Now Deep Research is available to ChatGPT users on the £20/mth tier, I’ve had a chance to experiment. The tl;dr is that it’s really very good, and the level of progress in just 6 months is mind-blowing.
I picked something I know about - financial pressures facing UK Universities. First, I asked ChatGPT to generate the prompt for Deep Research, using this template I found via a mailing list (and I can’t remember which one).
Edited to my needs, the template is:
Use the best practices provided below and the initial context I shared to create a deep research prompt on the following topic:
Context:
I need the final report to be as comprehensive and thorough as possible. It should be soundly rooted in business strategy, academic research, and data-driven. But it also needs to use industry blogs and other sources, too. Even reviews are ok.
Please build a prompt using the following guidelines:
Define the Objective:
- Clearly state the main research question or task.
- Specify the desired outcome (e.g., detailed analysis, comparison, recommendations).
Gather Context and Background:
- Include all relevant background information, definitions, and data.
- Specify any boundaries (e.g., scope, timeframes, geographic limits).
Use Specific and Clear Language:
- Provide precise wording and define key terms.
- Avoid vague or ambiguous language.
Provide Step-by-Step Guidance:
- Break the task into sequential steps or sub-tasks.
- Organize instructions using bullet points or numbered lists.
Specify the Desired Output Format:
- Describe how the final answer should be organized (e.g., report format, headings, bullet points, citations).
Include any specific formatting requirements.
Balance Detail with Flexibility:
- Offer sufficient detail to guide the response while allowing room for creative elaboration.
- Avoid over-constraining the prompt to enable exploration of relevant nuances.
Incorporate Iterative Refinement:
- Build in a process to test the prompt and refine it based on initial outputs.
- Allow for follow-up instructions to adjust or expand the response as needed.
Apply Proven Techniques:
- Use methods such as chain-of-thought prompting (e.g., “think step by step”) for complex tasks.
- Encourage the AI to break down problems into intermediate reasoning steps.
Set a Role or Perspective:
- Assign a specific role (e.g., “act as a market analyst” or “assume the perspective of a historian”) to tailor the tone and depth of the analysis.
Avoid Overloading the Prompt:
- Focus on one primary objective or break multiple questions into separate parts.
- Prevent overwhelming the prompt with too many distinct questions.
Request Justification and References:
- Instruct the AI to support its claims with evidence or to reference sources where possible.
- Enhance the credibility and verifiability of the response.
Review and Edit Thoroughly:
- Ensure the final prompt is clear, logically organized, and complete.
- Remove any ambiguous or redundant instructions.
That then generates this massive prompt:
Objective
Conduct a comprehensive, data-driven analysis of the financial stability of the University of Sheffield over time, considering the impact of declining international student numbers and other financial pressures in the UK Higher Education (HE) sector. The research should compare Sheffield with peer institutions (Leeds, Manchester, Nottingham, and similar Russell Group universities) and provide strategic insights into its future financial sustainability.
The final report should:
Analyze financial performance trends, including income sources, expenditure, and surplus/deficit patterns.
Assess the role of demographic shifts (UK and international student trends) and their financial impact.
Examine international relations and economic conditions in key markets such as China and India.
Evaluate the impact of league table rankings on financial and reputational standing.
Provide comparative insights with competitor institutions to highlight relative performance and strategic positioning.
Offer strategic recommendations to enhance financial resilience.
Context & Background
The University of Sheffield is a research-intensive university and a member of the Russell Group, with strengths in engineering, health, and sciences. UK Higher Education institutions face financial difficulties due to declining international student numbers, economic instability, and government policy changes.
Key challenges to investigate:
Demographic trends: Declining UK birth rates, visa policy impacts on international student recruitment, and long-term shifts in HE participation.
International market conditions: The economic performance of India and China, two key recruitment regions for international students.
Competitor analysis: Financial health and recruitment trends of Leeds, Manchester, Nottingham, and similar institutions.
League table rankings: How changes in global and domestic rankings impact Sheffield’s attractiveness to students and funders.
Data Sources:
HESA (Higher Education Statistics Agency): Student recruitment and demographic data.
University annual reports: Institutional financial data from Sheffield and comparators.
Industry blogs and reports: Trends from HE sector think tanks and financial analysts.
Government and international reports: Policy and economic outlooks for key student recruitment markets.
Step-by-Step Research Breakdown
Financial Performance Analysis
Retrieve Sheffield’s financial statements (revenue, costs, surplus/deficit trends) from annual reports over the last 10 years.
Compare with Leeds, Manchester, and Nottingham to identify key financial differences.
Identify major income streams (tuition, research grants, commercial activities) and their stability.
Demographic and Student Recruitment Trends
Use HESA data to track domestic and international student numbers at Sheffield and comparators.
Examine changes in regional student preferences and their impact on enrolment.
Consider how visa and immigration policies affect international student recruitment.
International Relations & Economic Factors
Investigate economic and policy trends in China and India affecting student mobility.
Identify any geopolitical risks that could further disrupt international recruitment.
Analyze Sheffield’s current international partnerships and their financial relevance.
Impact of League Table Rankings
Track Sheffield’s rankings in QS, THE, and domestic league tables over time.
Assess correlations between ranking changes and student demand (especially international).
Compare the rankings-financial impact relationship with peer universities.
Comparator Institution Benchmarking
Compare Sheffield’s financial resilience to Leeds, Manchester, and Nottingham.
Identify best practices used by competitors to diversify income streams or cut costs.
Explore student satisfaction, employer reputation, and research output data as indirect financial indicators.
Strategic Recommendations for Financial Sustainability
Identify opportunities for new income streams (e.g., lifelong learning, online education, corporate partnerships).
Suggest policies to improve student recruitment despite demographic challenges.
Propose strategies to enhance rankings and maintain global competitiveness.
Desired Output Format
The final report should be structured as follows:
Executive Summary
Key findings and recommendations in a concise format.
Introduction
Purpose of the research, scope, and methodology.
Financial Trends Analysis
University of Sheffield’s financial trajectory and comparator analysis.
Demographic and Student Recruitment Analysis
Domestic and international student trends.
International Relations & Economic Impact
Impact of China/India economic and policy changes on recruitment.
Impact of League Table Position
Rankings analysis and its financial implications.
Comparator Institution Benchmarking
Performance comparison with Leeds, Manchester, Nottingham.
Strategic Recommendations
Actionable insights for Sheffield’s financial sustainability.
References & Data Sources
Citations from HESA, university reports, government data, industry insights.
Flexibility & Iterative Refinement
This research should be iteratively refined based on preliminary findings.
Additional comparators or focus areas can be included if emerging data suggests relevance.
The report should balance academic rigor with industry insights, using sources beyond just peer-reviewed literature.
Role & Perspective
Act as a higher education financial strategist, providing data-driven insights and actionable recommendations.
Assume a long-term institutional sustainability lens, rather than short-term financial tactics.
Justification & References
All claims must be supported with evidence, with references to HESA, annual reports, academic sources, and industry analysis.
Where applicable, include quantitative comparisons (e.g., student number trends, financial ratios, ranking shifts).
I then take the output from this, and feed it into a new ChatGPT session and hit the “Deep Research” button. Answer a few clarifying questions and away it goes.
It’s not smooth. The first time the model got stuck, and the second time it became a bit distracted right at the end:
I'm gathering info on Apex Pest Control's financials, cross-checking other sources for accuracy ...
I have no idea where Apex Pest Control came from!
But the full report is pretty good. Based only on public info, it doesn’t tell me anything I don’t know (and that wasn’t the aim) but it’s coherent and covers the basics well.
Total time was ~19 minutes for the successful run.
Now if it supported adding in private documents as well, this would suddenly become extremely powerful, and the rate of improvement over the last 12 months is absurd