Seldon - Model what happens next
Model what happens next.
Seldon is an applied research lab building models that reflect how reasoning, emotion, experience and social influence shape our decisions. Our ambition is to establish a new standard for modeling human behavior.
Book a demo How it works
Personality, Goals & motivations, Beliefs & expectations, Emotions & attention, Environment & context, Experience & memory
- Personality
- Goals & motivations
- Beliefs & expectations
- Emotions & attention
- Environment & context
- Experience & memory
How it works
Test before it happens
- A user abandoning checkout
- A critical bug reaching production
- A decision under pressure
- A strategy challenged by changing conditions
Seldon models how people behave
Agents bring different goals, information and experience to a situation. Follow what they encounter, the choices they make, and what happens next.
A user abandoning checkout
- Behavior: A customer struggles to find delivery information, grows frustrated and leaves without completing their purchase.
A critical bug reaching production
- Failure: An agent edits their cart during checkout, triggering an unexpected error in the order total.
A decision in an uncertain environment
- Decision: Faced with incomplete information and competing priorities, an actor weighs their options and chooses a course of action.
How you adapt to changing conditions
- Adaptation: New intelligence changes an actor's assessment, prompting a shift in strategy.
So you can learn…
See where trajectories diverge. Inspect the evidence. Decide what to investigate or change.
- what drives different outcomes
- where people encounter friction
- where software breaks
- how strategies hold up under pressure
Agents shaped by their world.
Personality, beliefs and past experience shape how people make decisions. Seldon's agents carry these influences into the choices they make.
Their goals, the information available to them and the people around them also matter. Change who an agent represents or the situation they face to explore how their choices change.
Sofia L.
- Takes time to decide
- Risk tolerance: Low
- Decision speed: Deliberate
- Response to uncertainty: High
- Social influence: Low
- Cognitive flexibility: High
- Belief: Trust is earned through evidence, not authority
- Current situation: Facing an unfamiliar decision with incomplete information and competing advice.
Maya R.
- Seeks certainty
- Risk tolerance: Low
- Decision speed: Deliberate
- Loss aversion: High
- Need for certainty: High
- Social influence: High
- Belief: It's better to be certain than to be first
- Current situation: Facing an unfamiliar decision with incomplete information and conflicting advice
Devin K.
- Comfortable taking risks
- Risk tolerance: High
- Decision speed: Fast
- Novelty seeking: High
- Social influence: Low
- Response to uncertainty: Exploratory
- Belief: The best way to learn is to try
- Current situation: Facing an unfamiliar decision with incomplete information and conflicting advice.
How closely does a simulation reflect real behavior?
We evaluate our models against observed human behaviour, studying where decisions align, where they diverge, and how people and agents respond to changing circumstances. By measuring these differences, we can understand where simulation succeeds, and where there are limitations.
What Behavioral Fidelity Actually Means - And Why It Matters
Behavioral simulation only becomes useful when it faithfully reproduces how real people make decisions. Behavioral fidelity is the measure of that trust.