AI Assistants: How To Level Up Your Work

Should you be using an AI assistant in your business? If you've ever wished for a consultant who's available 24/7, never gets frustrated, and costs a fraction of a typical advisory fee, then the answer is yes.

In this article, you'll discover how to train an AI model to function like an always-available assistant specifically designed for your business needs.

Why AI Assistants Matter for Marketers and Business Owners

Have you ever paid for a consultant? Unlike human consultants who are only available during certain days and hours or for finite periods, an AI personal assistant:

• Are available 24/7 whenever you need them
• Don't get impatient when you ask the same questions repeatedly
• Cost only around $20 per month (depending on which AI model you use)
• Can be customized to your specific business needs and goals

Just imagine if every person in your organization had an AI assistant working alongside them—a consultant, a mentor they could turn to whenever they needed help. How much time could they save? How much more work could they do independently if they didn't have to wait for input or inspiration from others?

#1: Use the RICCE Framework to Create AI Assistants for Various Tasks

While you can use Mike Allton's RICCE framework in individual conversations with AI, creating custom AI assistants allows you to save your instructions for ongoing use.

The major AI platforms all offer ways to create these custom assistants. Google Gemini calls theirs Gems, ChatGPT has CustomGPTs, and Claude has Projects.

They all work similarly, allowing you to:

1. Give your assistant a title
2. Provide a description
3. Add custom instructions that define how it should behave
4. Attach relevant files to inform its knowledge

Think of the RICCE framework as training wheels that help you provide all the information an AI needs to serve you effectively. You don't necessarily have to use a framework in every conversation, but it helps you start on the right path.

Role

First, tell the AI what role you want it to play. This role specification helps the AI narrow its focus to the specific expertise needed for your task. While the AI doesn't actually have the entire sum of human knowledge, it has access to a vast amount of knowledge data, and within all that knowledge, a small subset is what you need for the task at hand.

Pro Tip: Research has shown a difference between phrasing like “act as” versus “you are” when assigning roles, with the latter being more effective. For example:

You are the world's best email strategist.

Instructions

Next, clearly explain what you want to accomplish and what you expect from the conversation. Be as specific as possible about your objectives, and be sure to instruct the AI to ask you questions if it needs more information.

Marketing tasks like creating an email campaign might involve specifying the exact nature of the campaign:

Today, I am doing an email campaign. I want to reheat my audience because many of them haven't been opening emails for a while. I want to target them and get them to re-engage with my emails overall.

An important aspect of these instructions is to tell the AI if you want to take a step-by-step approach rather than letting it jump straight to the final product. Without this guidance, the AI will try to be helpful by immediately producing an output.

For example:

We're gonna go step by step through this process. The first step is to identify who I'm talking to.

Context

Now, you need to provide background information about your business, target audience, and other relevant details that will customize the results to your unique business. This might include:

• Who your business is
• Who your target audience is
• Your brand voice and style
• Links to relevant documents or websites

While you can copy and paste these details into the chat, you can also attach several types of document files. For instance, if you're giving the AI model custom instructions for creating marketing copy, you could attach a PDF that includes your brand style and voice guidelines with a detailed description of your ideal customer profile.

Google Gemini offers users a helpful enhancement for custom instructions because it can access Google Docs. As you update your brand documents or client information in Google Drive, your AI assistants will always work with the latest version of the data without needing to be retrained.

Constraints

Follow your context with boundaries to help the AI understand your preferences and ensure the output matches your needs. This might include:

• Specific formats you prefer
• Geographic considerations (e.g., “We're only talking to our North American audience”)
• Language requirements
• Style constraints (e.g., “Don't overuse emojis”)
• Word count limits

For example, if your emails are typically short, you might tell the AI that any email it writes must be 500 words or less. Or you might stipulate long-form content by telling the AI any email it writes must be at least 1500 to 2000 words long.

Evaluation

This final step is to define what will success look like. How will you know if the AI's response is good? Did the AI assistant produce a great email or a ho-hum email?

Having clear criteria for the response helps you evaluate and refine the AI's output.

#2: Create Your Own AI Assistant Work Buddy

To help others create their own personalized AI assistants, Allton has developed the AI Work Buddy resource that includes:

• A one-paragraph prompt to get started
• A downloadable PDF with instructions
• A guided process where the AI asks you questions about your role, business, objectives, and communication preferences
• Automated generation of custom instructions for your personal AI assistant

Imagine you have a work buddy based in AI. An assistant trained in your role to achieve the same goals and objectives as you. This assistant could help you:

• Brainstorm ideas
• Prioritize tasks
• Create content

It could even provide empathy on difficult days!

“Once it gets done asking you all those questions, it's been programmed to give you a complete summary, a one-prompt output. Here are the custom instructions you can copy and paste into your new AI work buddy for whatever role you are in.”

#3: Create Advanced AI Assistants

Here are some higher-level strategic activities you can train an AI assistant to help with.

Strategic Planning Assistants

AI assistants can go beyond basic content creation tasks to become strategic partners in your business planning. They can help you map out entire marketing campaigns, translate content into different languages, and even push that content into other systems.

They can also help with strategic content planning by quarter. The key difference between this approach and merely using AI for content generation is that you engage with the AI at the planning and conceptual stage before creating any content. 

This allows you to leverage the AI's ability to analyze past content performance, identify patterns, suggest new approaches, and help prioritize your efforts based on your stated marketing initiatives so you ensure your content aligns with your overall business objectives.

Brand Voice Content Creation Assistants

A helpful aspect of a customized AI assistant is its ability to learn and consistently apply your specific brand voice and style, transforming generic AI outputs into content that authentically represents your brand.

This personalization goes beyond just sounding like you—it helps maintain focus on your strategic priorities because it's been trained to know what you want to accomplish and who you're talking to.

For example, after Allton's business pivoted to helping St. Louis businesses implement AI, he trained his assistant to keep this focus front and center. When he brainstorms an email campaign or a blog post, the assistant constantly reminds him to include St. Louis businesses in the content. This consistent reminder is a strategic safeguard, keeping Mike aligned with his business goals. This assistant type can also help you focus on your audience's needs rather than your product or service features.

For ongoing refinement, you can provide feedback on the assistant's outputs, telling it when it's captured your voice perfectly or missed the mark. Over time, the assistant becomes increasingly adept at producing content that sounds authentically like you or your brand while maintaining strategic alignment with your business goals.

The result is more efficient content creation and a consistent brand voice across all your communications—particularly valuable for teams where multiple people might be creating content.

AI Assistants for Specialized Tasks

AI assistants can be designed for very particular workflows, not just general brainstorming or content creation. For example, Allton has created a showrunner production assistant to handle the preparations for each new guest on his podcasts. 

By programming the exact sequence of steps into the custom instructions, he created an assistant that walks him through a step-by-step process that ensures no important preparation tasks are missed.

The AI walks through each step, methodically prompting Mike for specific details about the guest, gathering background information from their LinkedIn profile and other sources, and then compiling everything into a comprehensive pre-show document that helps Mike prepare for the interview.

#4: How to Use Google Gemini Deep Research to Develop AI Assistant-Training Documents

If your business pays for Google Workspace, you already have access to Gemini.

Key advantages of Gemini include:

• Integration with the Google ecosystem
• Very large context window (allowing you to include more information)
• Reference to living Google Docs (which update as you change them)
• Tools like Deep Research for comprehensive information gathering

When you give Deep Research a topic, the system reads your request and comes back with a research plan you can review before proceeding. Allton used Gemini's Deep Research when rebranding his business to focus on helping St. Louis companies.

He asked Deep Research to:

Help him understand the St. Louis business landscape by identifying the top industries in St. Louis, examples of businesses that work in those industries, the challenges those businesses have that AI could resolve, and the associations or organizations that represent those businesses.

The system repeated his requests and added additional research areas it thought would be helpful.

After he approved the research plan, the system scanned over a hundred websites, scraped them, and returned a complete report in about 10 minutes. This report now informs all of Mike's conversations with his AI assistant.

Other Notes From This Episode

• Connect with Michael Stelzner @Stelzner on Facebook and @Mike_Stelzner on X.
• Watch this interview and other exclusive content from Social Media Examiner on YouTube.

Where to subscribe: Apple Podcasts | Spotify | YouTube Music | YouTube | Amazon Music | RSS

✋🏽 If you enjoyed this episode of the AI Explored podcast, please head over to Apple Podcasts, leave a rating, write a review, and subscribe.

---

Stay Up-to-Date: Get New Marketing Articles Delivered to You!

Don't miss out on upcoming social media marketing insights and strategies! Sign up to receive notifications when we publish new articles on Social Media Examiner. Our expertly crafted content will help you stay ahead of the curve and drive results for your business. Click the link below to sign up now and receive our annual report!