AI Explored Podcast Summary: "Prompting at Scale: How to Deploy AI Across Your Company"

Release Date: November 12, 2024
Host: Michael Stelzner, Social Media Examiner
Guest: Jon Munsell, Founder of Bazooka

Introduction

In this episode of the AI Explored podcast, host Michael Stelzner delves into the intricate world of scaling AI prompting within organizations. Joined by Jon Munsell, the founder of Bazooka and author of the forthcoming book "In Strategy Through Execution, the Blueprint to Scale in AI First Culture," the discussion centers around creating a structured framework for AI prompts that can be uniformly deployed across various departments and teams within a company.

Guest Background

Jon Munsell brings a wealth of experience from his transition from banking to digital marketing and, ultimately, to AI training and strategy. With over 15 years in financial services and a significant tenure in marketing, Jon highlights his passion for automation and AI, which led him to establish Bazooka, an AI training consultancy and strategy firm.

Notable Quote:
“I thought, okay, well this is where the new future is. So I sold off the agency, agency side and wanted to kind of contract because my wife and I are this close to being empty nesters.”
— Jon Munsell [02:04]

Journey into AI

Jon outlines his professional journey, emphasizing his early adoption of web technologies and gradual pivot to AI. Approximately two and a half years ago, recognizing the potential of AI, he sold his digital marketing agency to focus solely on AI training and strategy. This move was driven by a desire to explore AI's possibilities and develop scalable tools for its implementation across organizations.

Notable Quote:
“We developed some very robust tools for scaling AI. And so that's what I did.”
— Jon Munsell [03:45]

The AI Strategy Canvas

At the core of Jon's methodology is the AI Strategy Canvas, a comprehensive guide designed to help businesses effectively deploy AI across their operations. The canvas is divided into nine essential blocks:

1. Target Audience: Defines the beneficiary of the AI's output, such as specific customer personas.
2. Company: Details essential information about the organization to contextualize AI interactions.
3. Products and Services: Outlines the depth of information AI needs regarding the company's offerings.
4. Context: Additional specifics to guide AI responses, ensuring relevance and accuracy.
5. Role: Specifies the AI's function, whether as an analyst, copywriter, or expert in a particular field.
6. Style/Brand Voice: Determines the tone and narrative style AI should adopt.
7. Resources: Includes supplementary materials like transcripts, URLs, or data sources.
8. Rules: Establishes guidelines for AI behavior, including do’s and don’ts.
9. Request: The actual prompt or task given to AI.

Notable Quote:
“What most people do is they... start asking ChatGPT or Claude how to create a prompt, now all of a sudden I'm a prompt genius.”
— Jon Munsell [11:07]

Scalable Prompt Engineering

Jon differentiates Scalable Prompt Engineering from traditional prompt engineering by emphasizing the importance of a structured approach. Instead of crafting lengthy, unstructured prompts, Jon advocates for breaking down prompts into manageable, repeatable components aligned with the AI Strategy Canvas. This method ensures consistency and efficiency, making it easier to scale AI usage across an organization.

Notable Quote:
“Scalable prompt engineering is how you construct a prompt that allows you to duplicate it, hot swap variables in it and excel its adoption throughout the company.”
— Jon Munsell [05:42]

Benefits of Structured Prompting

Implementing a structured prompting framework offers numerous advantages:

• Efficiency: Reduces the need for iterative back-and-forth with AI, enabling more accurate outputs on the first attempt.
• Consistency: Ensures uniform AI interactions across different departments, fostering a cohesive AI strategy.
• Scalability: Facilitates the easy replication and adaptation of prompts for various use cases within the organization.

Notable Quote:
“Once you understand the principles of it, you write a prompt faster. And what you get out of it the first try is significantly better. I mean, infinitely better.”
— Jon Munsell [11:33]

Practical Applications and Examples

Jon shares several real-world applications of his framework:

1. Transcript Analysis: Utilizing AI to dissect meeting transcripts, generating summaries, action items, and identifying key insights.
2. Book Writing: Employing AI to co-author his book on AI strategies, leveraging scalable prompting to maintain consistency and quality across chapters.
3. Webinar Creation: Automating the development of webinar outlines and slide decks tailored to specific audiences and regions.

Notable Quote:
“I've been teaching people this for almost a year now... I'm using scalable prompt engineering to prompt a GPT that has my stuff in it to actually write a book about prompt engineering.”
— Jon Munsell [40:44]

Implementation and Scaling Strategies

Jon emphasizes the importance of integrating the AI Strategy Canvas into organizational workflows using tools like Notion. By maintaining a library of prompts and context blocks, teams can efficiently access and utilize standardized prompts. Additionally, creating Custom GPTs or projects in platforms like ChatGPT and Claude allows for tailored AI interactions that align with the company's specific needs.

Notable Quote:
“If everybody knows how to do it the same way, then everybody's communicating the same way. And anybody can come in and see your prompt and know exactly what it does.”
— Jon Munsell [15:22]

Scaling Across the Organization

To scale AI prompting effectively, Jon recommends:

1. Strategic Planning: Using the AI Strategy Canvas to identify AI initiatives and necessary resources.
2. Team Collaboration: Facilitating cross-departmental discussions to ensure integrated AI deployment.
3. Standardization: Establishing uniform prompting conventions to streamline AI usage and troubleshooting.

Notable Quote:
“So when we're trying to scale, the only thing that you have to swap out is the transcript itself.”
— Jon Munsell [35:55]

Conclusion and Future Directions

The episode concludes with insights into the transformative potential of structured AI prompting. Jon illustrates how his methodologies not only enhance current operations but also lay the groundwork for future innovations within organizations. He encourages listeners to adopt a strategic approach to AI, leveraging frameworks like the AI Strategy Canvas to maximize efficiency and scalability.

Notable Quote:
“If you can get this right, you can increase the likelihood that you get what you want on the first go round instead of on the fifth go round.”
— Jon Munsell [14:48]

Final Thoughts and Resources

Jon invites listeners to connect with him on LinkedIn and visit his website, bazooka.com, for more information. He offers a free copy of his upcoming book for those who engage through the podcast's special URL, fostering a community of AI enthusiasts committed to advancing their organizational AI strategies.

Notable Quote:
“If they go to that URL, I'll let them request a copy of the AI Strategy Canvas so they'll actually see the canvas, they'll have a copy of it and they can work with it and they can start to make sense of it.”
— Jon Munsell [16:17]

Connect with Jon Munsell:

• LinkedIn: JW Munsel
• Website: bazooka.com
  Use the URL and mention you heard about it on the SME podcast to receive a free copy of his book upon publication.

For more insights and future episodes, follow AI Explored on your preferred podcast platform and visit SocialMediaExaminer.com/podcast for show notes and additional resources.