From respondents to an explorable panel.
HDTwin turns a target definition into an explorable synthetic panel through four steps.
Build
Create your panel
Define the population you want to investigate or use existing research data to initialize and calibrate your Human Digital Twins.
Ask
Define the question
Describe the topic, decision, product, proposition or scenario you want the panel to explore.
Explore
Run the discussion
HDTwin orchestrates iterative surveys and simulated focus groups across the panel, combining structured questions with open-ended reasoning.
Understand
Analyse the results
Explore responses, reasoning, opinion groups, disagreements and areas of convergence.
Overview - all 18 nodes
Scrollable region 1200 × 880 viewBox. On narrow screens scroll horizontally (drag, or focus the region and use the arrow keys).
The process steps in detail
- Target definition — Names the audience the study is about before any data is collected.
- Panel definition — Defines the sample frame the virtual panel will represent.
- Interviews and surveys — Real interviews and surveys supply the field evidence.
- Personas and survey results — Typical profiles and aggregated results summarise the fieldwork.
- Latent Cognitive Model — A shared map of meanings that keeps answers comparable across agents.
- Aligned agents — Agents adjusted to the character of the panel they represent.
- Model review — Checks agent answers against the source material.
- Fit check — Flags answers that drift outside the source perimeter.
- Bias control — Controls model bias by adapting models to each agent's character.
- Topic — The question the panel is asked to discuss.
- Digital twins — The panel members take part as anonymous discussants.
- Questions — Each agent proposes positions and questions the others.
- Answers — Agents give reasons for the positions they hold.
- Consensus analysis — Shared positions are grouped so agreement can be inspected.
- Opinion groups — Opinion groups show where the panel agrees and disagrees.
- Human control group — A small human group answers the same questions.
- Answers — Human answers give a reference the panel can be checked against.
- Deviation analysis — Compares panel answers with the human reference over time.
30-minute online conversation; bring a current research question and available evidence; next step is a process mapping session.