Sidecar Sync

7 AI Strategies to Revolutionize Your Content Writing | 45

• Amith Nagarajan and Mallory Mejias • Episode 45

Share episode

Send us a text

In this episode of Sidecar Sync, Mallory dives into the transformative potential of AI-assisted content generation, focusing on text and copywriting. Discover seven innovative strategies for leveraging large language models (LLMs) to enhance your writing, from brainstorming and editing to SEO optimization and content repurposing. Whether you're a seasoned AI user or just starting, these tips will help you supercharge your content creation process, ensuring your writing remains efficient, creative, and aligned with your association's voice.

🛠 AI Tools and Resources Mentioned in This Episode:
ChatGPT ➡ https://chat.openai.com
Claude ➡ https://www.anthropic.com/index/claude
Perplexity ➡ https://www.perplexity.ai
Google Gemini ➡ https://ai.google/tools/gemini/

Chapters:
00:00 - Introduction
03:27 - Understanding LLMs
07:13 - Strategy 1: Brainstorming with AI
11:09 - Strategy 2: Expert Editing with AI
16:41 - Strategy 3: Using AI as a Research Assistant
21:00 - Strategy 4: Content Summarization with AI
25:46 - Strategy 5: SEO Optimization with AI
28:02 - Strategy 6: Tone and Style Consistency
33:15 - Strategy 7: Content Repurposing with AI
38:41 - Final Thoughts and Takeaways

🚀 Follow Sidecar on LinkedIn
https://linkedin.com/sidecar-global

👍 Please Like & Subscribe!
https://twitter.com/sidecarglobal
https://www.youtube.com/@SidecarSync
https://sidecarglobal.com

More about Your Hosts:

Amith Nagarajan is the Chairman of Blue Cypress 🔗 https://BlueCypress.io, a family of purpose-driven companies and proud practitioners of Conscious Capitalism. The Blue Cypress companies focus on helping associations, non-profits, and other purpose-driven organizations achieve long-term success. Amith is also an active early-stage investor in B2B SaaS companies. He’s had the good fortune of nearly three decades of success as an entrepreneur and enjoys helping others in their journey.

📣 Follow Amith on LinkedIn:
https://linkedin.com/amithnagarajan

Mallory Mejias is the Manager at Sidecar, and she's passionate about creating opportunities for association professionals to learn, grow, and better serve their members using artificial intelligence. She enjoys blending creativity and innovation to produce fresh, meaningful content for the association space.

📣 Follow Mallory on Linkedin:
https://linkedin.com/mallorymejias

Speaker 1:

LLMs are powerful allies in repurposing existing content into different formats, maximizing the value of your content creation efforts.

Speaker 2:

Welcome to Sidecar Sync, your weekly dose of innovation. If you're looking for the latest news, insights and developments in the association world, especially those driven by artificial intelligence, you're in the right place. We cut through the noise to bring you the most relevant updates, with a keen focus on how AI and other emerging technologies are shaping the future. No fluff, just facts and informed discussions. I'm Amit Nagarajan, chairman of Blue Cypress, and I'm your host.

Speaker 1:

Hello everyone and welcome back to another episode of the Sidecar Sync podcast. My name is Mallory Mejiaz and I am one of your co-hosts, along with Amit Nagarajan, but today I am joining you solo. So welcome back to all of our regular listeners and if this is the first time you're listening to the Sidecar Sync podcast, welcome to you. Today we are talking about a topic that is near and dear to my heart, and that is AI-assisted content generation, but not just content generation in general. Specifically, today, we're talking about text content generation and or copywriting. It's certainly an area that has gotten a lot of press in the past few years, so today we're going to explore seven ways that you can use large language models to supercharge your writing that aren't necessarily just having the large language model write everything for you. But before we dive into that topic, first a quick word from our sponsor. Today's sponsor is Sidecar's AI Learning Hub. The Learning Hub is your go-to place to sharpen your AI skills, ensuring you're keeping up with the latest in the AI space. With the AI Learning Hub, you'll get access to a library of lessons designed to the unique challenges and opportunities within associations, weekly live office hours with AI experts and a community of fellow AI enthusiasts who are just as excited about learning AI as you are. Are you ready to future-proof your career? You can purchase 12-month access to the AI Learning Hub for $399. For more information, go to sidecarglobalcom slash hub. As I mentioned at the top of this episode, we're exploring seven strategies that you can use with large language models out there to assist in your writing process that don't involve the large language models just doing everything for you.

Speaker 1:

This topic of the podcast was actually inspired by a section in the marketing chapter of Ascend second edition. We've talked about that a little bit on the podcast before, but just last month basically end of July, early August we released the second edition of Ascend, unlocking the Power of AI for Associations. You can actually go right now to Amazon and get a hard copy of that book if you would like, or you can download it for free at our website, sidecarglobalcom slash AI. But today's topic was inspired by a section within the marketing chapter. But let me say today's episode is not just for marketers. It is anyone who regularly writes in their workflow, which I would dare say is probably all of you listening to this podcast. So, whether it's for an email you're writing or a report you're generating or a summary, or a blog or a social media post. Today's episode will help you get the most out of your large language models. When, in the past, maybe, you've just asked it to generate a blog for you. We'll give you several strategies that you can use to make those outputs better.

Speaker 1:

Before we dive into today's seven strategies, I think we need to take a moment to understand what large language models, or LLMs, actually are. We're not going to spend a ton of time on this, but I think it's essential to make sure we're all working with the same foundation. Large language models, or LL, are sophisticated AI systems trained on vast amounts of data, but it's important to understand that they're essentially very advanced next word predictors. They don't think or reason like humans do. Instead, they use patterns in their training data to predict the most likely next word or sequence of words. When you hear the term LLM, you can think of tools like ChatGPT, claude and Gemini.

Speaker 1:

Now, I know some of you have probably clicked onto this episode because you are skeptical, and I hear you on that. Some of you are probably thinking is AI going to replace human writers? Will it make our content feel robotic or impersonal? We got this question actually recently on one of our last Intro to AI webinars. Will it make writers lazy? These are all valid concerns and I'm here to tell you Sidecar doesn't have all the answers to these questions. I don't think that anyone does.

Speaker 1:

But here's the thing we don't see large language models as something designed to replace human creativity or expertise. Instead, we see them as tools, powerful tools that can enhance the writing process to help you work more efficiently and potentially unlock new levels of creativity that you didn't have access to before. Large language models can do a lot more than spit out a generic email after a single prompt. They can help with ideation, providing different perspectives and even handling some of the more tedious aspects of writing, but they still need human guidance, expertise and that personal touch that makes content resonate. So throughout this episode, we are going to explore how to use these tools in a way that amplifies your talents rather than replacing them, and we'll also be providing tips for beginners, but also to our more experienced users, especially regular listeners to the Sidecar Sync podcast. Maybe you have dabbled with large language models before. Maybe you're using tools like ChatGPT and Cloud every single day in your workflow, so we'll try to include some more intermediate to advanced examples for you as well.

Speaker 1:

Our first strategy to supercharge your writing using AI is to use it as a brainstorming assistant. I think it's safe to say writer's block can happen to anyone, especially if you're the person responsible for constantly creating content for your association. Large language models can be a powerful tool to jumpstart that creativity. Large language models can be a powerful tool to jumpstart that creativity. So by providing a prompt like generate 10 blog post ideas about sustainable practices for accountants, you can quickly get a list of potential topics. Now, it doesn't mean that you'll use all of the ideas as is, but it can spark your own creativity and help you think of angles you might not have considered. It's like having a tireless brainstorming partner always ready to help you generate ideas for blog posts, social media content, email subject lines or, hey, even internal emails. I think we've all probably been there sitting at our desk trying to figure out exactly how we wanted to phrase something to someone. You could use ChatGPT to help you brainstorm that. Now some of our more intermediate users and experienced listeners on the Sidecursing podcast might think yeah, that's how I use ChatGPT all the time. So here's kind of a more advanced example, you could say you can try using the large language model to generate ideas from different member personas. Ask it to brainstorm content ideas from the perspective of a new member, a longtime member and a board member, and this can help you create more targeted content strategies and potentially uncover some blind spots in your current approach.

Speaker 1:

For each of these seven strategies, today I didn't just want to talk about them. I actually wanted to demo what I mean as well. So for those of you who are joining us, audio only I'm actually sharing my screen right now. If that is something that you would like to see, you can check out the Sidecar Sync podcast on YouTube, where you can actually see my screen, and we'll drop a link to our YouTube account in the show notes as well. But right now I'm in my chat GPT account and I'm looking at a prompt that I gave it to help me elicit this brainstorming assistant power. So basically I said act as an assistant specializing in content creation for professional associations.

Speaker 1:

Your task is to generate diverse blog post ideas. Please follow these steps and then you'll see some sequential steps. After that. Number one generate 10 blog post ideas about sustainable practices for accountants. Ensure the ideas are varied and cover different aspects of sustainability and accounting. Two, this is that more intermediate use case I talked about. Take on the perspective of three different member personas and generate three content ideas for each New member, a recent graduate just starting their accounting career. Longtime member, a seasoned accountant with 20 plus years of experience. And board member. An industry leader focused 20 plus years of experience. And board member an industry leader focused on the future of the accounting profession. And then number three for each idea provide a brief explanation of why it would be valuable to that specific persona. Then there's a little note at the bottom here Remember to keep the ideas relevant to the current trends in accounting and sustainability and ensure they align with the professional tone of an accounting association.

Speaker 1:

So in this prompt there's kind of a few things that I think we did well, and I'm not tooting my own horn here. I actually used AI to help me create this prompt for the AI so it's a little bit meta, but one. I assigned it a role act as an assistant. I didn't say I am working for an accounting association. I said you are. So essentially, I'm priming the AI to respond in a way that's in line with the role that I've assigned it. And then something else that's helpful here is kind of breaking down the prompt into sequential steps, so that way I'm saying do this, do this and do this.

Speaker 1:

Next, in terms of what it generated, you'll see we have 10 blog post ideas. I'll give you all just a few blurb on each of what this would be about. And then, on the second piece of this prompt, I actually have content ideas for each of those member personas. So I've got my new member. One of those blog ideas is essential skills for accountants in a sustainable economy For the long-term member. One of the examples it generated was mentorship and sustainability, guiding the next generation of accountants. And then, under the board member persona, I've got shaping policy and advocacy for sustainable accounting standards. So you can really see here, just with one prompt and a fairly short prompt at that, if I do say so myself I was able to create 10 blog post ideas at the front and then three blog post ideas for each of these member personas. So that's 19 total blog ideas in basically a matter of seconds. And now, with each of these blog post ideas, probably what I would do next is pick the ones that I like, go back and forth a little bit and say what I like about it, maybe give it a little bit more context about my association in general. From there I would probably ask it to generate the outline of that blog and then I would go through and either write the pieces of that outline myself or have ChatGPT write it with me, making sure to give feedback constantly along the way. But this is the overall summary of using AI as a brainstorming system.

Speaker 1:

The next strategy for having AI supercharge your writing is using it as an expert editor. Here we're leveraging large language models to provide feedback on our writing. By instructing the large language model to take on the role of a specific type of editor, say an expert in association communications, you can get tailored feedback on your content. For example, you might ask it to review your newsletter draft for engagement, clarity and relevance to your member base. The AI can suggest improvements in tone, structure or even point out ideas where you might want to add more detail. Remember, this isn't about replacing your judgment per se, but just about getting a different perspective that can help refine your writing.

Speaker 1:

I think I've mentioned this on a podcast episode before, but in our client calls with teams that were in our AI learning hub. Someone shared with me the example of using ChatGPT and telling it to adopt the persona of different people on their board. Now, they obviously didn't give any personal information like this is Sally from my board but they said okay, this person is a technology expert, maybe they're a bit more aggressive when communicating their points. I'm just using this as an example. I don't remember exactly what they said. And then they started engaging with ChatGPT, which essentially was taking on the role of someone on their board, and then they were presenting ideas to it to get feedback and to get potential questions that might come up. So I think this goes back to the idea of using AI as an editor or to adopt that persona that will critique the work you are providing. That, at least. Well, I will say the persona example is a little bit more intermediate, but I wanted to add another intermediate example in terms of expert editing for our listeners, who use tools like this every day.

Speaker 1:

Consider creating a custom style guide for your association and maybe you already have one including tone and common phrases and industry specific jargon, and then you can prompt the LLM to edit your content based on that guide. This can help you maintain consistency across communications and even assist in training new team members. On your association's voice, which I find in general something that can be tough to communicate to new hires, even if you have the voice kind of written down, sometimes it feels like a feeling or an intuition almost. So I think having an AI that could provide that critique on tone would be really important. So right now I am inside Claude, which is a large language model by the company Anthropic, and I will say if you've listened to the pod before, you've heard me say Claude is my absolute favorite new tool. Every day this is what I find myself going to over and over again. I think ChatGPT is great, do every day and you work in marketing. But honestly, I would say, even across the board and I've heard this from our CEO as well Claude seems to be performing better. Now, I'm not saying the benchmarks say that per se, I'm just saying it is a gut feeling.

Speaker 1:

But for my audio-only listeners, right now I am in Claude showing an example of how I would prompt AI to act as an expert editor. So again, I'm assigning it a role. At the beginning, you are an award-winning editor specializing in content for association professionals. Now, for this example, I wanted to use a blog that Sidecar wrote, so I had to tailor this one a little bit more towards us as an organization. So I gave it context on our company, what we do, our target audience being association executives and professionals interested in AI adoption.

Speaker 1:

The purpose of this blog post, which, I should mention, is overcoming AI adoption obstacles for association leaders. I asked it to evaluate the text on engagement how well does it capture and maintain reader interest, clarity, relevance, tone, structure and value? And then I pasted in the blog post and I'm going to scroll down here You'll see. This is where, in Claude, you actually get to see a neat feature in action which is called artifacts, which is essentially dual screens. So on one side you've got the chat interface and on the other side you have the document that you are working on. So if you're watching on YouTube, you'll see on my right side I'm not sure if it's your right side of the screen as well On my right side you'll see this blog post review. It gives us an overall impression and then a detailed analysis on engagement clarity, relevance, tone, structure. Under each of those, it gives us strengths from the post and then also areas for improvement. I'll share some of the areas for improvement with you all that are listening audio only.

Speaker 1:

It says define AI briefly at the beginning for readers who may be less familiar with the concept. I think that's a great piece of feedback. Consider adding a glossary of key terms. For readers new to the field, that's an excellent piece of feedback as well. It also says some things that we did successfully as well. So, overall, this is how I would use a large language model WOD to be exact as an expert editor of my content, and this could really apply across the board. It doesn't have to be to blogs. It could be for your social post, it could be for an email that you want to send to your board or a report that you're generating, anything like that. If you want to have someone critique your work and be able to say exactly who that person is you are an expert in association boards and then have them critique your email or your report or your summary. You can do that with AI right now. Today.

Speaker 1:

The next way AI can supercharge your writing is using it as a research assistant when writing about complex topics or industry trends. Gathering background information can be time-consuming, to say the least, and LLMs can help by providing a quick summary of key points from various sources or providing an overview of a topic. For example, you could ask an LLM to give you a brief rundown of recent developments in cybersecurity for accountants. This gives you a starting point for your research, helping you identify areas that you can dig deeper. Now it's important to say that you should verify the information that you receive when using large language models, so you can ensure that you are disseminating information that is true and accurate. However, I will say this can significantly speed up the time it takes for you to initially start the research process. For our more intermediate users that regularly use AI as a research assistant, consider using an LLM to create a dynamic knowledge base from your association's past publications, conference proceedings and member discussions. When researching new content, you can then ask that LLM to provide insights solely based on this collective knowledge, ensuring that your content remains uniquely tied to your association's expertise, while also identifying trends or gaps in your existing content. And this is an intermediate example, but this very thing does exist in the association market and it's called Betty Bot, which is typically a member-facing version of what I just said, but it's also incredibly powerful to have something like that that you can reference internally within your association as well.

Speaker 1:

I could not talk about research assistance without talking about the tool perplexity, which has become my personal favorite tool to use when I'm researching basically any topics, particularly AI news, but kind of anything that has to do with anything in my workflow where I need factual, citable information, I am opting to use Perplexity. So for audio only listeners. Right now I'm sharing my screen and I am inside Perplexity. The prompt I gave it was fairly simple I need a comprehensive overview of recent developments in cybersecurity for accountants. Please include major threats and vulnerabilities specific to the accounting industry, new cybersecurity regulations, emerging technologies, any notable cybersecurity incidents involving accounting firms in the past year, provide a summary of each point and include sources for further reading. So that was the prompt.

Speaker 1:

It was pretty short, and then, once I pressed enter, you'll see the sources start populating that it's referencing and these are actually clickable. I can click into these sources right now and you'll see that there's a total of one, two, three, four, five, six, seven, eight, at least that it's linking in its research for this prompt and then it dives right in. We've got major threats and vulnerabilities phishing attacks, ransomware, cloud security risks, insider threats, supply chain attacks and there's a little blurb to go with each one of those. It provided regulations and standards, emerging technologies and best practices, notable cyber security incidents and that's it. But here's the thing. You might be thinking, well, can I just do this in chat, jt, and you could, but what's really neat to me about perplexity is that everything pretty much is cited. So after almost all of these sentences that are provided in this output, there's a little clickable number and if I click that, it will actually take me to the resource that it got this information from. I don't know about you, but that just makes me feel a bit safer when I'm using AI as a research assistant. The fact of the matter is it's doing this incredibly quickly and I it would take me a minute to go through every single one of these points and fact check it, but having these clickable links makes me feel better. I use perplexity a lot when prepping for the podcast, because we might be talking about a more technical topic that I'm not as familiar with. So I'll drop a small prompt. I'll say tell me more about you know mixture of experts, architecture, and then it will give me all the citable information and links back to articles which are really helpful for educating yourself in general. So perplexity is one of my favorite tools to use as a research assistant to supercharge your writing.

Speaker 1:

Our next strategy may seem obvious to some people, but maybe not to others, and I had to include it because I feel like it is one of the best uses of AI in terms of text generation, and that is content summarization. Llms excel at distilling long form content into concise summaries which can be useful for creating executive summaries of reports, crafting social media posts from longer articles and even summarizing member feedback for board meetings. So, for example, you could ask an LLM to condense a 20-page annual report into a one-page executive summary highlighting key points and achievements, which saves a ton of your time but also ensures that important information is communicated effectively to different audiences. Now for our more intermediate example. You could use LLMs to create tiered summaries of the same content a one-sentence overview, a paragraph summary and a detailed executive summary which allows you to repurpose content for different platforms and audiences efficiently, which is kind of a teaser to later in this episode, where we will be talking exclusively about content repurposing, but for the sake of this strategy, we're talking about content summarization. To demo an example of this.

Speaker 1:

Right now I am in chat GPT using model GPT-4-0 or GPT-4-OMNI. If you want to know what exactly that means, we have an earlier episode that we did a few months ago on GPT-4-0. But right now I'm looking at my chat and I've assigned the AI a prompt. I said you are an AI assistant for Sidecar, a company that provides AI education to associations. An AI assistant for Sidecar, a company that provides AI education to associations. Your task is to create multiple summaries of our blog post about AI adoption obstacles and associations. And this is that same blog post I used earlier in the episode. And then I gave it these steps. I said create a one sentence overview of the blog post, key message. Develop a paragraph summary three to five sentences highlighting the main points. And generate a detailed executive summary 250 to 300 words that covers the main obstacles to AI adoption, key strategies to overcome these obstacles and any significant action steps or recommendations. And then all I did was paste in a copy of this blog, which was written by one of our team members, amelia. So I should say shout out to Amelia, and then I'm scrolling down to take a look at the output and I got exactly what I needed One sentence overview, paragraph summary and an executive summary with key strategies and significant action steps.

Speaker 1:

I'm sure all of us have been in a place where we've received a really, really long PDF and we weren't even really sure where to start. The prime example that I've talked about on this podcast before for me were the exhibitor packets at large industry events. Sometimes these exhibitor packets can be like 50 plus PDF pages, and I mean to be totally honest, I can't imagine that anyone is sitting there reading all 50 PDF pages. So that's something else I could do here. You don't just have to copy and paste text in. You can actually attach a PDF file and assign it the same prompt and say hey, here's this exhibitor packet. Can you pull out any points that are essential that I not mess up? For example, like the height of a booth, like I talked about on the previous episode, which was a major mess up I had because I didn't read the exhibitor packet. But all that's to say, we've all been in situations, whether it's marketing related or not, where we've had a lot of text to consume, and using AI as an assistant to create summaries for you to consume it more easily is an excellent use case, and I'll also point out now we use Microsoft, the Microsoft suite, at the Blue Cypress family of companies, and I was out of office on Friday and I was in this long Teams thread, which, again, is sometimes difficult to go back, find out where you left off, read all the messages, and there was actually an option there that said summarize what I've missed. So I don't know if that's available to everyone or if that's just because we have a co-pilot activated, but something to consider as well, that we're also going to have this feature available to us in tools that we use every day, all the time.

Speaker 1:

Our next strategy is a bit more marketing focused, and that is SEO optimization Having AI analyze your content for SEO potential, suggesting keywords, meta descriptions and ways to improve search engine visibility. You might ask the LLM to review a blog post and suggest relevant keywords that could help improve its search ranking. It can also help in crafting meta descriptions that are both informative and enticing for search engine users. As a slightly more intermediate example, you can prompt the LLM to rewrite your meta description and suggest header structures that incorporate your target keywords. Naturally, this will then help improve your content's SEO performance while maintaining readability and value for your audience For this example.

Speaker 1:

I am back in Claude and I'm using the same blog that I've used in some of the previous examples and I tell Claude to act as an SEO expert specializing in content for an association professional or association professionals in general. I should say Analyze the blog post and suggest five to seven relevant keywords that could help improve his search ranking. Propose an SEO friendly title for the blog post that incorporates one of the main keywords. Write a meta description. Suggest how to naturally incorporate the identified keywords into the post, including recommendations for header usage. Provide two to three internal linking suggestions to other relevant content on our site about AI or association management. Remember, our target audience consists of association professionals. And then in a few seconds it spit out this prompt.

Speaker 1:

It gave us a few keywords which are pretty spot on for us AI adoption and associations, overcoming AI obstacles, association, ai implementation, ai policies for associations, so on and so forth. I would say most of these are pretty spot on, probably except overcoming AI obstacles, I would say for sidecar. That would be a bit too general and we wouldn't want a lot of that traffic for people who are searching those keywords because they probably are not looking for sidecar specifically. And then it provides the meta description and suggestions for ways that we can incorporate keywords, naturally even suggesting H2 headers and H3 headers and internal linking suggestions headers, nh3 headers and internal linking suggestions. I will say I'm not sure if these internal linking suggestions are, if it's hallucinating or if it's actually referencing real blogs on our website. I did not provide the link to the Sidecar website, so I will say that this piece could be a hallucination, but I'm not sure. But overall, this was a prompt that I created very quickly. As you can see, I know for Sidecar we have this really long, beautiful list of keywords that we've researched in the past. That would work for us. So typically, if I was actually doing this, I would attach that Excel sheet of keywords and then ask it to help the content rank for those keywords specifically. I think it's also a valid exercise to ask the AI to create the keywords, but if that is a piece of work that you've already done in your organization, you should certainly use it.

Speaker 1:

We talked about this strategy a little bit earlier with Expert Editor, but I think it deserves its own spotlight, and that is tone and style consistency. Maintaining a consistent brand voice across different pieces of content can be challenging, especially when you have multiple people involved in the content creation process. Llms can help by suggesting adjustments to align with your association's preferred tone and style. You can ask it to review a piece of content and adjust it to match your association's voice, whether that's professional but friendly, or maybe authoritative but approachable. I imagine this is especially important given the realm that your association exists within. So I'm sure the association of piano players right probably communicates to its audience a little bit different than the association of radiologists, and I think that could especially this piece could especially be impactful for new hires that you're bringing onto your team, let's say, that have written content in other industries which they likely have and may not understand completely how to communicate to your members.

Speaker 1:

I think using AI as an editor specifically to focus on tone and consistency would be essential in that scenario. And what I wanted to say for a more intermediate use case that's actually fairly easy to do I'm just saying it's intermediate because maybe not a lot of people have done this in the past is to use a brand voice guide that you already have, or create one if you don't have one, and then make a custom GPT within chat GPT trained on that brand voice guide and then you could kind of have the tone and style assistant for your association that anyone could go to. Maybe it's blogs, maybe it's social posts, but maybe it's some other material. You could go to this AI. You could say here's what I wrote. Can you adjust it based on the information that you've been quote unquote trained on which, in this scenario, would be the brand voice guide, and you can ensure that you have consistency across all the content that your association creates? To demo this strategy, I am back to chat GPT using GPT 4.0 and I'm assigning chat GPTa role. You are Sidecar's brand guardian.

Speaker 1:

Your task is to review a section of our blog post and ensure it aligns with our brand voice. Here's an excerpt from our style guide and I will say, for those of you watching on YouTube or even those of you listening audio only, this is not actually our style guide. I had AI create this, but I honestly feel like you know it did a pretty good job. So essentially, it said our tone is professional yet approachable. Our content should be clear, concise and actionable, providing practical value to association professionals. Ensure the use of AI and association terminology is appropriate for our audience of association professionals with varying levels of AI knowledge, so on and so forth.

Speaker 1:

And then I pasted in that same handy blog post that we've used for our other examples and I'm going to scroll down and see what feedback it gave. And actually it didn't even get feedback. It really just rewrote the entire blog based on that excerpt from the style guide, or the fictitious style guide that I gave it. I'm reading through it now and it did a pretty good job so you can see that it didn't really lose any pieces of the content, but it actually just rewarded it. It made sure that we focused on actionable next steps and that the terminology was clear and applicable to an audience of a wide range of AI experience levels, which is essential for Sidecar. We've got about 12,000 people in our newsletter currently. Some are AI beginners, some are more on that expert level, some are in the middle, some are not thinking about AI at all, and so we have to make sure constantly to be thinking about all of these different personas, which kind of goes back to the editing example earlier, to make sure that our content is speaking to them. So you can see in this example with a really quick prompt again and just copying and pasting that blog in there. I have a whole new blog which aligns with the fictitious sidecar style guide that it provided at the beginning.

Speaker 1:

Last but not least, the next strategy really should be its own episode on its own. So I want you all to know that we are barely scratching the surface with this strategy, but it is content repurposing. In fact, in Ascend, the book that I mentioned earlier, in this episode we have a whole chapter, not a section, but a whole chapter on content transformation, which can deal with translation from one language to another, to translating content from one experience level to another. You can think about this in a much deeper way, but for the sake of today's episode, I did want to mention it because it's important, and that is that LLMs are powerful allies in repurposing existing content into different formats, maximizing the value of your content creation efforts. For example, you can ask an LLM to transform a long form article into a series of social media posts, each capturing a key point from the original piece. This allows you to reach different segments of your audience through various channels with the same core message, and I know the example I just gave was again kind of a marketing example, but I'll tell you something that isn't really marketing related that I did recently.

Speaker 1:

We are in the process of revamping all of our AI Learning Hub content, so planning it out, re-recording it, editing it and adding it back to the AI Learning Hub as you know it, and so I've been using AI basically back and forth to kind of help me with the new content plan that we are bringing forward. Once I had that in a really good place, I realized, oh, now I have to take this content plan and I have to turn it. I have to figure out a project plan to go along with it to make sure that we stay on schedule. And then I had this light bulb moment of oh well, I can just have AI transform the content plan in a Word doc into a spreadsheet timeline calendar, and it did that in seconds. And that is another way of thinking about content repurposing, kind of outside the realm of marketing.

Speaker 1:

It can be internal things as well. If you have a piece of content or something that you have worked really hard on, even a slide deck, anything like that and you think, oh, it'd be so nice if I could use this to take the project further, you can do that For intermediate users. An example that I want to share is using LLMs to break down a comprehensive report or even a white paper into a series of smaller pieces like blog posts, social media content and an email sequence, each tailored to a specific audience segment, which can help you create a cohesive content strategy from a single piece of in-depth content. Another way that we do this at Sidecar is through the podcast. So it's no secret, we record these podcasts and then we take the transcripts and we use the transcripts to inspire many blog posts in the future social posts. We run the podcast video through Munch, which we've talked about, to generate video clips from it. So when we work hard on a piece of content at Sidecar, you can be sure that we are going to get basically as much as we can out of it, which is, I think, a good way to proceed. We put a lot of hard work into the content that we produce, and so we want to get the most out of it that we can.

Speaker 1:

For this last demo example, I am switching it up. I'm not in ChatGPT and I'm not in Claude, nor Perplexity. I'm actually in Google Gemini Now we've talked about, on the podcast before, that you can actually drop a video into Google Gemini and have it create content from that video or answer questions about that video, essentially watch it, quote, unquote and then provide output based on what it saw. However, I've never actually done this myself. I've seen Thomas Altman, who I co-host our Intro to AI webinar, do this, but I've never done it myself, and so I wanted to share this with you all. Maybe you have tried as well and you weren't able to do it, and so you clicked off. But I actually had to go to Google's AI studio to be able to do this, and if you're watching on YouTube, you can see exactly where I am. But if you just go to your regular Google Gemini, like as you do, chat GPT, you actually can't upload video. So I wanted to point that out if any of our listeners or viewers have ever tried it and weren't able to make Google Gemini work for them in this way. But I decided to take a video of last week's podcast episode actually, and run it through Google Gemini with this prompt. I said you are an expert content strategist for Sidecar. Told it who Sidecar was.

Speaker 1:

Based on this podcast content, create the following a 500 word blog post, a series of five LinkedIn posts, an email sequence of three emails to send to our subscribers and three tweet-length key takeaways In the output. You can say that it did exactly that. Now, as I mentioned earlier, I did use AI to create these prompts for me. I personally would not have asked Gemini to just create a 500-word blog. I like to work through that more sequentially.

Speaker 1:

Can you give me some ideas, as we talked about in brainstorming? Can you provide an outline of some of those ideas? Okay, now can you start writing in that outline chunk by chunk? I find that you get much better results that way and then when you see something that you don't like along the way, you can catch it and address it, as opposed to having a full 500 word blog and then being like I don't know, I just don't like it. There's something about this that I don't like. If you take the process a little slower, you can typically find the things that stand out to you that you want to fix.

Speaker 1:

So that's my little tidbit for the blog post, but you can see it created all these LinkedIn posts, and then what I think is really neat is it also created the emails, which I did ask it to do. But I will say this is not something that we actually currently do with the podcast Ask AI to create the email sequences to go with it. But I think this is a really good idea. And then I'm scrolling down and you'll see that it created tweets about this episode as well. So, essentially, for an hour of Amit and my time, we were able to quickly drop this into an AI tool and generate a blog, some LinkedIn posts, three emails and some tweets.

Speaker 1:

Work that in the past, I don't even know would have taken a long, long time. I feel like I'm so used to and adjusted to AI now that it's hard for me to remember exactly how things used to be Now. Again, I want to reiterate that I'm dropping in one prompt and these are the outputs that you see. So if you feel like these are not impressive or not exactly what you're looking for, I would encourage you again to keep working with your prompts and to go through this process a little bit more slowly. If you work in pieces, as I mentioned, you can more finely tune the output to what you are looking for.

Speaker 1:

But, as I said, content repurposing, content transformation really deserves its own episode. There's so much you can do here with AI, but I wanted to at least provide a little teaser, since it's an essential part of using AI to help with your text and your copywriting. So, for everyone who has stuck with me through the end of this episode, I want to say thank you so much for joining us, to our new viewers and listeners, and to our old ones. I will see you all next week in another episode of the Sidecar Sync.

Speaker 2:

Thanks for tuning into Sidecar Sync this week. Looking to dive deeper? Download your free copy of our new book Ascend Unlocking the Power of AI for Associations at ascendbookorg. It's packed with insights to power your association's journey with AI. And remember, sidecar is here with more resources, from webinars to bootcamps, to help you stay ahead in the association world. We'll catch you in the next episode. Until then, keep learning, keep growing and keep disrupting.