Practical guidance on the effective and responsible use of generative AI in academic work, research, teaching, and professional settings.
This resource covers key principles for working with large language models, AI course policy, a curated selection of generative AI tools across modalities, prompt engineering foundations, and research-specific resources. It is intended for students, researchers, faculty, and professionals seeking to understand and apply these tools productively while managing their risks and limitations. The guidance can, and should, be adapted to your specific context and needs.
This page was created with assistance from ChatGPT and Claude, primarily for language refinement, organization, and structural improvements.
This resource is licensed under CC BY-NC-ND 4.0. Suggested citation: Krakowski, S. (2026). Notes on the Use of Generative AI in Academic Work, Studies, and Research. Mimeo. Stockholm School of Economics.
This resource is continuously updated based on research and practical experience. For tested prompts and custom instructions, see the Prompt Library resource. For structured innovation techniques, see the LLM Innovation Techniques resource.
This document is a work in progress. Comments welcome.
Last updated: March 2026
Principles for Using Generative AI
Generative AI (GenAI) refers to a category of AI models - including large language models (LLMs) such as OpenAI's GPT series and Anthropic's Claude - that generate novel outputs based on patterns learned from training data. These models have demonstrated significant capabilities in understanding language, context, and intent, and are increasingly used across industries, including academic research, teaching, and professional knowledge work.
The technological, political, and legal landscape surrounding GenAI remains highly uncertain. Users should exercise caution, stay informed, and ensure their use complies with current regulations and institutional guidelines.
The following principles are based on research (notably Bowman, 2023) and practice (notably Mollick & Mollick, 2023a; 2023b), as well as the author's own experience.
Use the tools and experiment. 🧪 Learning to work with GenAI is an increasingly important skill. Try different tools and develop an intuition for how they work, where they help, and where they fall short. Start with tasks in your area of expertise, where you can evaluate the quality of the output.
Invest in your prompts. Minimum-effort prompts produce low-quality results. You will need to refine and iterate to get beyond mediocre output. This takes work. AI is unpredictable, and identical prompts can yield very different results across sessions. My best prompting advice is to approach prompting as a conversation and interact with the LLM as if it were human (knowing fully well it is not). I like to think of the models as aliens, emulating humans. 👽
Do not trust the output blindly. GenAI models are designed primarily to generate coherent and plausible language, not to ensure factual accuracy. Their output can appear authoritative and compelling while being entirely wrong. If the model gives you a number, a fact, or a reference, assume it may be incorrect unless you can verify it independently. This problem - commonly called "hallucination" - is not a bug but a fundamental feature of how these systems work.
Protect your privacy. A common misunderstanding is that these tools automatically train on, and/or disseminate, everything you submit. Information submitted to GenAI tools may be stored or used for model training, particularly on free tiers, but major providers such as ChatGPT now offer opt-out options even on free plans, and paid or enterprise tiers typically provide stronger guarantees, including no training on user data and automatic deletion of chat contents after a specified period. A useful rule of thumb when using free versions is to only share what you would be comfortable sharing in a public context. Check the current terms for whatever tool you use, as well as any applicable policies from your organization or institution.
Be thoughtful about applicability and bias. These tools are not appropriate for every task or context. Keep in mind that models are trained on historical data, and their output is shaped by the nature, representativeness, and processing of that data, along with design choices (such as guardrails and fine-tuning) made by the organizations behind each tool. The output can reflect and amplify existing biases.
AI Course Policy
This policy applies to courses taught by the author at the Stockholm School of Economics. It draws on Mollick & Mollick (2023a; 2023b) and is designed to be adaptable for educators across disciplines and institutions.
The use of AI tools (e.g., ChatGPT, Claude, Copilot) is not only permitted but encouraged in my courses. However, students are asked to explicitly acknowledge AI use in all assignments, including written submissions and presentations.
What to disclose:
The specific tool used (e.g., ChatGPT, Claude, Gemini)
When it was used (e.g., March 20, 2026)
The main purpose and/or prompt(s) (e.g., "Provide a brief outline of Acme Inc's history, along with its current competitive positioning and challenges.")
Your approach (e.g., "I used the output as a starting point for my analysis." or "I used the tool to explore alternative solutions to the case.")
You may use an appendix for this information if space or word limits are an issue. This applies to all AI-generated content: text, images, presentations, surveys, websites, and other outputs.
For referencing guidance, see APA Style Team (2025) and MLA Style Center (2025).
You are responsible for the final output. You must verify and substantiate AI-generated content, ensuring proper context, relevance, and factual correctness. If your submitted work contains inaccuracies, omissions, or plagiarism caused by the tools, you remain fully accountable - even if the errors were inadvertent.
AI is a tool, but one that you need to acknowledge using. Please include a paragraph at the end of any assignment that uses AI explaining what you used it for and what prompts you used. Failure to do so is considered a violation of SSE Academic Regulations.
Selected Generative AI Tools
The following is a curated selection of GenAI tools. Given the rapid pace of development, this list is not exhaustive and is subject to frequent updates. Inclusion does not constitute endorsement. Users should evaluate each tool's suitability for their needs and stay informed about emerging alternatives.
Note: Tool availability, features, naming, and pricing change frequently. URLs and descriptions reflect the state of the tools at last review. Some tools listed may have been renamed, merged, discontinued, or substantially changed since then.
General-purpose AI assistants (if you are just getting started, you do not need to read beyond this section)
The major multimodal platforms. Most now handle text, code, image generation, and web search to varying degrees.
ChatGPT (OpenAI): https://chat.openai.com
Claude (Anthropic): https://claude.ai - Also available as Cowork (https://claude.com/product/cowork), Anthropic's desktop workspace for tasks on local files and tools.
Copilot (Microsoft): https://copilot.microsoft.com
Gemini (Google): https://gemini.google.com - Recently also added music generation.
Meta AI (Meta, powered by Llama): https://www.meta.ai
Le Chat (Mistral AI): https://chat.mistral.ai
DeepSeek (DeepSeek): https://chat.deepseek.com
Grok (xAI): https://grok.com
HuggingChat (Hugging Face): https://huggingface.co/chat - Open-source alternative offering access to various models.
Poe (Quora): https://poe.com - Aggregator offering access to multiple LLMs including ChatGPT, Claude, and others.
Search and research tools
Tools designed for finding, synthesizing, or reasoning over information - whether general knowledge, academic literature, or domain-specific evidence.
Perplexity AI: https://www.perplexity.ai - Search engine with source transparency and citation. It offers an academic filter/search mode for prioritizing scholarly sources.
NotebookLM (Google): https://notebooklm.google - AI research assistant for working with uploaded sources. Can also generate podcast-style audio summaries.
OpenEvidence (OpenEvidence): https://www.openevidence.com - Clinical decision support platform for verified physicians, grounding answers in peer-reviewed sources including NEJM and JAMA.
Google Scholar (Labs Search): https://scholar.google.com/scholar_labs/search - AI-powered search layer for Google Scholar that analyzes research questions, identifies key topics and relationships, and explains how each returned paper addresses the query. Experimental, with limited access.
Stanford Agentic Reviewer (Stanford ML Group): https://paperreview.ai - Free AI tool that provides rapid, structured feedback on research manuscripts, grounding reviews in the latest arXiv literature.
Coding and software development
Tools purpose-built for writing, reviewing, or managing code - from IDE integrations and terminal agents to autonomous coding assistants.
Claude Code (Anthropic): https://code.claude.com/docs/en/overview - Command-line tool for agentic coding, letting developers delegate tasks to Claude directly from the terminal.
Copilot (GitHub/OpenAI): https://copilot.github.com
Cursor (Cursor): https://www.cursor.com
Windsurf (Codeium): https://codeium.com/windsurf
Antigravity (Google): https://antigravity.google - Google’s agentic development platform.
Jules (Google): https://jules.google.com - Autonomous, asynchronous coding agent that integrates with GitHub to handle bugs, tests, and features in cloud VMs while you work on other things.
Stitch (Google): https://stitch.withgoogle.com - AI-native design canvas that turns natural language into high-fidelity UI designs and interactive prototypes, with export to developer tools.
Lovable (Lovable): https://lovable.dev
Replit (Replit): https://replit.com
Tabnine (Tabnine): https://www.tabnine.com
v0 (Vercel): https://v0.dev
Image generation
Specialized tools for creating images from text prompts or other inputs.
Firefly (Adobe): https://firefly.adobe.com
Flux AI (Black Forest Labs): https://flux-ai.io
Ideogram (Ideogram): https://ideogram.ai
ImageFX (Google): https://labs.google/fx/tools/image-fx
Midjourney (Midjourney): https://www.midjourney.com
Recraft (Recraft): https://www.recraft.ai
Stable Diffusion (Stability AI): https://dreamstudio.ai/generate - Open-source image generation model.
Visual Electric (Visual Electric): https://visualelectric.com
Audio and music generation
MusicFX (Google): https://labs.google/fx/tools/music-fx
MusicGen (Meta): https://about.fb.com/news/2023/08/audiocraft-generative-ai-for-music-and-audio
Stability Audio (Stability AI): https://stableaudio.com
Suno AI (Suno): https://suno.com
Udio (Udio): https://www.udio.com
Video generation
Dream Machine (Luma Labs): https://lumalabs.ai/dream-machine
Flow (Google): https://labs.google/fx/tools/flow
Kling AI (Kuaishou): https://klingai.com
Movie Gen (Meta): https://ai.meta.com/research/movie-gen
Pika (Pika): https://pika.art
Runway (Runway AI): https://runwayml.com
Sora (OpenAI): https://sora.com
Veo (Google): https://cloud.google.com/vertex-ai/generative-ai/docs/video/generate-videos
Model playgrounds and alternative access
These platforms let you explore and compare models from multiple providers.
Explore (Replicate): https://replicate.com/explore
Fal (Features and Labels): https://fal.ai
OpenRouter: https://openrouter.ai - Unified API and interface for accessing models from multiple providers.
Perplexity Labs (Perplexity AI): https://labs.perplexity.ai
Playground (OpenAI): https://platform.openai.com/playground
Playground (Vercel): https://sdk.vercel.ai
Prompt Engineering
Prompt engineering refers to the practice of crafting effective inputs to get useful outputs from generative AI models. While the term can sound more technical than it is, the core idea is straightforward: the quality of what you get out depends heavily on what you put in.
Key principles
Be clear and specific. Provide context, state your goal, and define the desired format or tone.
Iterate. Treat prompting as a conversation with a human being (or a human-like alien 👽), not a one-shot query like Google or searching a document or a database. Refine based on what the model answers, such as "make it shorter", "focus on idea 2", or "stop talking like an AI".
Break complex tasks into steps. Smaller, sequential requests tend to produce better results than a single sprawling prompt.
Ask the model to explain its reasoning. "Chain-of-thought" prompting - guiding the model through intermediate steps - has been shown to improve reasoning quality (Wei et al., 2023), but requesting it through prompting seems to become less and less important as models become more independently capable.
In long sessions, models may lose track of earlier context. If responses degrade, clarify or start a fresh conversation.
For a practical collection of tested prompts and custom instructions, see the Prompt Library resource on this site.
Selected prompt engineering resources:
Anthropic (2023). Guide to Anthropic's prompt engineering resources. https://docs.anthropic.com/claude/docs/guide-to-anthropics-prompt-engineering-resources
Boonstra, L. (2024). Prompt engineering. Google Whitepaper. https://www.kaggle.com/whitepaper-prompt-engineering
Cohere AI (2022). Prompt engineering. https://docs.cohere.ai/docs/prompt-engineering
DAIR.AI (2023). Prompt engineering guide. GitHub. https://github.com/dair-ai/Prompt-Engineering-Guide
Hebenstreit, K. et al. (2023). An automatically discovered chain-of-thought prompt generalizes to novel models and datasets. arXiv. https://arxiv.org/abs/2305.02897
Hugging Face (2024). LLM prompting guide. https://huggingface.co/docs/transformers/main/en/tasks/prompting
Llama (2024). Prompting. Llama documentation. https://www.llama.com/docs/how-to-guides/prompting
Microsoft (2024). Promptbase. GitHub. https://github.com/microsoft/promptbase
Microsoft (2024). Prompts for education: Enhancing productivity & learning. GitHub. https://github.com/microsoft/prompts-for-edu
Mollick, E. (April 26, 2023). A guide to prompting AI (for what it is worth). One Useful Thing. https://www.oneusefulthing.org/p/a-guide-to-prompting-ai-for-what
Mollick, E. (November 1, 2023). Working with AI: Two paths to prompting. One Useful Thing. https://www.oneusefulthing.org/p/working-with-ai-two-paths-to-prompting
Mollick, E. & Mollick, L. (October 31, 2024). Stop writing all your AI prompts from scratch. Harvard Business Publishing Education. https://hbsp.harvard.edu/inspiring-minds/an-ai-prompting-template-for-teaching-tasks
OpenAI (2023). Prompt engineering. https://platform.openai.com/docs/guides/prompt-engineering
Schulhoff et al. (2024). The prompt report: A systematic survey of prompting techniques. https://trigaten.github.io/Prompt_Survey_Site
Shapiro, D. (2024). ChatGPT custom instructions. GitHub. https://github.com/daveshap/ChatGPT_Custom_Instructions
Wei, J. et al. (2023). Chain-of-thought prompting elicits reasoning in large language models. arXiv. https://arxiv.org/abs/2201.11903
Research-Specific Resources
The following tools and references are particularly relevant for academic research. They can support literature discovery, data analysis, academic writing, and research workflows.
Tools
Connected Papers: https://www.connectedpapers.com - Visual tool for exploring academic paper networks.
Consensus: https://consensus.app - AI-powered search engine for research papers.
Elicit (Ought): https://elicit.org - AI research assistant for literature review and data extraction.
Google Scholar (Labs Search): https://scholar.google.com/scholar_labs/search - AI-powered search layer for Google Scholar. Also listed under Search and research tools above.
Humata (Tilda Technologies): https://www.humata.ai - Upload and query documents using AI.
Jenni AI (Altum Inc.): https://jenni.ai - AI writing assistant for academic work.
Litmaps (Litmaps Ltd.): https://www.litmaps.com - Literature mapping and discovery tool.
NotebookLM (Google): https://notebooklm.google - AI research assistant for working with uploaded sources. Also listed under Search and research tools above.
OpenEvidence (OpenEvidence): https://www.openevidence.com - AI-powered clinical decision support platform grounding answers in peer-reviewed sources including NEJM and JAMA. Designed for verified physicians rather than general academic research. Also listed under Search and research tools above.
Paperpal (Cactus Communications): https://paperpal.com - Academic writing and editing assistant.
Perplexity AI: https://www.perplexity.ai - Search with source transparency. Academic mode queries published research. Also listed under Search and research tools above.
SciSpace (Typeset): https://typeset.io - AI tools for reading, understanding, and writing research papers.
scite.ai (scite): https://scite.ai - Smart citations showing how papers have been cited (supporting, contrasting, mentioning).
Stanford Agentic Reviewer (Stanford ML Group): https://paperreview.ai - Free AI tool for rapid manuscript feedback. Also listed under Search and research tools above.
Guides, courses, and collections
Boussioux, L. (2025). Generative AI teaching and learning materials. https://sites.google.com/view/leonardboussioux/genai
Boussioux, L. (2024). Resources to learn more about (Gen)AI. https://docs.google.com/document/d/1Hfpvr4A2NOw1NtO7YdwnM608oI0hxzVuX5xE7VWQhGs
Dell, M. (2024). Deep learning for economists. arXiv. https://doi.org/10.48550/arXiv.2407.15339
Dell, M. (2024). EconDL. https://econdl.github.io
HBS Baker Library (2024). Generative AI for MBAs. Harvard Business School. https://www.hbs.edu/it/elearning/public/baker/generative-ai-for-mbas/index.html
Hendriksen, C. (2023). ChatGPT and Bing: A practical guide for social science and management studies. https://docs.google.com/document/d/15CwNGJ9tPWJz826WYHd6ueVGIWN19UBGbqqKuARIm8o
Korinek, A. (2023). Generative AI for economic research: Use cases and implications for economists. Journal of Economic Literature, 61(4), 1281-1317. https://www.genaiforecon.org/JEL-2023-1736_published.pdf
Korinek, A. (2024). LLMs level up - Better, faster, cheaper. June 2024 update. https://www.genaiforecon.org/JEL-2024-June-LLMsLevelUp.pdf
Korinek, A. & Taliaferro, D. (2024). Generative AI for economic research. https://www.genaiforecon.org
Lastunen, J. (2024). AI for economists: Prompts & resources. https://sites.google.com/view/lastunen/ai-for-economists
van Quaquebeke, N. (2023). AI tools for research workflow in academia. https://docs.google.com/document/d/1mb4SWtqyi1iEGCn2uTnHkPHqW3UoQr8b0xv5_81a-4Y
Bibliography and Further Resources
General
APA Style Team (2025). Citing generative AI in APA Style. https://apastyle.apa.org/blog/cite-generative-ai-references
Athey, S. & Imbens, G. W. (2019). Machine learning methods that economists should know about. Annual Review of Economics, 11(1), 685-725.
Bowman, S. R. (2023). Eight things to know about large language models. arXiv. https://arxiv.org/abs/2304.00612
COPE (2024). Authorship and AI tools. Committee on Publication Ethics. https://publicationethics.org/cope-position-statements/ai-author
Goodfellow, I., Bengio, Y. & Courville, A. (2016). Deep learning. MIT Press. http://www.deeplearningbook.org
Lee, T. B. & Trott, S. (2023). Large language models, explained with a minimum of math and jargon. https://www.understandingai.org/p/large-language-models-explained-with
Microsoft (2023). Microsoft privacy statement. https://privacy.microsoft.com/en-US/privacystatement
MLA Style Center (2025). How do I cite generative AI in MLA style? https://style.mla.org/citing-generative-ai
Mollick, E. & Mollick, L. (2023a). Why all our classes suddenly became AI classes. Harvard Business Publishing Education. https://hbsp.harvard.edu/inspiring-minds/why-all-our-classes-suddenly-became-ai-classes
Mollick, E. & Mollick, L. (2023b). Student use cases for AI. Harvard Business Publishing Education. https://hbsp.harvard.edu/inspiring-minds/student-use-cases-for-ai
Mollick, E. (January 24, 2023a). The practical guide to using AI to do stuff. One Useful Thing. https://oneusefulthing.substack.com/p/the-practical-guide-to-using-ai-to
Mollick, E. (March 29, 2023b). How to use AI to do practical stuff: A new guide. One Useful Thing. https://oneusefulthing.substack.com/p/how-to-use-ai-to-do-practical-stuff
OpenAI (April 25, 2023). New ways to manage your data in ChatGPT. https://openai.com/blog/new-ways-to-manage-your-data-in-chatgpt
Wolfram, S. (2023). What is ChatGPT doing... and why does it work? Stephen Wolfram Writings. https://writings.stephenwolfram.com/2023/02/what-is-chatgpt-doing-and-why-does-it-work
Yang, J. et al. (2023). Harnessing the power of LLMs in practice: A survey on ChatGPT and beyond. arXiv. https://arxiv.org/abs/2304.13712
Zhao, W. X. et al. (2023). A survey of large language models. arXiv. https://arxiv.org/abs/2303.18223
Research ethics
Gatrell, C., Muzio, D., Post, C. & Wickert, C. (2024). Here, there and everywhere: On the responsible use of artificial intelligence (AI) in management research and the peer-review process. Journal of Management Studies, 61, 739-751.
Grimes, M., von Krogh, G., Feuerriegel, S., Rink, F. & Gruber, M. (2023). From scarcity to abundance: Scholars and scholarship in an age of generative artificial intelligence. Academy of Management Journal, 66, 1617-1624.
Hicks, M. T., Humphries, J. & Slater, J. (2024). ChatGPT is bullshit. Ethics and Information Technology, 26, 38.
Susarla, A., Gopal, R., Thatcher, J. B. & Sarker, S. (2023). The Janus effect of generative AI: Charting the path for responsible conduct of scholarly activities in information systems. Information Systems Research, 34(2), 399-408.
Videos
3Blue1Brown (2024). But what is a GPT? Visual intro to transformers. https://www.youtube.com/watch?v=wjZofJX0v4M
Karpathy, A. (2023). The busy person's intro to LLMs. https://www.youtube.com/watch?v=zjkBMFhNj_g
Karpathy, A. (2025). Deep dive into LLMs like ChatGPT. https://www.youtube.com/watch?v=7xTGNNLPyMI
Sanderson, G. (2024). Visualizing transformers and attention. https://www.youtube.com/watch?v=KJtZARuO3JY
Repositories
Calegario, F. (2024). Awesome generative AI. GitHub. https://github.com/filipecalegario/awesome-generative-ai
Google Cloud (2024). Generative AI. GitHub. https://github.com/GoogleCloudPlatform/generative-ai
Microsoft (2024). Generative AI for beginners. GitHub. https://github.com/microsoft/generative-ai-for-beginners
Reganti, A. N. (2024). Awesome generative AI guide. GitHub. https://github.com/aishwaryanr/awesome-generative-ai-guide
van Vaerenbergh, S. (2024). Awesome generative AI. GitHub. https://github.com/steven2358/awesome-generative-ai