From Mental Model to Graph: Building the Fundamentals of a Central Customer-Intelligence System

From Mental Model to Graph: Building the Fundamentals of a Central Customer-Intelligence System

What single factor most improves marketing (resonance) and product development (relevance)?

A holistic understanding of customers—functional and emotional progress in context (journey phases, triggers, constraints, habits). If we could capture qualitative customer research in a way that any team can query on demand, we’d ship better ideas faster.

What if those qualitative insights lived in a graph—and everyone could access them, as connected evidence, anytime?


1) The origin: a mental model of “customer progress”

In marketing & innovation work we used a board called The Wheel of Progress®—a practical way to map interviews to forces and outcomes (pushes, pulls, pains, anxieties, habits, trigger events, jobs-to-be-done, desired outcomes, gains…).

This mental model matured into the 12 Elements of Customer Progress Design®: a domain language for how customers make progress over time.


2) From mental model → data model

We formalized the 12 Elements with clear definitions, syntax, and allowed relations. Early on, we created partially connected nodes “by hand” to learn the shape of the data (what belongs where, and why).

That schema became our ontology for customer progress:

  • Node labels: e.g. JTBD, Pain, Pull, DesiredOutcome etc.

  • Relationship types (directed, typed): CAUSES, HINDERS, etc.

We attach evidence to everything:

  • source_id, case_id, etc.

3) Into Neo4j: schema, triples & import

Once the language stabilized, we automated extraction from interviews (GenAI-assisted classification → human verification), produced probable triples, and imported to Neo4j.

4) Why a graph? Because customer reality is relational

The value appears when you traverse motifs like:

Pain → Push → First Thought → ActiveSearch

These paths are explanations you can hand to humans and machines.


5) What we can do now (Graph → GenAI → output)

Because the graph already encodes who, what, why, when (with evidence), we can prompt GenAI with directed, typed, evidence-weighted paths instead of vague personas or scattered bullet points. This is a huge feature of using LPGs- the right (connected) data at the right time.

  • Persona maps (derived from evidence, not invented): Cluster by motifs and phases; produce on-demand summaries that stay linked to sources.

  • Marketing messaging: Generate headlines, CTAs, and narratives that explicitly address high-weight Push→Pain→JTBD→DesiredOutcome→Solution chains.

  • Innovation ideas: Ask for features that relieve a Constraint and enable a DesiredOutcome, with acceptance criteria and likely trade-offs.

  • Sales enablement: Objection handling from Anxiety/Habit HINDERS Solution edges, with counter-stories anchored in real cases.

This “graph-first” RAG approach increases precision, reduces hallucination, and keeps explainability (“why did the model say that?” → follow the path).


6) What surprised us

  • We consistently see fewer iterations and higher first-draft relevance when prompts carry paths + evidence weights (vs. text chunks alone).

  • Teams align faster because the graph encodes shared language + provenance.

  • Unstructured qualitative data—once trapped in presentation decks—becomes a living, queryable asset.


7) What’s next

  • Stronger evidence pipelines.

  • More automated motif detection.

  • Fine-tuning graph-aware RAG


Why share this here?

We moved from a domain mental modeldata modelontology/schemamachine-linked graphtriple import and now use Neo4j to power customer-intelligent outputs with GenAI. It’s a pragmatic pattern you can reproduce in other domains where qualitative context matters.

We are still in an early stage but one thing is clear already: applying graph technology/Neo4j is a game-changer for us.

Thanks for reading—and thanks to the Neo4j community for pushing graph thinking where it has the most human impact: making better decisions, faster, with real customer reality.

Thank you for sharing your approach. What inspired you specifically to create this? Is this for a specific use case that you would be able to share with us. I love hearing about how we are truly a game changer :slight_smile:

Ari, Thanks for asking.

The idea to put our data into a graph came from a business acquaintance who is a graph expert. She wanted to do a demo for a customer, a financial institution with qualitative customer research information.

My contact claimed the bank had “TBs of qualitative data”. This type of data is typically not stored in a graph. Most of it is in audio files, transcripts, PowerPoints, digital whiteboards and in people’s heads.

A couple of months ago, I started to build a process using real qualitative data to build triples and equip them with properties and then imported them into Neo4j. This experiment was not an easy one but more than worthwhile. It showed the potential to put qualitative data in a graph.

As I said, we’ve used our data mainly on posters and on digital whiteboards. Here is a picture of our end-to-end process on our Mural process template. We typically collect 100-130 items from a customer interview. This adds up to a lot of data to document, aggregate and process. Every sticky note is a datapoint.

Not only was storing the data points as nodes was helpful but creating relation between them. What we did partially manually (assigning a pain or gain to a job-to-be-done) can now be automated in an external process.

This new capability is another game-changer as it makes previously invisible connections visible and allows users to find causality in buying decisions and use these insights to build GenAI prompts grounded in customer reality. We are super impressed by the results from creating marketing campaigns to generating product ideas based on the data. There are many more advantages which I haven’t even touched on.

This feels like a breakthrough in customer-intelligence to us with the potential of causing transformative 2nd order effects of AI.

Best,
Eckhart

1 Like

See also New Use Case: Customer-Intelligence Graphs for Strategic Decision-Making

very cool - I did go to your site.

1 Like