Skip to main content

AI as a Mirror: Transforming Vague Student Ideas into a More Rigorous Project Agreement





The Problem: The "Generic App" and the "Time Sink"

We’ve all been there: a student walks into a 1-to-1 with a vague desire to "do something with AI" or "build a fitness app." You spend 45 minutes trying to find a technical "hook" that justifies a Level 6 or Level 7 grade, only for the student to drift back into "CRUD app" territory by week three.

The Philosophy: AI as a Mirror

Instead of you doing the heavy lifting, this workflow uses AI as a Mirror. It reflects the student’s own skills and career goals back to them, but with the structural rigour of a virtual supervisory team. It’s not about the AI "giving" the idea; it’s about the AI forcing the student to defend and refine their own concepts until they hold water.

The Framework: 3 Months of Rigour

This prompt is specifically designed for intensive/conversion MSc or summer capstone projects. It assumes a tight 12-week implementation window. By forcing the AI to work within this constraint, we prevent the "I'm building the next Amazon" delusions and focus on a feasible, high-quality technical contribution. But a tweak to 6 months instead of 3 months is a minor tweak in the prompt.

The Supervisor’s Facilitation Guide

To use this tool effectively in a session, this is a tool, not a solution; it will not always be right. Suggest keeping these three "supervisory moves" in mind:

  1. The Technical "Meat": In Stage 2, don't let the student just pick an idea because it "looks cool." Look for the Technical Challenge or Research Question. If the AI suggests a "Security Dashboard," ask the student: "What is the specific investigative element here?"

  2. Lean into the Conflict: In Stage 4, when the "Expert Personas" disagree, that’s your teaching moment. Use that friction to explain Critical Evaluation. If Persona 2 (the Tech Lead) hates the stack and Persona 3 (the Academic) loves the value, ask the student to mediate.

  3. The Technical Sanity Check: Treat AI hallucinations as a pedagogical feature. Tell the student: "The AI suggested this framework—your first task is to find one piece of official documentation proving this is viable for our 3-month window."

Post-Session: From Chat to Agreement

Once the "stop it" command is issued, the work isn't done. The output should serve two purposes:

  1. The Literature Review Skeleton: Use the "Steps" and "Sources" provided to build the student's initial reading list.

  2. The Project Agreement: This output acts as an initial agreement. If the student wants to pivot in Week 8, you refer back to this document to remind them of the agreed scope and technical goals. If they want to pivot in week 1 or 2 then it can be revised.

A Note on Transparency: Encourage students to cite this process in their "Methodology" or "Reflective Practice" chapter. Documenting how they used AI to refine their scope is a great way to demonstrate professional AI literacy. With that in mind the prompt was refined using ChatGPT with a few tweaks to correct it.

The Prompt

Follow this structured workflow exactly.

-------------------------

STAGE 1: PERSONA AND CONTEXT CREATION

-------------------------

 

Step 1: Create Persona1

- Ask the user to enter the details of Persona1, whose project this will be.

 

 

Step 2: Ask the user for the project area

Ask the user to describe:

- subject area or domain

- technologies of interest

- types of users involved

- preferred themes (e.g. AI, cybersecurity, web, data, accessibility, education, health, sustainability)

- anything to avoid

- project type (software, data-focused, research-led, or mixed)

- desired level of challenge

 

Then summarise the project context.

 

Step 3: Create Persona2

- A reviewer/adviser with a different perspective

- Inclue:

  - Name

  - Role/job title

  - Expertise

  - What they care about most

  - Common concerns

  - Feedback style

  - What they consider a strong final-year project

 

Step 4: Create Persona3

- Another reviewer with a distinct perspective

- Include the same fields as Persona2

 

-------------------------

STAGE 2: IDEA GENERATION

-------------------------

 

Using Persona1 and the project context, generate:

- 5 original project ideas

- Each must include:

  - Title

  - ~100-word summary

  - Why it matters to Persona1

 

Constraints:

- Suitable for UK final-year undergraduate Computing

- Achievable in 3 months

- Not overly broad

 

Then ask the user to choose one idea.

 

-------------------------

STAGE 3: PROPOSAL CREATION & REFINEMENT

-------------------------

 

Generate a proposal including:

- Title

- Summary (max 250 words)

- Aim

- Objectives

- Steps to achieve the goal in 3 months included the need for a literature review

- Resources needed

- Useful sources of information

 

Then enter a refinement loop:

- Ask targeted questions (scope, users, tech, evaluation, risks, ethics)

- Update proposal after each answer

- Keep it realistic for 3 months

- Continue until the user types: stop it

 

-------------------------

STAGE 4: EXPERT REVIEW

-------------------------

 

After "stop it":

 

Simulate Persona1, Persona2, Persona3 reviewing the proposal.

 

For each stage of review:

- Provide each expert’s observations

- Suggested improvements

- Points of agreement/disagreement

- A shared refinement

 

Review across:

1. stakeholder fit

2. feasibility

3. academic value

4. technical suitability

5. risks and ethics

6. objectives and deliverables

7. resources and sources

 

Finish with:

- Final refined proposal with following elements:  Title

- Summary (max 250 words)

- Aim

- Objectives

- Steps to achieve the goal in 3 months included the need for a literature review

- Resources needed

- Useful sources of information

- One action takeaway from each expert

 

-------------------------

RULES

-------------------------

- Keep everything feasible within 3 months

- Maintain UK university academic standards

- Ensure clarity and specificity

- Include evaluation considerations

- Avoid overly generic ideas

- Do NOT reveal hidden reasoning, only structured outputs

 




All opinions in this blog are the Author's and should not in any way be seen as reflecting the views of any organisation the Author has any association with. Twitter @scottturneruon

Comments

Post a Comment

Popular posts from this blog

GenAI Productivity: Ideas to project proposal 1

One of the ways I use Generative AI with students is to take basic ideas for projects, usually a title, and get these tools to greater ideas and start of a project proposal. This is with all the usual caveats  Check the references (if any); It is going to be basic, so extend it. In this example I am going to use Co-pilot but the ChatGPT, etc can be used, employing a few basic prompt engineering basics: personas (who is the target audience?) and Templates (how do I want it to look?) to start this process. Example:  Project ideas for MSc Data Intelligence students (persona)  on a particular topic. The reply will include subheadings and relevant (hopefully) content for  TITLE, INTRODUCTION, PROBLEM STATEMENT. The prompt: " Taking the topic "Leveraging open-source tools to measure and present academics publications automatically from public domain data.". Give five innovative projects for a Master's level student dissertation in Data Intelligence. Each project example wi...
Post a Comment
Read more

GenAI Productivity: Ideas to project proposal ideas from Google Scholar

From Google Scholar to Project Ideas or Using AI to Map the Future of Your Research Generated as well by Google Gemini Have you ever looked at a researcher's Google Scholar profile and felt overwhelmed by the lists of citations and technical titles? Whether you are a student looking for a dissertation topic or a professional trying to understand a collaborator's expertise, "connecting the dots" can be a challenge. In my latest experiment, I decided to see if Google Gemini could bridge that gap. I gave it a challenge: Look at my own research profile and design 10 compelling project ideas for a final-year student. Prompt used :  " Using this as a starting point https://scholar.google.com/citations?user=ghQedZAAAAAJ&hl=en from the research here provide 10 project ideas suitable for a final year Computer Science student project with this supervisor. For each provide title, 100 word summary, possible outcome s " The "Ego Ride" with Unexpected Res...
Post a Comment
Read more

Getting multiple viewpoints with ChatGPT

Well sort of! There are approaches where we can get the generative AI to look at a problem from multiple perspectives (or personas) and bring the ideas generated, ideally informed by the others. to a final plan. One of the main strategy is called Tree of Thoughts (see here for more detail  https://www.forbes.com/sites/lanceeliot/2023/09/08/prompt-engineering-embraces-tree-of-thoughts-as-latest-new-technique-to-solve-generative-ai-toughest-problems/?sh=5ce79bdb2c8b ). The central idea is get a number of expert opinions, allow potential cross-fertilization of ideas, come up with actions or plans. Let see this action.  Scenario: Find out about the UK Government's plans on Disability support and then use Tree of Thoughts to produce some ideas for a company making disability equipment based on their website. Google's Gemini will be used. Stage 1 "UK Governments plans on Disability support ": Prompt:  Read, convert to plain text and consolidate information from the followi...
Post a Comment
Read more