Prompt Lab #3: Human-Centered Writing Feedback
How to use AI to encourage more human-centered writing in the workplace or classroom
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.
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.
Keep reading with a 7-day free trial
Subscribe to Cyborgs Writing to keep reading this post and get 7 days of free access to the full post archives.