VIDEO
HIGHLIGHT
Log InSign up
You're Not Bad at Prompting. You're Bad at Defining the Work.
SummaryTranscriptChat

You're Not Bad at Prompting. You're Bad at Defining the Work.

Prompt Engineering: A Shift in Perspective

The Evolution of Prompting

  • Prompt engineering is becoming obsolete; it was once seen as essential but is now considered basic knowledge.
  • Recent updates (versions 4.7 and 5.5) have transformed AI interactions, making them more powerful and complex.
  • Many believe that simply asking AI for what they want suffices, but this only works if users know exactly what they need.

Understanding Agentic Workflows

  • Complex workflows require a deeper understanding of how to communicate with AI effectively.
  • Current AI capabilities allow for longer, more impactful work sessions compared to previous models.
  • The focus should shift from prompting to asking questions that guide the AI's capabilities.

The Question Method: Partnering with AI

Shifting Mental Models

  • Users must view AI as a senior partner rather than a junior one to maximize its potential.
  • A good manager exemplifies how to engage deeply with problems while allowing room for exploration.

Defining Effective Questions

  • The "question method" encourages collaboration by framing inquiries that enable the AI to perform optimally.
  • Distinction between agentic workflows (complex knowledge work with AI) and agentic pipelines (structured tasks).

Principles for Effective Communication with AI

Principle One: Intent in Questions

  • Clearly convey your perspective when asking questions; specificity helps guide the inquiry process.
  • Provide context and directionality in your questions, akin to shining a flashlight on specific areas of interest.

Principle Two: Exploring Outcomes

  • Ask open-ended questions that encourage the AI to consider various outcomes rather than just evaluating results.
  • Use examples like PR FAQs where multiple perspectives can be synthesized through collaborative questioning.

Principle Three: Engaging Data and Opinions

  • Frame questions that prompt the AI to analyze both hard data and softer opinions simultaneously.
  • Ensure your inquiries invite comprehensive engagement across all relevant files or data sources provided.

Conclusion: Embracing New Paradigms

Moving Beyond Traditional Prompting

  • As we transition into 2026, it's crucial to adapt our approach from simple prompts to strategic questioning methods.
  • Treating AI as a senior partner will enhance collaboration and lead to more meaningful outputs in knowledge work.
Video description

Full Post w/ Prompt Pack: https://natesnewsletter.substack.com/p/ai-agents-better-communicator?r=1z4sm5&utm_campaign=post&utm_medium=web&showWelcomeOnShare=true __________________________________ What's really happening with prompt engineering now that AI agents are 100x more powerful than they were six months ago? The common story is that prompt engineering is dead and you can just ask AI for what you want — but the reality is more complicated. In this video, I share the inside scoop on the shift from prompting to questioning AI agents: • Why prompt engineering is now table stakes, not a skill • How to treat frontier LLMs like a senior partner • What the AI Question Method looks like in practice • Where most knowledge workers are still stuck in 2025 habits The risk is that anyone running heavy knowledge work with weak questions gets shallow output from powerful agents, but the operators who learn to ask sharp, layered questions unlock real leverage. Chapters: 00:00 Prompt engineering is now table stakes 01:24 Why agents are 100x more powerful in 2026 02:48 Introducing the AI Question Method 04:05 AI as senior partner, not junior teammate 06:20 Why most people are still prompting like it's 2025 08:10 Defining agents vs. agentic pipelines 10:05 Principle 1: The flashlight intent 12:30 Conveying perspective and edges in your questions 14:45 Principle 2: Asking what good looks like 16:20 The PRFAQ example with Prime Video 19:10 Principle 3: Wrestling with data and opinions 21:30 The MRR product-led growth example 23:45 Why memory and quick-start guides matter Subscribe for daily AI strategy and news. For deeper playbooks and analysis: https://natesnewsletter.substack.com/ Listen to this video as a podcast. - Spotify: https://open.spotify.com/show/0gkFdjd1wptEKJKLu9LbZ4 - Apple Podcasts: https://podcasts.apple.com/us/podcast/ai-news-strategy-daily-with-nate-b-jones/id1877109372