ARISTOTLE BETA
An AI co-scientist built for researchers trained to question everything.
Role · Product Designer 0 → 1
Timeline · Oct 2025 - Feb 2026
Team · 2 designers + 3 engineers
THE CHALLENGE
Scientists don't trust AI. And they shouldn't have to.
Most AI tools are designed to make answers feel effortless. They return a polished response with little indication of how the answer was formed, how reliable the evidence is, or where the researcher should start questioning it.
That model works for everyday questions. Scientific research demands something different.
Researchers need to be able to:
See what the AI is doing.
Understand how it approached the question and what evidence shaped the response.
Question the answer.
Identify uncertainty, weak claims, and gaps instead of accepting a confident response at face value.
Work with rigor.
Move from an initial hypothesis to evidence, verification, and deeper investigation without leaving the research workflow.
The challenge wasn't simply making Aristotle more accurate.
It was designing an interface that made its intelligence inspectable.
THE DESIGN THESIS
Transparency is the product.
Instead of hiding Aristotle's complexity behind automation, we designed the interface around the ways researchers evaluate information themselves.
That meant giving researchers visibility into:
what Aristotle is doing
why it is doing it
how it reached an answer
and where they can challenge it
This became the principle behind the Beta experience.
WHERE WE STARTED
Just ask. Aristotle chooses the best model for you.
The first version of Aristotle was intentionally simple.
Every prompt was automatically routed across three models: Explore, Generate, and Verify.
There was no sidebar. No model picker. No visible reasoning layer.
The logic was straightforward:
And for simple questions, it worked.
And for simple questions, it worked.
But as Aristotle became capable of doing deeper research, the same simplicity became a limitation.
WHEN SIMPLICITY BROKE
A black box, for people trained to question everything.
Automatic model selection meant researchers couldn't see why Aristotle chose a particular approach.
When an answer felt wrong, there was little to interrogate.
At the same time, the product was gaining capabilities that couldn't comfortably live inside the original canvas:
Double Check needed room to surface verification.
Source previews needed space for evidence.
Reasoning traces needed somewhere researchers could inspect them.
Different research modes needed to become visible and understandable.
Putting everything directly into the conversation made the canvas increasingly noisy.
Two things had to change.
Researchers needed more control over how Aristotle approached a question.
And Aristotle needed a dedicated space for making its work visible.
DESIGNING FOR CONTROL
How much control should a researcher actually have?
As Aristotle became more capable, we had to rethink an assumption from the original experience: that hiding complexity would make AI easier to use.
Instead, I explored how much of Aristotle's underlying intelligence researchers should be able to see and control.
The exploration focused on two connected questions:
How should researchers choose how Aristotle approaches a question?
And how should Aristotle expose the work happening behind the answer?
MODEL CONTROL
01 — Let researchers choose the approach
One direction was to expose model selection directly.
Instead of automatically deciding which model to use, Aristotle could let researchers choose the approach based on what they were trying to accomplish.
This gave users more control, but it introduced a new problem:
Model names alone don't explain when or why someone should use them.
Simply exposing more controls wasn't enough. We needed to make the underlying capabilities understandable.
VERIFY EXPLORATION
02 — Make verification part of the interface
We also explored how Aristotle could expose the different ways it evaluates an answer.
Instead of treating verification as something that happens invisibly in the background, the interface could surface individual checks researchers might care about.
The challenge was information density.
Researchers needed access to this depth when they wanted it, but showing every capability inside the main conversation would make the experience harder to navigate.
INFORMATION ARCHITECTURE
03 — Where should the complexity live?
We explored keeping everything within the conversation itself, without a persistent sidebar or traditional navigation.
The advantage was simplicity: the researcher could focus entirely on the question and answer.
But as we introduced model controls, verification, sources, and reasoning, the conversation became responsible for too many jobs at once.
The interface needed another layer.
Not another screen.
Not another workflow.
A place for Aristotle's work to exist alongside the answer.
THE DESIGN DECISION
Move Aristotle's complexity out of the conversation.
Rather than continuing to add controls and verification states to the canvas, we introduced a persistent side panel for the work happening behind the answer.
The conversation remained the primary place to ask and explore.
The sidebar became the place to inspect and understand.
This created a clearer separation between:
THE ANSWER
What Aristotle is telling you.
THE WORK
How Aristotle got there.
THE EVIDENCE
What supports the answer.
FROM MODELS TO RESEARCH INTENT
Researchers don't think in models. They think in goals.
Giving researchers control over model selection created another UX problem: technical model names don't necessarily map to how researchers think about their work.
Instead of asking:
Which model do you want?
We reframed the choice around:
What are you trying to accomplish?
That became the foundation for Aristotle's four research modes.
SPARK
Generate and explore new ideas.
SEARCH
Find and synthesize relevant evidence.
VERIFY
Interrogate an answer and check its claims.
INSTANT
Get a fast response when depth isn't necessary.
The model became an implementation detail.
The research intent became the interface.