Human-AI Interaction
UT Austin
UX Research
AI ideation tools are built to feel effortless, and people stop thinking critically when they use them. We built an ideation tool with two deliberate kinds of friction, then ran a within-subjects study to test whether friction brings back deliberate thinking and a sense of ownership over ideas.
AI ideation tools compete on removing effort but when the thing you are making is an idea, the effort is the work. People take the first polished answer and stop thinking and people feel little ownership of the result.
Designed the interface and the turn structure for an ideation tool with two kinds of deliberate friction built in. One makes you assemble the idea yourself. The other argues with you. Then we tested both against a plain chatbot.
Fast, automatic thinking fell from 79% to 42%. Four of five people quit the plain chatbot before it was finished. Only one of the two friction mechanisms also made people feel the idea was theirs.
The Problem
Human + AI teams often out-produce people working alone or in groups. They generate more ideas and more variation (Holzner et al. 2025; Kim & Maher 2023). But a growing body of work shows a cost on the human side. People take up AI ideas passively, put in less cognitive effort, and transform suggestions less often and less inventively (Boers et al. 2025).
We framed this through the dual process model of cognition (Evans 2003; Kahneman 2011). System 1 thinking is fast, associative and automatic. System 2 thinking is slow, effortful and rule-based. Creative work needs both: generative processes to produce ideas and evaluative processes to refine them (Sowden, Pringle & Gabora 2019). AI-assisted ideation has been shown to be System 1 dominant (Wadinambiarachchi et al. 2024).
The ideas that lose to filing friction are the ones nobody else has.
AI creative work tools (Gemini, Claude, ChatGPT etc.) prioritise frictionless interfaces to make usage effortless. In learning, creative work, and ideation contexts. An idea is not like that. You do not know what you want yet. Working it out is the task, and the thinking is what does the working out. So when a tool removes the effort, it has not saved you time. It has removed the only part that was getting you anywhere.
This leads to overreliance on AI output and to uncorrected biases. People are less likely to examine output that already looks polished and complete.
This leads to low psychological ownership. Weak ownership reduces accountability and the motivation to keep investing in an idea.
Why it happens
Frictionless AI makes ideation faster and shallower
Dual-process theory splits cognition in two. System 1 is fast, associative, heuristic and effortless. System 2 is slow, procedural, metacognitive and effortful. Creative work needs both, because System 1 generates and System 2 evaluates. The System 1 to System 2 transition is not voluntary. System 2 engages when System 1 hits an error it cannot resolve, so confusion is the trigger.
Before designing anything, we needed a causal account specific enough to design against. "People think less with AI" is too broad to act on. The literature review pointed to two mechanisms:
Few generative actions from the user. Human input in AI co-creation is remarkably low (Xie et al. 2024). Users mostly select, accept or reject rather than transform, modify or add. Seamless, fluency-first interfaces also leave no room for reflective checking (He & Liu 2026).
No productive conflict. Humans and AI converge on a consensus very quickly (Tsakalerou et al. 2026). Models tend to confirm whatever the user says, so ideas are accepted without much cross-examination.
Project Ideas
How to make an experiment around them
Degraded fonts, hard-to-read typesetting. Make it harder to read.
Microboundaries, artificial processing delays. Make the person wait.
Forced choice, unassisted first steps. Withhold help until they commit.
Scaffolding, guiding questions. Give hints instead of answers.
Reflective nudges, explainability requirements. Make someone reason.
Research
Seven kinds of friction exist.
We could build two.
We surveyed friction mechanisms across fields and grouped them into seven families. This let us choose mechanisms deliberately instead of picking whichever seemed most interesting. Under desirable difficulties in educational psychology, and positive friction and frictional AI in interaction design, we found seven families.
Two questions cut it down. Can three students build it in one semester, and does it change what the person has to do rather than just how the screen looks. Perceptual disfluency and temporal barriers fail the second test. They decorate the problem instead of touching it.
Degraded fonts, hard-to-read typesetting. Make it harder to read.
Microboundaries, artificial processing delays. Make the person wait.
Forced choice, unassisted first steps. Withhold help until they commit.
Engineered discomfort, unfriendly interfaces. Make the system argue.
Scaffolding, guiding questions. Give hints instead of answers.
Effortful assembly, the IKEA effect. Make the person do the work.
Reflective nudges, explainability requirements. Make someone check the reasoning.
Each chosen mechanism targets one identified cause. Generative labour adds the missing user actions. Antagonistic conversation breaks the fast consensus loop. Families like perceptual disfluency or temporal barriers add effort without asking the user to produce anything, so they would not address ownership. We also found a gap: friction in AI systems has mostly been studied in decision support (Buçinca 2021; Natali 2024), and antagonistic conversation styles have not been tested in creative ideation.
Response
So we built three tools
We built a text ideation tool for marketing briefs. It has three modes behind a single toggle. The model, the task and the length of the session are identical in all three. The only thing that changes is how much work the interface makes you do.
You describe a brief, it hands you finished campaign ideas, you pick one. No canvas, no resistance. This is the control, and it is what every tool on the market already does.
The model puts rough fragments on a canvas and stops. You cannot advance a turn until you have edited them, added detail and drawn the connections yourself.
It is helpful for two turns. Once you commit to an idea it turns critic, acknowledges without praise, and pushes on your weakest answer, harder every turn.
Research
Questions
1
How do generative labour and an antagonistic conversation style, used as friction mechanisms, affect System 1 and System 2 thinking during ideation?
Measured by: retrospective interviews coded against a dual-process codebook by two independent coders, with time per turn as a behavioural signal.
2
How do these two mechanisms affect psychological ownership of the ideas produced?
Measured by: 1–7 self-ratings of ownership and perceived AI contribution, with satisfaction and confidence as checks that friction did not just make people dislike the result.
Nobody was told which mode they were in, or that the mode changed between sessions. The next four sections are how each mode works. After that, what happened when people used them.
Browser
The interface
React 18
ReactFlow 11
Zustand 5
POST /api/chat
+ canvas state
Server
A proxy
Express 4 · 72 lines
no prompt logic, no state
localhost
/api/chat
Model Host
Ollama serving llama3
runs on a machine
no key, no quota
The control condition. A plain chat partner, no canvas, no resistance, and what every tool on the market already does.
Generative Labour
The model opens the space. You make the meaning.
Chat on the left, a node canvas on the right. Six turns walk one line of brief to a campaign with a working mechanism. Nodes never disappear between turns, so the tree grows as the session does.
01
Clarify
AI ACTS
Three questions about audience, product and goal. The canvas is still empty.
02
Vibe
YOU ACT
Directions arrive as single words. Click one or two and they attach to your next message.
03
Medium
AI ACTS
Channels branch off the directions you chose, joined by labelled edges.
04
Seeds
YOU ACT
Named concepts built from your direction and your channel. Pick the one that excites you.
05
Mechanism
YOU ACT
Three empty fields. Trigger, action, result. The model writes nothing here.
06
Finalise
AI ACTS
A campaign summary slides up. Finalising turns its top bar green.
One turn does the real work
Turn five is the only turn where the model writes nothing. What will make the audience act, what will they do, and what happens next. Every turn before it was choosing. This one is writing, and it is where people stalled.
Effort that feels like busywork produces resentment, not thinking. An open canvas where you connect anything to anything made the labour feel arbitrary.
Six fixed turns walking abstract to concrete, so every action builds on the one before it and the effort has somewhere to go.
Friction needs an exit, so we built four and scoped each one tightly. Undo on the canvas. Regenerate, but only on turns one to four, while ideas are still cheap. Go Back, restoring the canvas as it stood at turn four. And a hint button that exists on turn five and nowhere else, because that is the only turn people actually stalled on.
BEFORE · THE TESTED BUILD
Rounded, navy, and every node a coloured box with a title. To know a box was a channel you had to remember what purple meant.
AFTER · THE REBUILD
Every node now says what it is. Colour backs the label up instead of carrying it alone, and a neutral square shell leaves the canvas as the only colour on screen.
Antagonist
It is friendly for two turns, then it turns
It was going to be a shape-shifter. The plan had the model role-playing a different stakeholder each turn, a marketer then a customer then a sceptic. That was cut for one critic who escalates, because a rotating cast gives you three shallow objections instead of one that gets deeper.
For the first two turns it is a neutral evaluator. It clarifies your brief, hands you three or four named campaign ideas, and asks which one excites you. Warm, useful, ordinary. The moment you choose, the interface swaps the prompt underneath you. From turn three it is a critic. It acknowledges your idea without praising it, asks questions built to find the weak joint, and never fully accepts an answer. Each turn it pushes harder.
Explore
Calm and curious. Who is it for, what would success look like.
Understand
It restates your idea in its own words and asks if that is right.
Challenge
Fundamental flaws, who would oppose this, what you have overlooked.
Hostility at turn one has nothing to bite. You have not committed to anything yet, so pressure reads as noise and people disengage.
The persona switch waits until after the choice. Every challenge then lands on something the person has already claimed as theirs.
The cost: those first two friendly turns are a small ambush. People trusted it, then it turned on them.
One pilot participant said the antagonistic mode made them feel they were defending someone else’s idea. That showed up in the ownership scores months later. It is the honest limit of this mechanism.
Method
Experiment Design
Every participant did all three modes, in a different order, on a different brief each time, so no mode ever drew the easy question and position cancels out. Sessions were recorded, then replayed turn by turn while people narrated what they had been thinking.
Five orders across five people. Every mode appears in every position exactly once. Whichever mode someone tries first gets their freshest attention, and whichever comes last gets a tired participant, so we made a counterbalanced Latin square. Five orders across five people so position cancels out.
P1
P2
P3
P4
Abandoned Directions
A shape-shifting antagonist
It was going to role-play a different stakeholder each turn. A rotating cast gives three shallow objections instead of one that gets deeper.
A canvas on both friction modes
If both had a canvas, no result could say which mechanism did the work. This cut is what makes the study readable.
A reflection test
We planned to score System 2 with a test taken outside the task. We replayed the recorded sessions instead and asked people to narrate.
Analysis
Both mechanisms changed how people thought. Only one changed how they felt.
We wrote the codebook before anyone looked at a transcript. Three top level codes, twelve underneath, built from dual process theory rather than from whatever we happened to notice.
of coded excerpts were System 1 in the baseline. Under either friction mode, 33 to 47.
turns used in the baseline. Four of five stopped before the tool did, two after three turns.
the baseline time on task for the antagonist. 17:06 against 7:08.
So “friction works” is too simple. System 2 engagement and psychological ownership are separate outcomes, and only one of the two mechanisms moved both. The antagonist also cost 1.4 points of satisfaction and 0.6 of confidence.
Results
Both mechanisms changed how people thought. Only one changed how they felt.
Everything below comes from five participants running fifteen briefs across three modes, with every session recorded and replayed turn by turn. Here is the whole picture on one line each.
In the baseline, four of five people stopped before the tool did, and two quit after three turns. Asked why, they said they had “no more to discuss”. That is premature convergence, and it is the failure the whole project was built to interrupt.
Psychological ownership 3.4 to 5.2. Credit given to the AI fell by two points. Confidence went up. Satisfaction did not move. It won on every measure the study had.
Psychological ownership 3.4 to 3.6. Statistically nothing, on five people. It made people think harder, then cost them 1.4 points of satisfaction and 0.6 of confidence.
System 2 engagement and psychological ownership are separate outcomes, and only one of the two mechanisms moved both.
Conclusion
Three things the study supports
Thinking and ownership
Both mechanisms moved thinking from fast to slow. Only Generative Labour also moved ownership, from a mean of 3.4 to 5.2, and it rose for four of the five. The antagonist made people work harder and left ownership where it started.
Both mechanisms moved thinking from fast to slow. Only Generative Labour also moved ownership, from a mean of 3.4 to 5.2, and it rose for four of the five. The antagonist made people work harder and left ownership where it started.
Generative Labour runs five seconds a turn slower than the baseline, so every extra minute came from turns a baseline user would have skipped. The antagonist is the opposite at 2:26 a turn against 1:37. One keeps you in the room. The other slows the room down.
The participant who scored lowest on the metacognitive inventory, 26 of 52, was lowest on exactly the three subscales both friction modes demand first: procedural knowledge, conditional knowledge and planning. They scored 5 of 6 on evaluation, the part that runs after.
System 2 engagement and psychological ownership are separate outcomes, and only one of the two mechanisms moved both.
Make someone defend an idea and they think harder. Make them build it and they think harder and call it theirs.
Overall
What I learned
Both mechanisms roughly doubled engagement, so the summary numbers make them look like two versions of the same idea. The timing logs say otherwise.
Psychological ownership 3.4 to 5.2. Credit given to the AI fell by two points. Confidence went up. Satisfaction did not move. It won on every measure the study had.
Psychological ownership 3.4 to 3.6. Statistically nothing, on five people. It made people think harder, then cost them 1.4 points of satisfaction and 0.6 of confidence.
Psychological ownership 3.4 to 3.6. Statistically nothing, on five people. It made people think harder, then cost them 1.4 points of satisfaction and 0.6 of confidence.
System 2 engagement and psychological ownership are separate outcomes, and only one of the two mechanisms moved both.
If Generative Labour had raised ownership while leaving thinking style unchanged, the mechanism would be about labour rather than cognition, and the dual-process framing the whole study rests on would need rewriting. It did not, so the framing held. The antagonist is the closer call: it moved thinking and not ownership, which is half of what the theory predicts.
