School Business Insider – Episode Summary
Episode: Speak Like a Human, Prompt Like a Pro
Date: August 19, 2025
Host: John Brucato
Guest: Aziz Agaev, CEO of Flow List
Overview
This episode features AI expert Aziz Agaev’s return to discuss how school business professionals can move beyond the basics of AI usage. The conversation centers on turning casual, everyday thoughts into structured, highly effective AI queries—especially via prompt engineering and custom GPTs. Aziz walks listeners through practical adoption strategies, showcases real district case studies, and explains his six-phase AI adoption model, all while emphasizing responsible AI practices that enable users rather than replace them.
Key Discussion Points & Insights
1. Shifting Perspectives: AI as Assistant, Not Cheat
-
Challenging the "Cheating" Bias ([02:09]):
- Aziz notes most school business officials (SBOs) come to training suspecting AI is "cheating."
- Realization comes when AI is presented as an assistant for repetitive, clerical tasks (note taking, minutes, summaries, etc.).
- Quote (Aziz, 02:09):
“Everyone comes in with a bias saying that AI is cheating. I cannot use AI because I want to use my own material. ... After the training, people realize that it is not the cheating material, it's just an assistant and it can help you to do secretarial tasks a lot faster.”
-
Examples of Effectiveness ([03:13]):
- AI note-taking enables focused participation in meetings.
- AI feedback to teachers based on class transcriptions ("act as an experienced math teacher...")
2. Enabling Productivity, Not Overuse
-
Balanced Approach ([05:50]):
- SBOs are cautious rather than reckless in adopting AI.
- Power users increase efficiency by reshaping and refining existing materials.
-
Emerging Superusers ([07:03]):
- Example: Ron Anderson, a district official who created specialized custom GPTs per document set (contracts, ERP, handbooks)—shared for staff-wide direct access.
- Quote (Aziz, 07:03):
“He created these kind of custom GPTs per document. ... Now employees can easily go and interact with it. These are the things that create efficiencies.”
3. Prompting Like a Pro
-
Prompt Quality = Output Quality ([09:22]):
- Compare prompt writing to asking good interview questions.
- Best output requires explicit, well-structured prompts: assign roles, specify format/output, ask for clarifying questions.
-
Chunking & Checklists ([11:16]):
- Tackle layered queries by splitting into clearly delineated questions, mimicking checklists for completeness.
-
Key Best Practices ([12:50]):
- Assign roles (“act as...”)
- Provide context and constraints
- Request clarifying questions before final output
- Quote (Aziz, 12:50):
“If you structure your prompt with act as, which is assigning role, then you put all of your context, all of your questions. And then third, you ask for the constraints, don'ts the formats, the output, how you want it. And then you tell it to ask you clarifying questions before it responds.”
-
Treat AI Like a Human (or Toddler) ([10:14], [16:58]):
- Talk to AI as you would to an assistant: explain task, expectations, ask “any questions?”
- Adapting to this conversational mode is often unnatural but highly effective.
4. Voice Over Typing: The Power of Dictation
- Natural Language Wins ([17:39]):
- Aziz’s training: have users dictate prompts while looking away from the screen to encourage natural, conversational prompting.
- AI is highly capable of interpreting informal, fragmented speech and course corrections.
- Quote (Aziz, 18:51):
“I explain myself and then I say, for example, if I'm explaining something, something in Excel, I say, column A is my school, column B is first name. Oh, no, wait, column B is actually last name. ... the response, I see that it fixed it.”
5. Custom GPTs & Prompt Assistants
-
Automating Repetitive Info-Heavy Tasks ([20:09]-[23:40]):
- Custom GPTs serve as specialized assistants—e.g., board meeting minutes, contract Q&As, staff handbooks, transportation info bots.
- Once instructions and example files/templates are loaded, staff/parents can query instantly.
-
DIY Creation Workflow ([24:55]):
- ChatGPT (paid): Shareable custom GPTs, built via chat interactions.
- Gemini (free): Custom Gems for personal use.
- Platforms such as PCAX/Chatbase: Embed GPTs as web chatbots.
-
No Coding Needed ([30:58]):
- Anyone can start with plain language; can use AI itself as an instructor (“teach me step-by-step”).
- Quote (Aziz, 31:16):
“The best way to start is to start. There is no training. You can learn AI from AI.”
6. Responsible Adoption & AI Accuracy
-
The Six-Phase Adoption Model ([34:16]):
- Surprise: Hear about AI's potential.
- Curiosity: Observe others, try cautiously.
- Confusion: Struggle with inconsistent outputs.
- Frustration: Persevere or give up here.
- Joy: Start experiencing real benefits.
- Productivity: Confident, regular use.
- Most SBOs remain in surprise/curiosity or frustration.
-
Tips for Progressing ([37:19]):
- Perseverance is key; training can accelerate confidence.
- Practice speaking/explaining tasks to AI.
-
Accuracy & Bias Control ([38:43]):
- Always verify AI outputs—especially on policy, regulation, or factual queries.
- Ask for sources, but independently check them for legitimacy.
- Quote (Aziz, 38:43):
“You cannot use anything AI gives you without reading and confirming it. ... Make sure you verify.”
7. Building AI Mastery in 15 Minutes per Week
- Project-Driven Practice ([40:35]):
- Each week, use AI on real-life, everyday work tasks—e.g., “Let AI create a board revenue presentation; compare results.”
- Results matter most when AI is applied to authentic projects, not just hypothetical prompts.
8. The Road Ahead: AI’s Role in School Business
-
The Urgency for Leadership ([41:54]):
- Students are already using AI; school leaders must keep pace or risk an expertise gap.
- Leadership should embrace and model responsible AI use to drive efficiency and innovation.
- Quote (Aziz, 41:54):
“All of our students use AI to its potential and our leadership and teachers, if they don't use it, there will be one time ... two parties will speak two different languages.”
-
Unlocking Time for the “Big Picture” ([43:23]):
- Routine AI use frees up hours per task, shifting staff focus to long-delayed policy or strategic work.
Notable Quotes & Moments
-
On Prompt Structure:
“Treat it as a five year old. ... you have to specify the format, the output, the tone, all of that you need to specify in the prompt.”
– Aziz, [10:14] -
Human Approach to AI:
“You have an assistant, you don't take a manila folder and drop it on their desk and leave what you do, you explain what you want ... At the end you say, do you have any questions?”
– Aziz, [15:59] -
Custom GPTs for Practical Use:
“What if we do staff manual GPT and have it available for our internal website for all of our employees?”
– Aziz, [27:56] -
On AI Learning Usability:
“It is a technology where you can learn that technology from the technology.”
– Aziz, [31:16] -
Addressing AI Hallucinations:
“AI hallucinates ... you cannot use anything AI gives you without reading and confirming it.”
– Aziz, [38:43] -
Leadership’s Role in AI Adoption:
“Using AI can reduce tasks from eight hours to half an hour ... allows us to focus on a bigger picture and not just day to day little tasks that occupy all of our time.”
– Aziz, [43:23]
Timestamps for Key Segments
- AI as an Assistant (Biases & Introduction) – [02:09]-[04:58]
- Prompt Engineering Best Practices – [09:22]-[14:58]
- Natural Voice Interfaces – [17:39]-[19:49]
- Custom GPTs: What & How – [20:09]-[23:57]
- Embedding/Sharing Custom GPTs – [29:22]-[30:44]
- Six-Phase AI Adoption Model – [34:16]-[38:23]
- Project-Based Learning in Minutes – [40:35]-[41:42]
- Vision for Future Leadership – [41:54]-[43:49]
Conclusion
Aziz Agaev offers a step-by-step roadmap for school business officials to move from wary curiosity to confident, responsible AI use. The episode is densely packed with practical prompt strategies, real-world examples, and mindset shifts that emphasize speaking to AI “like a human,” iteratively practicing, and verifying results. School leaders are encouraged to lead by example in AI adoption—equipping their teams for the generational tech leap already underway in classrooms.
Actionable takeaway: Start small, use real projects, and let AI teach you—embracing both its efficiencies and its learning curve.