Note: This guide is about using generative artificial intelligence (GenAI) as a drafting and editing tool when writing. For a general introduction to AI tools and prompt engineering, please consult Artificial Intelligence - A Student Guide.
Since 2022, new GenAI writing technologies called Large Language Models (LLMS) have been available for public use. Popular examples include ChatGPT (OpenAI) and Claude (Anthropic). LLMs are driven by mathematical algorithms. While they can't truly think for themselves, because they are trained on enormous data sets, they are capable of drafting sophisticated texts on the basis of probability. In other words, much like humans, LLMs learn how to write by reading other writing and replicating the structures, patterns, and choices they encounter. Unlike humans, however, LLMs have no true understanding of what they have written, how, or why.
The writing process traditionally involves brainstorming ideas, planning/outlining, drafting content, revising for clarity and coherence, proofreading for grammar and style, and finalizing after feedback. It is rarely linear, often involving returns to earlier stages throughout a project's lifecycle. The writing process requires a significant investment of time and energy and relies heavily on individual creativity, knowledge, and skill. Because of this, writing by oneself--while also writing for other readers, such as peers and instructors--remains one of the most powerful technologies for learning, thinking, and communicating.
GenAI has begun to transform writing by automating aspects of content creation. Writers can now prompt brainstorming, generate drafts, overcome creative blocks, explore alternative phrasings, and refine content through AI collaboration. This has accelerated timelines, democratized content creation, and shifted the writer's role toward strategic direction and thoughtful editing rather than producing every word from scratch.
While these technologies hold promise for efficiency and accomplishment, they also pose some risks to students' ability to learn as well as writers' ability to think for themselves (Vee 2023). In such an environment, critical engagement with AI inputs and outputs becomes crucial to learning, just as establishing ethical processes for writing with GenAI becomes essential to upholding academic integrity.
One productive way to approach the role of GenAI in student writing is to explore its potential as a new evolution of the old writing process, in which "prompt-engineering, output curation, fact-checking, and revision" (Graham, 2023, p. 166) become indispensable skills.
Pigg (2024) has found that "requesting, evaluating, and refining" are "three categories of practice that describe research writers' interactions with generative AI across research design, writing research genres, and proofreading and editing research communication" (p. 2). The Generative AI Writing Process Guide adapts her research to suggest a three-step process for writing with LLMs.
When writing with GenAI, MacEwan students should keep in mind the following principles.
Ghimire, A. (2025). Utilizing ChatGPT to integrate world English and diverse knowledge: A transnational perspective in critical artificial intelligence (AI) literacy. Computers and Composition, 75, 102913. https://doi.org/10.1016/j.compcom.2024.102913
Graham, S. S. (2023). Post-process but not post-writing: Large language models and a future for composition pedagogy. Composition Studies 51(3), 162-168. https://eric.ed.gov/?id=EJ1390327
Pigg, S. (2024). Research writing with ChaptGPT: A descriptive embodied practice framework. Computers and Composition, 71, 102830. https://doi.org/10.1016/j.compcom.2024.102830
Vee, A. (2023). Large language models write answers. Composition Studies, 51(1), 176-181.
