Agentic Worflows·Automotive · Synthetic Personas

Synthetic Users
for GEO

Transforming customer research to simulate car buying behaviour

An agentic research framework that builds brand-neutral synthetic personas and a large prompt catalogue.

AI Research · Generative Engine Optimisation
Aerial tilt-shift view of a city intersection with cars, crossings and autumn trees
01 / The Problem

LLMs are changing how people discover and evaluate brands.

People now ask large language models to research, compare and choose vehicles. In that shift, a brand that is not surfaced by AI is absent from the decision long before a dealer visit or a search result click.

Brands that are not referenced, cited, or selected by AI platforms effectively cease to exist in the eyes of users.

SEO → climb the rankings GEO → join the conversation
The question is no longer where you rank — it's whether you're part of the generated answer at all.
Abstract collage — a halftone face fragmented across geometric panels, an eye motif and small figures

AI discovery is early-stage influence

Users are forming a shortlist inside conversational systems.

Visibility is conversational

Is the brand is cited and recommended in generated answers?

Measurement becomes behavioural

Evaluation requires archetypes rather than individual representations.

02 / The Challenge

From Insights to Value

Convert fragmented qualitative research into a defensible behavioural framework capable of producing thousands of vehicle-purchase queries for large-scale GEO analysis across brands and customer journey stages.

AI Transformation

Research was abundant but not operational for agentic frameworks.

Ethics & Compliance

Abstraction of first hand customer data to meet compliance constrains.

Context
Awareness

Users prompt differently in different phases of the customer journey.

Customer's
Tone of voice

Linguistic synthetic dataset capturing how different customer segments naturally ask questions.

03 / The Solution

An agentic synthetic user framework

The system translated qualitative research into synthetic users, generated prompts by journey phase, validated them, and handed the catalogue into GEO workflows for large-scale brand visibility measurement.

01

Research Analysis

Extract, normalize and abstract customer evidence from studies, interviews, workshops and repository material.

02

Synthetic Personas

Model behaviour-rich personas with enough context, language and motivation to simulate buyer decision-making.

03

Prompt Generation

Create a catalogue mapped to customer journey phases, emotional drivers and varying levels of purchase intent.

04

Human in the Loop

Experts review prompts for neutrality, duplication, coverage, language consistency and approving before scale.

05

Handover

Translate the outputs into a practical instrument for the GEO team.

04 / Systems Design

From Single Agent
To Multi Agent Orchestration

Five architectural decisions transformed qualitative research into a scalable agentic workflow while preserving behavioural fidelity.

05 / Context Aware

Modular prompts adapt to where the buyer is in the journey,
not just who they are

Collage of three layered profile portraits with halftone textures and geometric shapes
01
CTX
Knowledge level

Prompt depth adjusts to novice, intermediate or expert familiarity with vehicles and EV topics.

02
CTX
Journey phase

Discovery, consideration, decision and transaction each trigger very different prompting behaviour.

03
CTX
Emotional driver

Status, sustainability, reassurance or excitement shape the prompt wording as much as the topic itself.

04
CTX
Brand neutrality

Proprietary shorthand is removed so the catalogue can measure visibility fairly across competing brands.

06 / Business Outcomes

A stronger foundation

GEO had a grounded starting point.

The team received a prompt catalogue rooted in first-hand OEM research rather than abstract AI assumptions.

Research became operational.

A fragmented repository became usable input for GenAI and agentic workflows, not just reference material for slide decks.

The project created internal momentum.

Leaders could see how research and marketing intersect in AI discovery and why investing in research infrastructure matters.

Time-to-market improved.

The method showed how AI research operations can accelerate delivery without abandoning rigour, compliance or human review.

80%grounded
60% First-hand user data
20% Research studies & benchmarks
20% Synthetic enrichment

The bigger outcome was cultural. This shifted the conversation from reporting insights to operationalizing research for AI systems.

07 / Technical Stack & Lessons

A practical stack,
then five lessons

The stack was deliberately lightweight. The hard part was judgment: choosing data, structuring context, neutralizing bias and validating outputs before scale.

Research

Behavioural evidence

Grounded the personas in observed customer behaviour.

Configuration

YAML structures

Persona memory, taxonomies and prompt templates were stored in files that improved through iteration.

Orchestration

CrewAI + Azure OpenAI

Micro-agent workflows handled extraction, generation and validation while keeping the human reviewer in the loop.

Isometric collage of layered data — exploded stack of pages, slabs and blocks
01

Choose the data

Be critical with the material at hand and keep the signal tied to real behaviour, not just available documents.

02

Context data for LLMs

Highly descriptive, diverse material gives models enough context to infer intent with greater consistency.

03

Neutralize and anonymize

Plan time, compliance and brand fairness often require manual modeling work.

04

Use the right framework

Different agent architectures suit different phases of the research journey. Matching method to task lowers drift.

05

Validate qualitative output

Analytical checks, expert review and human judgment remain essential before any synthetic output can be trusted.

The innovation lies in bridging human insight with data-driven orchestration

Client identity and proprietary figures abstracted for confidentiality