Skip to main content

From Blank Page to Proposal: Mastering GenAI for Academic and Professional Projects

For many professionals, one of the hardest parts of any project isn’t the work itself—it’s the "blank page" problem. Whether you are drafting a project proposal, conducting a literature review, or brainstorming innovative solutions, getting started can be a significant mental hurdle.

Generative AI (GenAI) tools like ChatGPT, Claude, and Copilot are often described as "content creators," but their true value for professionals lies in enhancing productivity. By applying specific prompting techniques, you can transform a vague idea into a well-structured, reference-supported document in a fraction of the time.

Here is a three-step workflow to turn GenAI into your ultimate research and planning partner.

1. Brainstorming with "Personas" and "Templates"

Don't just ask the AI for "ideas." To get professional results, you must give the AI a Persona (who it is acting as) and a Template (how you want the output to look).

In our recent experiments, I used GenAI to generate project ideas for specialized fields like Ambient Assisted Living or Data Intelligence. By asking the AI to act as a "Supervisor" and by providing a template (Title, Introduction, Problem Statement), the AI produces structured options rather than generic paragraphs.

Pro-Tip: Once you have a few ideas, ask the AI to "expand" the best one with specific word counts for each section (e.g., "Justification: 500 words"). This forces the AI to provide depth rather than surface-level summaries.

2. The "Chain of Density" for Richer Detail

A common complaint about AI writing is that it feels "fluffy." To combat this, you can use a technique called Chain of Density (see here for more details)

Instead of accepting the first draft, you ask the AI to rewrite the content multiple times. In each iteration, you instruct it to identify missing "informative entities" (specific details, technical terms, or key facts) and fuse them into the existing text without increasing the word count.

  • The Result: The prose becomes increasingly "dense" with information, making it much more useful for a professional audience who values substance over wordiness.

3. Accelerated Literature Reviews

Gathering evidence is often the most time-consuming part of professional writing. You can use GenAI to "scout" for you. By using an iterative search prompt, you can instruct the AI to:

  1. Find specific papers or articles on a topic.

  2. Identify "Common Features" across those sources.

  3. Organise these into a Comparison Table showing which papers support which themes.

This doesn't just give you a list of links; it gives you a thematic analysis of the current landscape, complete with references.

The "Human-in-the-Loop" Requirement

While these tools are powerful, they are not autonomous. As a professional, you are the editor and the "validator." Before finalising any AI-assisted work, always:

  • Check the References: Ensure the papers and citations provided actually exist (AI can sometimes "hallucinate" plausible-sounding sources).

  • Apply the "Human Bit": Ask yourself, "Is this doable?" and "Does this fit my specific context?"

  • Refine the Voice: AI provides the skeleton; you provide the nuance, ethics, and professional judgment.

Conclusion

GenAI isn't here to replace the thinking process—it’s here to accelerate the structuring process. By using personas, density chains, and iterative research tables, you can spend less time staring at a blank screen and more time refining high-quality, impactful work.

Labels:

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