gives the question its context.
Layered on top ofgrounds the answer ↑
04Per question
What you supply
In the prompt or attached files: test material, briefs, documents, campaign lines and concepts.
03Per organisation
Your own data
Geography, CRM, campaign response, satisfaction studies, product ownership, behavioural data, support cases and qualitative interviews.
02Optional foundation
Segmentation data
An optional data foundation: currently Mosaic from InsightOne with 600+ data points per profile.
01General
The AI model
Language and reasoning capabilities. Knowledge acquired during training.
Source material gives profiles context.
The profiles’ source material can come from your own data or licensed segmentation data. When both are available, the layers are combined. A brief, draft or concept makes the conversation relevant to the question you are working on.
“How might Mosaic group H in a particular region react to this offer, given that they already use one of our services but not another?” rather than “What do our customers think in general?”
How your data is added
Layer 03, in practice.
The data layers explain how source material supports a profile answer. The next question is how your own data becomes part of it.
Your customer base, seen through the profiles.
With a Mosaic licence, individuals in your customer base can be classified. This helps you view your own customer base through the profiles rather than relying on a general audience description.
Enrichment starts with the home address.
Personal identity numbers are not required to enrich a customer base with Mosaic.
More than purchase data.
Surveys, insight reports, satisfaction studies, campaign responses and your own clusters can sit in the same layer. You can build on the work you have already done.
You do not need to be finished.
We help you assess which source material is enough to get started. More customer data can be added over time.
Layer 03 can grow as you work; it does not have to be complete before you start.
A closed system
The agents do not search the web. By design.
The agents do not search for new sources on the web during profile conversations. They work with the source material you supply. The AI model’s prior knowledge also contributes to the reasoning.
Defined sources, clear source material.
The supplied source material is limited to the profiles’ data and the material in the conversation. When you review a web page using the Chrome extension, the page is supplied as material; the agents do not search further on the web.
The traceability report shows which data points have been linked to an answer. You can review their relevance without mistaking this for full visibility into how the model arrived at its interpretation.
Defined source material makes it easier to review answers and formulate the next customer question.
The web
Svava’s system
Closed by design
AI modelSegmentation dataYour dataTest material
No web searchFrom personas to working methods
Customer perspectives you can review.
When using AI for customer understanding, you need to assess both the source material and how to use the results. Svava brings profiles, data and expert-led working methods into one environment.
Questions to ask
What do you need to assess?
- What source material are the profiles based on?
- Which sources are supplied in the conversation?
- How are answers linked to their source material?
- How do you compare customer perspectives?
- What needs to be confirmed with real customers?
Svava
A shared way of working.
- Profiles grounded in selected customer data
- Defined source material without web search during profile conversations
- A traceability report with data points linked to answers
- Four expert agents for selection, interviews, focus groups and workshops
- Perspectives and hypotheses to review and test further
You get more perspectives and a foundation for formulating better questions for the next customer test.
Apps
Recurring workflows, packaged.
Profiles, agents and tension maps are building blocks. For recurring work, ready-made apps take you from question to deliverable.
From brief to finished marketing automation material.
Selects profiles, runs in-depth interviews, generates email, SMS and push variants, and packages material for export to common marketing automation systems.
Daily signal monitoring.
Automatic daily monitoring of market signals relevant to your industry. An example of extending Svava with customer-specific monitoring apps.
Where results go
Insights go where the work already happens.
Export to your marketing automation system, share the synthesis in Slack or Notion, or bring the tension map to a strategy meeting. Svava feeds into your existing tools.
Dynamic profiles from real interviews
Read about Ciao Nova→When you want to build your own profiles from scratch.
For B2B, niche audiences or specific segments beyond the standard profiles, Ciao Nova builds your own profiles from real voice interviews. These can complement your existing profiles or provide their own foundation.
Book a demo
Book a demo. Bring a real question.
We build a first example together around a concrete question you are actually working on. 30 minutes. No sales deck.