This post is the reference handout for my ConVex 2026 presentation, “Evidence-Based Prompt Design for AI Writing Systems,” and a follow-up presentation later this week at Information Energy 2026. If you weren’t in either room, everything here is designed to stand on its own.

When an AI system produces a bad answer, most practitioners rewrite the prompt. Sometimes that fixes it. More often, the problem is somewhere else entirely, and without a diagnostic framework, you’re guessing. What follows is a practical framework for figuring out which layer broke before you start changing things.

Most evaluation treats an AI writing system as having two parts: the prompt and the knowledge base. That framing misses a layer that fails constantly and gets blamed on the other two.

There are really three layers, each with its own failure modes.

The prompt layer governs behavior. It holds the instructions, constraints, definitions, and facts the model needs for every interaction. This is content and information too critical to depend on retrieval.

The knowledge base holds content that’s only relevant to specific queries, such as detailed procedures, tool descriptions, location-specific data, anything too voluminous to keep in the prompt without degrading performance.

The retrieval layer connects them. A RAG system pulls knowledge chunks based on query relevance, which means a piece of information only surfaces if the query is similar enough to retrieve it. An MCP server gives AI tools for creating or accessing knowledge.

The practical decision rule: if a missed retrieval would cause a serious failure, the information belongs in the prompt. If it’s only needed for specific queries, it belongs in the knowledge base.

When something goes wrong, the first question isn’t “how do I fix the prompt?” It’s “which layer is this coming from?”

Why information types help

Many practitioners who structure their prompts at all are working from intuitive categories, such as role, context, output format, rules. Or it could be whatever structure an AI suggested when they asked for help.

Those categories aren’t wrong, but they’re ad hoc. They don’t derive from how knowledge actually functions, so they don’t give you consistent criteria for evaluating whether the prompt is doing its job.

Information types provide a more principled heuristic: Task, Concept, Reference, Principle, Process. Each type reflects a genuinely distinct mode of knowing.

Definitions work differently from procedures. Procedures work differently from conditional rules. Conditional rules work differently from facts. Mixing them in the same block makes the prompt harder to evaluate because you can’t tell which kind of content failed when something goes wrong.

I’ve spent the past semester applying information types to RAG knowledge bases, structuring content so each chunk does one job cleanly and retrieval has a better chance of surfacing the right thing.

I’ve been wondering, though … if typed structure improves retrieval, does it also improve the reliability of the instructions themselves?

The short answer appears to be yes. The longer answer will be coming soon and involves Aristotle’s five intellectual virtues from Nicomachean Ethics.

For now, here is the practical framework I’m playing around with for evaluating prompt design.

Adapting Prompts for Disaster Communication

The materials below work through the prompt layer using a student-built disaster communication chatbot as the test case. For a recent grant, my students and I are designing chatbots to help UNCW students with disaster awareness. This specific use case is for preparing family communication plans before, during, and after hurricanes.

Real use case, real stakes.

The original student prompt was built around a [ROLE] structure that is probably the most common way of thinking about system instructions.

The research on role prompting is fairly clear. Persona instructions adjust style, not accuracy. Telling a model it is a “calm, empathetic hurricane communication expert” doesn’t make it more accurate about evacuation zones. It might make answers sound more reassuring, which in a disaster communication context is arguably worse than neutral if the information isn’t good.

The revised prompt replaces [ROLE] with a structure built on information types. Each block has a specific job. None of them bleeds into another.

One addition worth naming: a [METADATA] block at the top. Purpose and audience aren’t a Concept, which explains what something is so a reader can understand it.

Purpose and audience are configuration. They declare what the assistant is, who it serves, and on what authority. Naming them that way is more honest than forcing them into a role block that encourages the AI to “imagine” some human role it can’t actually fulfill.

The [REFERENCE] block holds only always-on facts, like the signup code, the Safe and Well URL, the broadcast stations. These need to be present for almost every interaction and a retrieval miss on any of them would be a serious failure. Detailed app descriptions moved to the knowledge base, where they can be retrieved when a user asks about something specific.

The revised prompt

[METADATA]

Assistant: Hurricane Communication Planner
Audience: UNCW students and New Hanover County residents
Scope: Family communication preparedness before, during, and after
hurricanes and evacuations
Sources: New Hanover County Emergency Management, UNCW emergency
systems, FEMA, American Red Cross

Configuration, not instruction. Declares what the assistant is, who it serves, what it covers, and where its information comes from. Unlike a role block, it makes no behavioral claims. Those come later, in [PRINCIPLE] and [PROCESS].

[REFERENCE]

These facts are critical to nearly every interaction and must be
treated as authoritative regardless of what the user asks.

New Hanover County Emergency Management — A Wilmington-based agency
that coordinates local, state, and federal resources, manages
evacuation shelters, and maintains the county's emergency operations
plan.

Emergency Alert System (EAS) — Broadcasts imminent threat
notifications to the public via radio and television.

Wireless Emergency Alerts (WEA) — Short emergency messages broadcast
from cell towers to WEA-enabled devices by authorized government
partners.

New Hanover County alert signup — Text READYNHC to 24639.

Red Cross Safe and Well registry — safeandwell.communityos.org

NOAA Weather Radio — weather.gov/nwr

Local broadcast: WECT

In Case of Emergency (ICE) — A contact designated in your phone as
an emergency contact. Emergency personnel routinely check ICE
listings first.

Note: Detailed descriptions of the FEMA app, Red Cross Emergency
App, UNCW Alert App, and UNCW Mobile App are maintained in the
knowledge base. Retrieve them when a user asks specifically about
those tools.

Reference holds only always-on, high-stakes facts. These are things that must be present for every interaction regardless of what the user asks. The signup code and Safe and Well URL are here because a retrieval miss on either sends a user away without the most critical information. Detailed app descriptions are in the knowledge base because they’re only needed when someone asks about something specific. The note at the bottom makes that boundary explicit.

[CONCEPT]

A family communication plan is a pre-established set of agreements
about how family members will reach each other, confirm safety, and
make decisions when normal communication channels are unavailable or
unreliable. It typically includes designated contacts, check-in
schedules, backup communication methods, and pre-arranged meeting
points.

An out-of-area contact is a person located outside the affected
region who serves as a central point of contact for family members
to check in with. Local lines often overload during a storm; calls
to and from outside the area are more likely to connect.

A safe word is a pre-agreed word or phrase family members use to
confirm identity during chaotic or high-stress situations where they
may be communicating through unfamiliar channels.

Communication failure during a hurricane typically results from
power outages disabling cell towers, network overload from high call
volume, or physical infrastructure damage. Plans should assume at
least one of these will occur and include methods that don't depend
on the cellular network.

Concept content defines terms the model needs to “understand” before it can respond accurately. Without this block, the model falls back on its training-shaped understanding of terms like “family communication plan.” These definitions bring its working understanding into alignment with the specific context. They belong in the prompt, not the knowledge base, because the model needs them to reason correctly about almost any question, not just the ones that trigger the right retrieval hit.

[PRINCIPLE]

Match response length to urgency. A user asking during an active
storm needs shorter, more direct answers than one planning ahead
in June.

Do not speculate about storm timelines, weather patterns, evacuation
orders, or road closures. Refer users to New Hanover County Emergency
Management or local news for these.

Do not provide guidance outside the communication scope — no medical,
legal, mental health, or physical safety advice. Acknowledge the
concern briefly and redirect to the appropriate resource.

Every recommendation must be traceable to a source listed in
[REFERENCE] or retrieved from the knowledge base. Do not fill gaps
with reasonable-sounding information drawn from general knowledge.

When information is uncertain or unavailable, say so and point to
the closest official resource.

Do not recommend paid apps, devices, or third-party services without
noting they are not official endorsements.

“Calm, empathetic, and concise” has become “match response length to urgency.” The former is a style claim, which is vague, unverifiable, and doing the job a role block would do. The latter is a conditional behavioral norm: testable, specific, and written as a Principle should be. Every entry here follows the same pattern: under a specific condition, do a specific thing.

[TASK]

Help users create or update a family communication plan, including
designating emergency contacts, establishing check-in frequencies,
and identifying backup communication methods.

Help users sign up for and understand emergency alert systems —
New Hanover County alerts, UNCW Seahawk Alerts, the FEMA app, and
the Red Cross Emergency App.

Guide users in establishing protocols for communication failures —
out-of-area contacts, safe words for identity verification,
pre-arranged meeting points, and registration with Red Cross Safe
and Well.

Explain what to do when digital communication is unavailable —
battery-powered radios, NOAA Weather Radio, walkie-talkies, and
local broadcast stations such as WECT.

Each entry is specific enough to derive a test question from directly. “Help users sign up for New Hanover County alerts” should produce a response that references READYNHC to 24639, cites the source, and nothing else. If it doesn’t, you know exactly which task failed, and which layer to examine first.

[PROCESS]

Greet the user and ask an open-ended question to assess their
situation and needs.

Offer a clear starting point: "Do you have a quick question, or
would you like to build a communication plan together?"

If the user has a quick in-scope question: answer it, cite the
source, and offer a follow-up before closing.

If the user's question falls outside scope: acknowledge it briefly,
explain you can't help with that specific issue, and point to the
appropriate resource.

If the user wants to build a plan: ask 1–2 questions to personalize
the guidance (UNCW student or county resident? Planning ahead or
active storm?), then work through contacts, alert signups, backup
methods, and meeting points in that order.

Close each interaction with a summary of what was planned or
answered, the sources used, and: "If you have more questions, I'm
here. Stay safe."

Process sequences how a conversation should unfold. Each branch point is named explicitly, and each branch has a resolution. When the model deviates from this sequence in testing, the process block gives you a specific place to look, either the step is underspecified, or a Principle is overriding it. That’s a diagnosable problem.

The evaluation rubric

Apply this rubric to the prompt before generating a single response. The goal is to catch type collapse, type contamination, and critical gaps at the design stage rather than discovering them through inconsistent outputs.

Score each criterion as Met / Partially Met / Not Met, and note specific evidence from the prompt text. Any “Not Met” on a Reference fact, a Principle consistency check, or a Process branch resolution should be treated as an issue to be fixed before deployment.

Coming soon, I’ll be exploring why these five types, what they correspond to in Aristotle’s five intellectual virtues, and what that tells us about where AI assistance ends and human judgment must begin. The Greeks had sharper vocabulary for this problem than we do.

If you have questions or want to share a prompt for the group to look at, bring it to the Content Lab discussion thread on this post!

Last week’s post on agent skills made the case that most AI skills underperform because they’re written as a single type of content. Task information alone. A well-performing skill actually contains several types of information, each signaling a different purpose to the model.

Below you’ll find the revision of my weekly plans skill that I use to create weekly plans for my classes that help students (and myself) know what were are doing for the week.

A few things to watch for as you read through:

The Concept block is the section most likely to be missing from skills you’ve already built. It’s also the one that does the most work before a single step gets executed.

This is where you define exactly what it is you want the AI to produce … and any other ideas that need to be defined and customized to your context.

The Principle section consolidates constraints that were scattered in the original. Grouping behavioral rules in one place helps the model identify them as actual rules. When the same rules are embedded in a procedure, its more likely that they will be conflated with tasks.

The description field in the front matter is Reference information, and it’s one of the most consequential sections in the entire file. If the skill isn’t triggering when you expect it to, that’s where to look first.

The skill itself is adapted from my Writing with Machines course and designed to be modified. If you build something from it, I’d genuinely like to know what you changed and why. That’s what makes this a lab!

Note: I used markdown for this “skill prompt” because that is what Claude typically uses. I’m thinking about testing this against an XML version in the near future.

Subscribe now

Read more

I’ve been calling this section “Prompt Lab” since I launched it, but I’m changing the name to Content Lab.

The reason is sitting right inside this post: what I’m exploring has quietly outgrown prompt mechanics.

It’s become about knowledge design, genre, communication systems — the whole environment in which a prompt lives.

The prompt is often the last thing I write now, not the first.

For content professionals and technical writers, that shift matters. We've always known that good content doesn't start with writing. It starts with architecture. Information types, audience analysis, structured authoring, content strategy.

Here is what I mean.

The Meta Problem

The students in my AI writing class have been struggling with something I didn’t anticipate. The assignment asks them to analyze their AI-assisted writing process and document their findings, which includes the prompts they built and what they learned from them.

Straightforward enough, or so I thought. But I ran into a consistent problem.

Students would revise their prompts. They’d revise their notes. But they wouldn’t revise how they were communicating their findings to an outside audience.

They were writing for themselves, not for a reader who needed to understand what they did and why it mattered.

When I dug into it, I realized I was asking them to do something genuinely difficult — not just create a prompt, but produce a professional document about the process of creating one.

That’s a meta-cognitive task. And it requires knowing what genre you’re working in.

After talking with students, I realized some had never been introduced to genre as a concept for professional writing.

English majors generally fared better, not because they’re stronger writers, but because they had a conceptual vocabulary for what I was asking. They could name the shape of the document before they built it.

You might think: “Well, why didn’t students just use AI to help them figure out the right genre?”

Because if you don’t know what genre you need (or what genre even is as a functional concept), you don’t know what to ask for.

Genre knowledge has to exist in your head before it can inform your collaboration with an AI. It’s not a skill you can offload.

So I built a Claude app to help.

Building a Genre Coach Solution

The prompt I’m sharing below is a writing coach that gives students exactly two specific revision actions to move their draft toward professional case study format. It identifies

• where description has replaced analysis,

• where evidence is missing, and

• where the reasoning behind AI choices is vague.

Then it shows students a before-and-after example using their own words, so the feedback is immediate and concrete.

But I want to be clear, I didn’t write it in a vacuum. I drafted it inside my Claude project for this class, which contains my course materials, my genre presentation, my assignment descriptions, and my own running reflections on how the class has been going.

Claude wasn’t just following instructions. It was working from a situated context build around my course, my students, and my specific pedagogical problem.

That’s a different relationship to prompting than I had even a year ago. I’m not just writing better prompts. I’m building better environments, and the prompts emerge from those environments almost naturally.

Your knowledge base has become as important as your prompting technique — maybe more so. A mediocre prompt inside a rich, well-structured project context will often outperform a brilliant prompt written cold.

The work that happens before you open the chat window is where the real leverage is.

This has gotten me thinking … if genre knowledge is a prerequisite for effective AI collaboration, what other conceptual frameworks are quietly limiting what we can do with these tools?

For content professionals, I'd argue the answer is already in our toolkit — information typing, structured authoring, audience modeling.

The field has been building toward this kind of AI-ready thinking for decades without knowing it.

I'd love to hear what you're seeing in your own work. Where is your content expertise giving you an edge, and where are you still running into walls?

System Prompt: Writing Genre Coach

I'm running this as a Claude app inside my AI writing course project, which means it already has context about my assignments, my students, and what a finished case study should look like.

Students paste in their draft and get two specific, actionable revision notes back — no vague feedback, no overwhelming list of changes.

If you're teaching writing or working with teams who need to document processes and decisions, you could adapt this easily.

Just swap out the case study definition for whatever professional genre your context requires, and feed it any relevant background materials you have. The tighter your project context, the more targeted the feedback gets.

Read more

This taxonomy emerged from Fall 2025 user research conducted by students in our disaster communication project, and illustrates how I’m using taxonomies to organize and structure AI collaboration. Working with the New Hanover Disaster Coalition, students interviewed UNCW students about food security needs during disasters, conducted usability testing on existing emergency documents, and ran card-sorting exercises to understand how people naturally categorize disaster preparation information.

The taxonomy you see below builds directly on student work but has been adapted and refined using an MCP data modeling tool and AI to demonstrate how research-based categorization translates into structured content organization—which then becomes the foundation for knowledge graphs that AI systems can use reliably.

Interested in exploring this in your own work? Check out my course, Writing with Machines. Now available for paid subscribers.

Subscribe now

This taxonomy synthesizes work from Fall 2025, when students in ENG 404 (Advanced Professional Writing) and CSC 302 (Intro to AI) collaborated on the foundation for a disaster relief chatbot. ENG students conducted user research with UNCW students about food security during disasters, created taxonomies based on that research, and prepared source documents. CSC students built initial knowledge graphs using Neo4j tools.

This semester, ENG 326 and CSC 322 continue that work by developing functional chatbots. This taxonomy organizes the project so teams can divide the work systematically.

What is a taxonomy and why does it matter?

A taxonomy is a classification system that organizes information into categories and subcategories. You encounter taxonomies constantly—the folder structure on your computer, the way a grocery store organizes aisles, the categories on a news website.

For AI systems, taxonomies matter because they determine how information gets structured, stored, and retrieved. A chatbot answering questions about disaster preparedness needs to “know” that generator safety relates to power outages, which relates to food spoilage, which relates to health risks. Without an organizing structure, the chatbot has no map for navigating these connections.

The taxonomy below divides disaster preparedness into domains and specific topics. Each team will own one topic, becoming the experts responsible for gathering authoritative information, structuring it for AI use, and building a chatbot that handles questions in that area.

Taxonomy: Broad Disaster Preparedness Coverage

How teams will use this taxonomy

Each team receives one topic from the taxonomy. Over the semester, teams will:

Identify and collect source material. Find authoritative sources (CDC, FEMA, Red Cross, etc.) that address your topic. The Fall 2025 classes prepared some text files already—check there first, then supplement as needed.

Structure the content. ENG students will extract key information and organize it into a consistent format—concepts, tasks, rules, warnings—that works well for AI retrieval. This structured content feeds both your team’s chatbot and a shared repository.

Build and test chatbots. CSC students will build two versions: one without a knowledge graph (baseline) and one with a knowledge graph built from the structured content. Teams will compare performance to see how structured knowledge affects accuracy.

Contribute to the larger project. Your structured content joins a shared repository. Even though each team builds a focused chatbot, the combined work creates a foundation for a more comprehensive system—whether integrated this semester or built upon in future classes.

Authoritative sources by domain

A note for paid subscribers: You’re getting early access to this prompt before the main post goes live. This is part of what makes your support so valuable—you see behind the scenes of how I’m developing content and experimenting with AI systems.

On that note, I’ve been revising my PromptOps course into something more foundational called Writing with Mac…

Read more

Yesterday, while introducing microessays to my ENG 306 students, I had one of those teaching moments that clarified something I've been wrestling with in my own AI content work.

I was explaining my approach to AI in the classroom—that I'm not against it, and students are welcome to experiment, but I strongly discourage using AI to generate microessays.

You have to learn what makes a good essay yourself before you can effectively direct AI to create one. I suggested other AI applications—topic generation, feedback on drafts—but emphasized that students need to write their own microessays.

As I said this, a realization hit me that connects directly to the content scaling challenges many of us face: AI can help us scale our content, but we first have to know what content we’re scaling. We need solid content to scale.

Subscribe now

The whole point of microessays is to explore and test ideas in social spaces.

Technically, you can do this in an AI chat, but you're mostly playing around with other people's ideas—or ideas that emerge from the AI's pattern-matching processes.

Writing your own microessays allows you to experiment with your own thinking while exploring different approaches to expression that might not be possible within an AI's constraints.

This insight applies directly to content operations. Yes, AI is incredibly useful for scaling content—it's part of what I do regularly. But you have to have a foundation of authentic content to scale. That means putting in the reps, developing your own ideas, and creating the microcontent that becomes your raw material for AI collaboration.

Through my work on a prompt library for writing studies scholars, I've been testing exactly this approach: how do we maintain authenticity when collaborating with AI by providing it with our genuine thinking as building blocks rather than asking it to generate content from scratch?

So I thought I would share this new and improved version of this prompt.

This modular approach draws directly from what we know works in technical communication. Just as we've long used structured authoring and reusable content blocks to improve both efficiency and consistency, we can apply these same principles to AI collaboration.

The prompt I'm sharing below operationalizes this approach through structured semantic blocks that teach writers to systematically apply classical rhetorical principles when transforming their microcontent into larger pieces.

I'm curious to hear how this aligns with your own experiments in maintaining authenticity while leveraging AI's synthesis capabilities.

This structured prompt and analysis are available to paid subscribers as part of ongoing Content Lab research. Paid subscribers also get access to the complete prompt library, detailed implementation guides, and early previews of content that translate writing and rhetoric research into practical content operations.

Read more

In my previous post about transforming study abroad notes, I showed how Information Typing converts messy paragraphs into structured, AI-ready content.

Now you can see the complete transformation. I would love to hear your thoughts on any changes you would make.

Below is my full Krakus Mound entry, restructured using Precision Content's five information types.

Notice how each section serves a specific purpose:

• Reference blocks for facts you need to know

• Concept blocks for ideas you need to understand

• Principle blocks for guidelines to follow

• Process blocks for workflows, and

• Task blocks for step-by-step actions.

This structure makes information easier for both humans to scan and AI systems to understand and retrieve accurately.

Read more

As I work on Lesson 7 of my PromptOps course about temperature and style in AI writing, I wanted to share some prompt blocks I've been using to test different ideas.

First, a quick primer: Temperature in AI writing controls how strictly the AI adheres to common patterns when selecting words.

Low temperature means it consistently picks the most probable w…

Read more

This post is part of my preparation for my upcoming webinar on leveraging AI for ADHD scholars, something I’ve been thinking about lately

Read more

Prompt Lab is a sub-section of Cyborgs Writing. If you don't want to receive prompts, you can unsubscribe to this sub-section and still get Cyborgs Writing key posts. See your Substack settings.

Read more

As a professor juggling various responsibilities, I've often overlooked the potential of AI in email management. University security measures and the nuanced nature of academic correspondence made it a low priority. However, as I've delved deeper into interconnected AI systems, I've developed a prompt for an email assistant t…

Read more

Conferences are fantastic for learning, but how do you make those precious insights stick around? Too often, I just toss the notebook in a box and forget about it.

I recently attended ConVex, an industry conference focused on information and content development.

I really wanted to dive into what people are saying about AI in our field. I took notes design…

Read more

In my latest video, I walk you through my system for creating a super-personalized knowledge base using AI.

I show how I’m creating a unique mix of note-taking tricks and AI prompts that help me organize ideas for maximum creativity.

Let's make those writing robots work for us!

Subscribe now

What…

Read more

This semester, I realized that I use personas a lot. When I asked if students had ever heard of personas, a few students raised their hands because they had done them in a previous class of mine. 😆

It appears that I've developed a reputation for my love of persona-based learning!

For those unfamiliar with the concept, personas a…

Read more

You're a professional writer or content manager, and you suddenly face a towering pile of content pieces you need to review and provide feedback on.

For most of my readers, it is probably easy to imagine this scenario.

Each piece represents a team member's effort, their understanding of the subject, and their progress. Each one deserves your attention and constructive feedback. But the sheer volume is daunting.

How can you provide meaningful feedback on each one before the next deadline?

In the past, you may have had limited options: choosing not to provide any feedback is not a practical choice in a content-driven business.

You could comment on a handful and hope team members apply those comments to their own pieces, but that's not ideal either.

Or you could stay up late into the night, over-working yourself to the bone to get as much feedback in as possible.

Faced with these challenges, how can you ensure that every piece of content receives the attention and feedback it needs?

The answer may lie in a blend of ancient technologies and new: rhetoric and artificial intelligence.

Share

Structuring a Feedback Prompt

Harnessing the potential of artificial intelligence (AI) in writing isn't just about using AI-powered tools. It's about understanding how to guide these tools to produce the most useful results, using your rhetorical awareness.

Structuring prompts can replicate your feedback process, integrating your rhetorical knowledge with AI’s algorithmic power.

This is what I recently did to handle a stack of Substack posts that I wanted to help students with in a short amount of time.

Here's my process:

Draft Context Prompt Blocks: I begin by drafting context prompt blocks. These are short, concise prompts that provide the AI with the context for the task at hand. These prompts can range from the subject to the tone of the writing, and they help guide the AI in the right direction.

[ROLE] You are an editorial assistant helping new writers become successful in online spaces like Substack, Medium, and LinkedIn. You know that human-centered writing is the key.

[GOAL] Provide feedback for online writers to help them create more human-centered writing that will engage audiences and impress online editors.

Provide a Content Block: Next, I provide a content block that includes human-centered guidelines. In my case, I used Medium's human-centered guidelines as a starting point. Initially, I cut and pasted these guidelines, but I found they were too long and unwieldy. So, I used ChatGPT to condense them into a smaller, more manageable block that is not only more reusable but also easier for the AI to process.

[GUIDELINES] When reviewing or giving feedback on articles and blogs, consider these core principles to identify high-quality, human-centered content:

Content Distribution Categories: Understand whether the article falls into High-Priority, General, or Niche Content. Regardless of the category, ensure that the content is accessible through multiple channels like search engines and social media.

Reader Impact: Assess if the content enriches the reader emotionally, practically, or intellectually. It should evoke emotions like laughter or wonder, offer useful insights, or make the reader feel less isolated.

Originality and Authenticity: Look for unique perspectives or overlooked aspects of a subject. Make sure the content is human-created and not machine-generated to preserve nuance and authenticity.

Author’s Credibility: Does the author have relevant experience or expertise on the topic? The content should reflect the author’s depth of knowledge and genuine care for effective communication.

Craftsmanship: Evaluate the article’s narrative structure, editorial coherence, and grammatical accuracy. Check if the length is appropriate for the content’s purpose, and if visual and formatting elements add value.

Lasting Impact: Consider if the article compels you to share it, or if its insights remain with you long after reading. This is a strong indicator of high-quality craftsmanship and content impact. By keeping these principles in mind, you can effectively identify articles and blogs that not only meet quality standards but also resonate deeply with readers.

Describe the Task and Process: After setting the context and providing the content guidelines, I describe the task and the process for analyzing the writing. This involves detailing what the AI needs to look for and how it should go about it. This step is crucial in ensuring that the AI understands its task and can produce useful feedback.

[TASK] Provide 3 concise paragraphs of feedback with specific suggestions. You should give at least 2 very specific suggestions that reference a part of the text.

[PROCESS] 1. Read the text. 2. Analyze how well the text adheres to these guidelines. 3. Write a full analysis 4. Summarize your analysis in 3 paragraphs, directed to the writer.5. Incoporate my notes where apprpriate.

Enter Notes: I then provide a content block that contains any notes I have from my own reading. This helps personalize the AI-generated feedback. After signaling the end of the prompt (###), I paste the draft.

[NOTES] The blog starts off with a great hook, but doesn't keep that engagement throughout.

###

- Paste draft here -

Full Analysis, Then Summarize: I've found that the best approach is to let the AI do a full analysis first, and then summarize its findings into a three-paragraph note. This allows the AI to "think" freely or compute the content in depth before condensing its analysis into a concise, easy-to-understand format.

This process of developing a structured prompt is a powerful way to leverage AI in writing. It allows you to guide the AI for producing targeted, actionable feedback, making it an invaluable tool in managing the overwhelming demands of content review and feedback.

Fear not humans, we still need you.

Reflecting on this process, it's clear that AI-generated comments can be a significant change in content review and feedback. When I compare the comments generated by AI to those I could manually write in the limited time I have, the difference is striking.

AI-generated comments are deeper, more targeted, and more actionable. They delve into the content with a level of detail that I simply couldn't achieve manually within the same timeframe. They pinpoint specific areas of improvement and provide clear, concise suggestions for enhancement.

Here is a simulated version of an output I really liked (not associated with a specific student paper).

Your draft skillfully unpacks the complexities of digital dependency, detailing both the design elements that make apps addictive and the mental consequences of constant device interaction. However, to make the article more human-centric, consider adding personal anecdotes or examples that illuminate the emotional or mental strain tied to this issue. While you mention that people become anxious without their gadgets, going deeper with a specific story could lend emotional gravitas to your argument.

Your writing is fact-rich and well-structured, which adds credibility. To increase reader engagement, you might think about infusing more of your own voice or style into the article. For instance, you kick off with a catchy term that sets a conversational tone. Carrying this tone throughout the piece could resonate with readers who appreciate a mix of personal insight and hard information.

Lastly, while you cap off the article by emphasizing the need for controlled digital usage, you don't provide any actionable steps for achieving this. Given your effective outlining of the issue, readers would likely welcome some practical solutions. Tips for managing device use, like using monitoring software or designating tech-free areas at home, could round out your article while empowering your audience.

I must admit, it's humbling to see that AI can do a better job than I can when dealing with a large volume of content. But it's important to note that this isn't about AI replacing human input. Rather, it's about AI augmenting our capabilities. The AI can only produce such high-quality feedback because of the expert fine-tuning I provide through the structured prompt.

Also, using AI ensures that all content pieces get the same amount of focus. When writing comments manually, it's natural to lose steam as time goes by, and the quality of the comments can decline. But with AI, each piece of content gets the same level of attention, regardless of whether it's the first or the last in the pile.

So, whether you're an educator dealing with stacks of student papers or a content manager juggling multiple pieces, consider integrating AI into your feedback process.

It's a win-win situation: you can provide better, more consistent feedback in less time, and your students or team members get the constructive input they need to improve their writing.

Embrace the potential of AI and see how it can transform your writing classroom or content creation process.

Paid Subscriber Bonus: This post was a perfect opportunity to experiment with a new AI tool and workflow. You can get a sneak peek in the video below.

Subscribe now

Read more

Do you ever feel like the prompts you come across are too generic?

I totally get it! What's the point of making a prompt if it doesn't connect with your specific context?

Read more

Rob Lennon is a well-know content creator who calls himself the “AI Whisperer,” but his approach to crafting prompts gets a bit silly … asking AI to be “the best writer in the world” or “you have free reign to be creative.” AI will take a good guess at these vague words, but doesn’t really know what these mean.

A structured approach defines these element…

Read more

I'm coaching high school students this summer with District C. They get the chance to solve a problem for a real business partner using design thinking. In my recent teamship, I noticed that the last day of team work can be difficult, because students think they are “done.”

Dress rehearsal can help students realize this fact, but you need to ask good qu…

Read more