Summary
Elijah and Kevin trade war stories from the prompt trenches, and land on a counterintuitive rule, more context can make outputs worse. They unpack why Gemini “Gems” feel powerful but brittle, and how NotebookLM just changed the game by becoming a reusable source library that Gems can tap. From there, it turns into a practical playbook, curate your notebooks, keep lightweight brand style guides handy, and use purpose-built “skills” when you need up-to-date platform know how. The second half pivots to ads, trust, and a looming zero click future where the chat converts the sale.Takeaways
- Overprompting backfires fast, give the model clean context, then get out of its way.
- NotebookLM as a shared source library plus Gems for repeatable workflows is a strong combo.
- Keep brand guidance simple and current, a lightweight style guide beats a bloated brand book.
- “Skills” are a practical workaround for stale model knowledge, wire them to living docs and repos.
- Ads inside chat pushes us toward zero click buying, which changes brand control, trust, and attribution.
Explore practical AI implementation: https://assessment.ascendlabs.ai/
Book a conversation with Kevin: tidycal.com/kevinwilliams
Show Notes & Links: https://www.spark6.com/podcast
Submit listener questions:
Check out Kevin’s stuff:
Ascend Labs: https://ascendlabs.ai/
Follow Kevin on LinkedIn: https://www.linkedin.com/in/kevinguywilliams/
Check out Eli’s Stuff:
SPARK6 Agency: https://www.spark6.com/
Sign up for FREE AI Framework Friday Newsletter: https://www.spark6.com/newsletter
Follow Elijah on LinkedIn: https://www.linkedin.com/in/elijahszasz/
