The Three-Prompt Trap
A university student opens ChatGPT minutes after receiving a creative problem-solving assignment. Within seconds, the AI generates several polished solutions. The student picks one, makes a few small tweaks, and submits it. The work looks sophisticated. Something vital has been lost: the student's independent idea generation. The AI completes much of the cognitive work before the learning process has even begun.
This isn't hypothetical. It's the default pattern when generative AI is treated as an answer generator rather than a thinking partner. The question facing higher education today isn't whether students should use AI—it's how AI can support learning without replacing human reasoning.
The Three-Prompt Trap
Guo et al.'s (2025) study, Student–AI Creative Problem-Solving: The Role of Human Agency, investigated this exact problem across two quantitative experiments involving 346 university students. Participants completed the same creative task—developing innovative ways to improve a toy bunny to increase sales—under different AI collaboration conditions.
In the first experiment (n=170), one group generated their own ideas before consulting ChatGPT (pre-SHT), another consulted AI first and then added their own ideas afterwards (post-SHT), and a control group relied on AI throughout without any instruction to engage in independent thinking.
Students who generated their own ideas before using AI reported greater initiative, stronger ownership of their work, and invested more mental effort than those who immediately turned to AI. This pre-SHT group also produced more cognitively sophisticated prompts that reflected higher-order thinking rather than simply repeating information from the task.
But here's the catch: this advantage gradually disappeared as students continued collaborating with AI. By the third prompt, many participants had begun following the AI's suggestions instead of directing the collaboration themselves.
Simply delaying AI use encouraged independent thinking initially, but it was insufficient to sustain human agency throughout the task. This is the three-prompt trap: students who thought first still drifted toward passive following within three exchanges.
Deep Idea Integration: The Fix
Recognizing this limitation, Guo et al. redesigned the collaboration in a second experiment involving 176 students. Instead of asking participants to think independently only at the beginning, they introduced a deep idea integration (DII) condition, which required students to integrate their own ideas into every interaction with ChatGPT.
Rather than asking broad questions and accepting AI-generated solutions, participants first generated an original idea before using AI to refine, challenge, or extend it. For example, instead of asking ChatGPT how to improve the toy bunny, a student who had already proposed making the toy glow safely in the dark might ask which child-safe materials could achieve this or whether similar products already existed.
In this condition, students—not the AI—determined the direction of the collaboration.
The learning benefits of the DII constraint were substantial. Students maintained higher levels of perceived agency throughout the task, produced prompts that remained cognitively sophisticated across all stages of the collaboration, and generated final solutions that were significantly more novel and useful. Their final design solutions were also less similar to one another, suggesting that students were developing genuinely original ideas rather than converging on the AI's preferred solutions.
Importantly, participants also reported greater perceived cognitive improvement, indicating that the collaboration enhanced their own learning experience rather than simply improving the quality of the final output.
What the Broader Literature Says
These findings align with a growing body of research on human-AI collaboration in educational settings.
Xia et al. (2026) found that while GenAI-supported group work assisted learning and metacognitive engagement, groups working without GenAI produced more original creative thinking solutions. The presence of AI, when not carefully structured, tends to homogenize idea generation.
Perifanou and Economides (2025) found that students valued GenAI most when it was used to clarify difficult concepts rather than replace independent learning. This is a crucial distinction: AI as a tool for understanding, not a replacement for thinking.
Together, these findings reinforce Guo et al.'s central conclusion: AI supports learning most effectively when educational design requires students to remain active contributors rather than passive recipients throughout the learning process.
What This Means for Educators
The implication for education is not to completely suppress the use of AI in learning environments. It's to design interactions that preserve students' intellectual independence, curiosity, engagement, and understanding of how AI can influence learning.
Generative AI can act as a powerful learning partner when students use it to refine and expand their own ideas rather than outsource the learning process. As AI becomes increasingly embedded within higher education, educators will need to develop assessment and teaching strategies that reward the learning process as much as the final product.
Encouraging students to critically question and build upon AI-generated suggestions will help ensure that AI strengthens, rather than diminishes, both intellectual skills and human agency.
The Takeaway
Agency in AI collaboration must be sustained throughout a task, not just established at the start. If you want students to maintain ownership over their work, require them to generate original ideas at every prompt—not just the first one. That's the difference between using AI as a thinking partner and using it as a shortcut.
Source: Guo, Y., Gilmartin, A., Surlis, P., & Hogan, M. (2025). Student–AI Creative Problem-Solving: The Role of Human Agency. Psychology Today. https://www.psychologytoday.com/us/blog/in-one-lifespan/202607/how-do-you-hold-on-to-your-own-thinking-with-ai
Additional context from:
- Generative AI — Wikipedia
- Generative AI — IBM