0/9 sections
Wrap-up

Key Takeaways

Pull the threads together: where each tool wins, where it warns, and what to actually do in the week after the workshop.

SECTION OBJECTIVES
  • Pick one tool and one configuration surface to invest in this term.
  • Agree an AI-use disclosure stance for your next paper.
  • Leave with a 10-item action checklist.

You've now seen the three tools through the same lens: persistent roles, grounded sources, document-aware drafting, and reusable specialists. The comparison below is a starting point, not a verdict. Pick on the basis of where your sources, your collaborators, and your institution already are.

Gemini vs ChatGPT vs Claude. For research

DimensionGeminiChatGPTClaude
Best atOpen-web deep research, multimodal input, source-grounded reading packs (via NotebookLM)Configurable specialist agents (Custom GPTs), live folder/Drive workflows, broad ecosystemLong-context drafting, methods/critique work, careful citation discipline, team workflows
Persistent context surfaceGems + NotebookLM notebooksProjects + Custom GPTs + Custom InstructionsProjects + Skills
Source-grounded modeNotebookLM (strongest of the three)Projects + ConnectorsProjects (large knowledge base, citations)
Team / co-author supportWorkspace sharing of Gems and notebooksShared GPTs and team workspacesClaude CoWork shared Projects (most explicit)
Drafting surfaceCanvasCanvasArtifacts + Projects
Watch-outCitation accuracy outside Deep Research can driftMemory across Projects can leak context; audit periodicallySmaller plugin/connector ecosystem than ChatGPT

What publishers actually say

Across Elsevier, Wiley, Taylor & Francis and IEEE the message is consistent: AI is accepted for language editing, readability and writing improvement, but not for producing scientific insights, drawing conclusions, fabricating data, or claiming authorship. You remain fully accountable for the work, and disclosure of AI use is expected (and in some cases required).

Elsevier and Wiley author guidance: generative AI may be used to improve readability and language, with human oversight; authors remain accountable.
Elsevier & Wiley — AI for readability and language, with human oversight.
Taylor & Francis and IEEE author guidance: responsible use of generative AI for idea exploration, language improvement, literature classification and grammar editing, with disclosure.
Taylor & Francis & IEEE — responsible use, with disclosure expected.

Ethics & integrity checklist

  • 1Disclose AI assistance in line with your institution's and target journal's policies. And check both before submission.
  • 2Never paste student work, unpublished peer-review material, or interview transcripts into a tool whose data-handling terms you haven't read. Or without turning off data usage for training.
  • 3Treat every citation an LLM produces as unverified until you have opened the source yourself.
  • 4Keep a brief AI-use log per paper (tool, purpose, date). It makes the methods paragraph and any reviewer query trivial to answer.
  • 5Discuss tool norms with co-authors and supervisees before, not after, the first draft.

Official data-handling and privacy policies

10 take-home actions

  1. 1Build one Gem, one Custom GPT, or one Claude Skill this week for a research task you do at least monthly.
  2. 2Convert one currently-painful folder of PDFs into a NotebookLM notebook or a Claude Project.
  3. 3Write your ChatGPT Custom Instructions (or the equivalent for your chosen tool). Under 1500 characters.
  4. 4Pick one paper-in-progress and create a Project for it; pin the charter as message #1.
  5. 5Run one Deep Research report on a research question you're currently exploring; treat it as a starting brief, not a finished one.
  6. 6Draft a 1-paragraph AI-use disclosure you'd be comfortable including in a methods section.
  7. 7Agree shared AI norms with your most frequent co-author or RA.
  8. 8Trial a source-grounded tool against an open-web tool on the same question; note where each wins.
  9. 9Use AI to pre-flight one draft before submission: check methods-description completeness, citation consistency, and argument flow.
  10. 10Subscribe to one signal source for AI-in-research developments (a newsletter, a journal special issue, a colleague). Refresh quarterly.

Further reading

  • NotebookLM and Gemini documentation. Google's own guidance is updated frequently and underrated.
  • Anthropic's prompt-engineering and Skills documentation. The clearest writing on context engineering in the industry.
  • OpenAI's Custom GPT and Projects help centre. Read the data-handling sections, not just the how-to.
  • Your institution's research-integrity office. Most have issued AI-use guidance in the last 18 months.
  • Recent journal editorials in your sub-field on AI authorship and disclosure norms.
Previous4. Other Useful ToolsBack to start