The Art of Prompting in Speed Reading and AI

Introduction
The word prompt has quietly but powerfully embedded itself into the fabric of human cognition and communication. It is a word that signifies readiness, guidance and stimulation, whether initiating a thought, nudging action or setting the course for a machine’s output. In the age of artificial intelligence and information overload, especially within domains such as speed reading and human computer interaction, the concept of prompting has taken on new layers of significance. This blog explores the rich history, evolving applications and scientific grounding of prompting, culminating in practical lessons for readers and prompt engineers alike.

Defining “Prompt”: Etymology and Evolution

Etymology and Historical Usage
The English word prompt finds its etymological roots in the Latin word promptus, meaning “brought forth” or “ready”, derived from promere, a compound of pro (forward) and emere (to take or obtain). The word originally implied an action that brought something into view or readiness. By the mid fourteenth century, the English verb prompten meant “to incite to action” or “urge”. By the fifteenth century, the term had expanded its meanings to include “readiness”, “a hint or suggestion” and the act of reminding or encouraging.

Modern Definitions and Usage
In contemporary usage, prompt can function as a verb, noun or adjective:

As a verb: To elicit a response, encourage action or give a cue (e.g. “She was prompted to speak”).
As a noun: A stimulus, cue or instruction (e.g. “The actor forgot his lines and needed a prompt”).
As an adjective: Describes something done quickly or without delay (e.g. “Prompt action was taken”).

Prompting thus remains both linguistic and psychological, a way of initiating cognitive or behavioural response, making it particularly pertinent in education, AI and cognitive optimisation techniques such as speed reading.

Prompting in the Age of Artificial Intelligence

Prompting in AI: From Input to Intelligence
In artificial intelligence, especially with large language models such as ChatGPT, prompting has acquired a precise technical definition. A prompt is the initial input or query provided to the system, which frames the scope and direction of the AI’s response. In other words, prompting is the act of shaping a conversation or computational output through strategic verbal framing.

As Wolfe (2024) describes, the creative potential of generative AI is not autonomous but co constructed. It is the human prompt that defines, modulates and directs the AI’s otherwise generalised capability. Just as the quality of a question shapes the quality of a conversation, the quality of a prompt shapes the outcome of AI interaction.

The Rise of Prompt Engineering
Prompt engineering has emerged as a specialised skill set and area of research. It involves the deliberate crafting of prompts to optimise AI performance across tasks, from content generation to code development and data extraction. Techniques include:

Instruction based prompting (e.g. “Summarise this article”)
Chain of thought prompting (e.g. “Explain step by step”)
Few shot prompting (e.g. “Here are three examples”)
Multimodal prompting (integrating text with images or other data)

Poorly designed prompts can lead to “hallucinations” in AI outputs, fabricated or inaccurate responses. Conversely, well structured prompts increase relevance, coherence and ethical robustness (Chen et al., 2023).

Recent meta analyses, such as The Prompt Report (2024), which reviewed over 1,500 scholarly articles, confirm that reasoning based prompts, especially those that scaffold logic or include specific goals, tend to yield superior outcomes across cognitive and linguistic tasks.

A Structured Model for Prompt Engineering
One particularly effective approach to prompt engineering is based on a structured markdown framework that ensures clarity, context and purpose. This is especially useful when designing prompts for CustomGPTs or complex applications requiring nuanced responses.

Role: Define the role the AI should take. For example: “You are a cognitive psychologist helping someone improve their reading habits.”

Objective: Clearly state what you want the AI to accomplish. For example: “Provide evidence based strategies to enhance reading speed without losing comprehension.”

Context: Supply background information that helps the AI understand the scope. For example: “The user is preparing for postgraduate exams and struggles with slow reading and information retention.”

Instructions: Break down specific steps you want the AI to follow.

Instruction 1: Recommend three practical techniques for improving reading speed.

Instruction 2: Provide a summary of recent research findings related to reading cognition.

Instruction 3: Suggest how these strategies can be incorporated into a weekly study routine.

Notes:

Tailor language for a postgraduate audience.
Avoid overly technical jargon unless necessary.
Prioritise methods backed by peer reviewed studies.

This structure enables both human and machine to interact more efficiently and effectively, transforming vague queries into purposeful engagements.

Purpose Based Prompting Using the SMART Model
Another effective prompt engineering strategy involves using the SMART goal setting framework. This model helps clarify the intention behind a prompt, ensuring it is well defined and actionable. SMART stands for:

Specific: What exactly do you want the AI to do? Avoid vague language. For example: “Summarise the three main arguments in this article.”
Measurable: Can you assess the quality or completeness of the response? For instance: “Include no more than 150 words.”
Achievable: Is your request realistic given the AI’s capabilities? Complex computations or very abstract reasoning may not always yield reliable answers.
Relevant: Is the prompt aligned with your overall task or purpose? Unfocused prompts lead to unfocused responses.
Time bound: If necessary, specify time related constraints. For example: “Summarise the changes in the past five years.”

Using the SMART model can drastically improve the clarity and effectiveness of prompts in both academic and professional settings. It helps the user formulate purposeful prompts that the AI can execute with greater precision.

The Only Prompt You Need to Know

For those just beginning their journey with AI, or even for experienced users faced with a vague intention or creative block, there is one prompt that often unlocks surprising power and precision:

“Improve this prompt…[state what you need]”

By simply stating what you want in broad or imprecise terms and then asking the AI to improve your prompt, you activate a collaborative loop that refines intent, clarifies output, and often reveals better phrasing or structure. It is an elegant solution for overcoming uncertainty. For example:

“I want something about stress at work” → Improve this prompt.
“I need a plan for eating better” → Improve this prompt.
“Summarise this, I guess” → Improve this prompt.

This single strategy turns ambiguity into clarity. It is a meta prompt that empowers the user to prompt better—simply by prompting the AI to help.

Prompting and Speed Reading: Parallels and Cognitive Lessons
Speed reading is a discipline of cognitive efficiency. At its core, it involves directing mental attention to relevant parts of a text and reducing obstacles such as subvocalisation or regressions. In this context, we can think of reading techniques as internalised prompts, mental cues that frame and filter our engagement with information.

Comma Prompting and Structural Cues
One insightful parallel is comma prompting, a technique in speed reading where punctuation, grammar, and layout guide reading rhythm. Similar to how a prompt cues AI, comma prompting directs the human eye and mind towards meaningful clusters of content. This approach is closely related to chunking, where readers process text in meaningful units rather than individual words.

Setting a Purpose: The Human Prompt
Just as a prompt tells an AI what to generate, the act of setting a purpose before reading tells the brain what to notice, what to skip, and what to retain. Research in cognitive psychology confirms that goal-setting significantly enhances comprehension and retention (Lovebrain, 2024). Purpose acts as a metacognitive frame—an anticipatory orientation that primes the brain’s attentional system.

Scientific Research on Prompting and Speed Reading

Several studies and surveys have established the credibility of prompting as a cognitive tool:

Lovebrain (2024) demonstrated that structured cognitive training can triple reading speed while maintaining comprehension, particularly when priming techniques are embedded into the reading strategy.
Chen et al. (2023) showed that prompt-based instruction in LLMs mirrors how humans use context-setting strategies in reading.
Wolfe (2024) argued that prompt engineering not only optimises AI output but models new frameworks for human cognitive scaffolding.
Nature (2025) published a practical guide for academic prompting, noting its parallels with literature review skills such as scoping, sampling, and thematic synthesis.

These developments show that prompting is not only a technical skill but also a cognitive metaphor bridging human learning and machine intelligence.

Top Tips: What Speed Reading Teaches Us About Prompting

Set a Clear Purpose
Before reading or prompting an AI, clarify your goal. This reduces mental noise and sharpens focus.
Use Structural Cues
In reading, use punctuation and headings; in AI, use formatting and logical sequence to guide the model.
Chunk Information
Group words or ideas for faster comprehension. In prompting, break complex tasks into simpler, modular queries.
Minimise Distractions
Avoid regression and subvocalisation in reading. In prompting, eliminate ambiguity and overload.
Preview and Scan
Skim first to frame your focus—just like giving an AI background before a specific request.
Ask Questions
Questioning sustains engagement in both reading and AI. Direct queries yield clearer responses.
Practice and Refine
Both speed reading and prompting improve with iterative testing. Review your outputs and refine techniques.

Conclusion

Prompting sits at the intersection of language, cognition, and technology. From its Latin roots to its reinvention in the digital age, it remains a tool for initiating, guiding, and optimising action. Whether we are skimming a text at triple speed or coaxing meaningful output from a generative AI, the principles of good prompting—clarity, purpose, structure, and feedback—remain consistent. The mastery of prompting is thus not only a technological advantage but a cognitive one. It is the art of bringing forth readiness—promptus—for insight, speed, and creativity.

To prompt, or not to prompt

As prompting becomes a cognitive and technological superpower in both reading and AI, it seems only fitting to playfully reimagine the wisdom of past thinkers in the language of the prompt. After all, if prompting is about setting intention, framing inquiry, and directing consciousness (or algorithmic reasoning), then perhaps the great minds of history were simply early prompt engineers.

“To prompt, or not to prompt” — William Shakespeare
A timeless question, updated for the age of language models and mind hacks. Shall we engage with clarity, or drift into mental noise?

“I prompt, therefore I am” — René Descartes
If thought affirms existence, then intentional prompting affirms creative agency.

“In the beginning was the prompt” — The Bible, Genesis
Before creation, there was the Word. In our modern genesis, it begins with a well-phrased input.

“Ask not what your prompt can do for you — ask what you can do for your prompt.” — John F. Kennedy
The AI revolution calls for responsibility. The quality of our prompts reflects our intent, ethics, and clarity.

“All the world’s a stage, and all the men and women merely prompts.” — William Shakespeare (almost)
Perhaps we are all scripts in one another’s dialogues, shaping each other’s narratives by suggestion.

Watch this video on The Prompt Theory

“To err is human, to prompt, divine.” — Alexander Pope
Prompts refine our imperfections, elevating both human and machine understanding.

“The map is not the territory, but the prompt can shape the map.” — Alfred Korzybski
While symbols and representations are not reality, the right prompt can reframe perception and meaning.

“There is no failure, only feedback — and every prompt is an opportunity to learn.” — NLP presupposition
In the dance of cognition, each misstep is a rehearsal for mastery. Every prompt offers data, direction, and growth.

“People have all the resources they need, and every prompt can unlock them.” — Another NLP presupposition
Just as a good question can open the mind, a strong prompt can activate inner capacities and external tools.

“We shape our prompts, thereafter they shape us.” — Winston Churchill (reimagined)
In the age of generative technologies, this twist on Churchill’s insight reminds us that the tools we design—linguistic or digital—come to design us in return.

This light-hearted homage serves as a reminder that the power of the prompt is not just computational but existential. Whether guiding thought, influencing behaviour, or co-creating with AI, the prompt is the invisible architecture behind awareness and agency.

References

“Unleashing the Potential of Prompt Engineering for Large Language Models” by Chen, X., Zhang, Y., Liu, S., & Wu, J. (2023), available at https://arxiv.org/abs/2302.11382

“Accelerating Reading Speed Without Compromising Comprehension: A Cognitive Training Approach” by Lovebrain, H. (2024), available at https://lovebrain.com/studies/accelerating-reading-speed-without-compromising-comprehension-a-cognitive-training-approach

“Prompt Engineering in ChatGPT for Literature Review: Practical Guide” (2025) in Scientific Reports, available at https://www.nature.com/articles/s41598-025-99423-9

“Tell Me Your Prompts and I Will Make Them True” in Open Praxis (2024), available at https://openpraxis.org/articles/10.55982/openpraxis.16.2.661

“Modern Advances in Prompt Engineering” by Wolfe, C. R. (2024), available at https://cameronrwolfe.substack.com/p/advanced-prompt-engineering

“A Systematic Survey of Prompt Engineering in Large Language Models” (The Prompt Report, 2024), available at https://arxiv.org/abs/2403.04561

5/5 - (6 votes)