Can’t see the video? Enable cookies using the button in the bottom-left corner.
Session 2: Prompt Design as System Design
The Road to Agentic AI
Fill out the form above to watch the full length session!
What you'll learn
This session goes beyond basic prompt writing to explore how prompts shape probabilistic outcomes in LLMs. Learn to think less like a user giving commands and more like a designer sculpting behavior—unlocking smarter, more consistent AI responses through deliberate, strategic prompting.
Who should watch
This session is ideal for:
- Business and tech leaders integrating AI tools
- Enterprise users frustrated with “hit-or-miss” results
- Anyone serious about developing prompt engineering skills
- Teams tasked with AI implementation or strategy
Key takeaways
- Prompting isn’t querying—it’s designing: A prompt isn’t a question or instruction. It’s a probability-shaping mechanism. You’re creating the conditions for the most likely, desired outcome—not issuing commands.
- Structure guides results: Strong patterns (like outlines, haikus, tables, or personas) create highly directional outputs. LLMs “love” structure because it narrows the probability space with consistent syntax.
- Framing matters: Whether it’s asking a question as a noir detective or a security analyst, the framing you choose influences the tone, voice, and style of the response—without changing the core content.
- Temperature = creativity: Want wild ideas? Raise the “temperature” with open-ended prompts. Want precise results? Use clear, structured, positively framed input to reduce randomness.
- Context is cumulative: Every response influences the next. Iterating across a conversation—or priming the model with examples—allows you to refine outputs in stages and build toward nuanced, goal-driven results.
About the speaker
Julian Lancaster
As Chief Information Security Officer at Prowess Consulting, Julian Lancaster brings a grounded, refreshing, and practical perspective to the Agentic AI series. A passionate advocate for responsible AI adoption, Julian focuses on building foundational understanding of how large language models (LLMs) work, and how teams, individuals, and organizations can leverage them to increase efficiency, scale capacity, and drive smarter decision-making. With a strong background in cybersecurity and enterprise operations, Julian helps demystify AI technologies so they can be used effectively and securely across the business.