Class is in session
4.9 (5)
3 Days
·Cohort-based Course
Develop a foundational understanding of how AI & LLMs see, hear, and read your input, + how to use them to 10x your output speed and impact.
Class is in session
4.9 (5)
3 Days
·Cohort-based Course
Develop a foundational understanding of how AI & LLMs see, hear, and read your input, + how to use them to 10x your output speed and impact.
Learn how to master AI from...
Course overview
The challenge: most people do not understand the reasons why products like ChatGPT, Claude, or Cursor respond the way they do. Because of this, they also don't understand how to get what they want and need out of AI tools.
Even power users who constantly talk to AI products every day aren't necessarily getting everything out of it. And as the world of work and productivity change, as AI becomes ever more agentic and capable of taking over our systems, processes, and tasks, it is essential to become excellent at its use to get and stay ahead.
Every user needs to understand not just "prompt engineering," as you've heard described elsewhere.
It's more fundamental than that. It's...
• An understanding of how modern language models are influenced by even the slightest change to your prompt
• The nuances of how different tools are 'packaged' (using ChatGPT is very different from using GPT-4.5 integrated in a third party product)
• The incredible power of reflective techniques – the best outputs are 5 to 7 messages after your initial prompt
This 3-day intensive will cover the above, and so much more, with the outcome of getting you to become fluent in talking to AI systems, including large language models and other generative AI modalities (like image & video generation).
And when I say "fluent," I mean something very specific. Just as language fluency isn't about memorizing phrases from a travel guidebook, AI fluency isn't about collecting prompts from Twitter. True fluency means understanding the deeper patterns of interaction -- knowing when to push, when to pivot, and most importantly, why.
Consider this: most courses teach you what to say to AI. This course teaches you how to think about AI conversation. It's the difference between learning to order coffee in French versus understanding why French speakers structure their thoughts the way they do.
We'll cover:
• How to consistently and easily judge new models as they're released for task-specific competence
• Nuances between reasoning, agentic, task-based, and primitive models
• Current power rankings based on real-world application (not biased evals)
We'll play with advanced uses of:
• Foundational SOTA models, like GPT 4.5, o3, 4o-mini, Gemini 2.5 Pro, Grok 3, Claude Sonnet 3.7
• Open source models like Llama 4 and DeepSeek-V3
• Agentic tools like Replit, Manus, GenSpark, and Devin
• Wrapper tools like Gamma, Napkin, and Perplexity
• My cheat code apps to 10x your workflow, both in ease and speed
I'll share my theory on the future of work.
And the OSD Framework I've developed to help people get ahead of the curve.
You'll learn about the 3 core muscles I believe every job will distill down to:
• Orchestration, the architect of AI-enabled systems
• Supervision, the human-in-the-loop steering or polishing outputs
• Delivery, the last-mile getting AI value to its end-user
Day 1
Mental Models & Mechanics
• What AI knows versus what it can do; how AI reads, thinks, and speaks, + biases and limits
• The hidden landscape of latent space, embeddings, and vectors - what does it all mean for your usage?
• Differences in AI paradigms, LLM models, genAI models, and the applications that sit on top of them
Day 2
Conversations & Debugging
• Ask the unaskable: form questions that inspire LLMs to answer you; learn the DRIVE context framework
• Use layered prompting and multi-turn conversations for your most advanced queries and topics
• Get AI to "think out loud," giving you more data, more insights, and the ability to iterate over time
Day 3
Advanced Applications
• Use reflective and agentic techniques + products to get AI "working for you" - soon, you'll have a team
• Get multi-modal - combine models, model types, and apps to generate fast, impactful outputs
• Learn how to use non-AI workflow applications to move dramatically faster and make advanced AI use 10x easier for yourself
• & more: analysis, tools, fine-tuning, hallucinations, ethical considerations, and real world use
And more
• retrieval augmented generation (RAG), code use, integration + extensions, voice-based nuances
• chain of thought, reflection, context windows, and other AI concepts explained
• how do apps make use of LLMs, how is AI being integrated by companies across tech
At the end of this 3-day intensive, you'll...
• be able to transform vague ideas into incredible outputs, whether you're brainstorming, working with data and statistics, coding with AI, using it for workflow, asking it knowledge questions, utilizing it for research, adopting it as a content companion, or using it in an academic setting
• troubleshoot and debug AI responses - you'll know when you've hit a real limit versus a bug or user error, unlocking the boundaries of what AI can do before anyone else -- no matter the field you're in
• future-proof your skills - because you're going to have a deep understanding of how these products work, you'll remain capable of using them as the models are continuously updated and evolved, even as the rapid pace of AI development continues
It's about harnessing the power of this transformative technology to amplify your own creativity, productivity, and impact on the world. Get ready to go beyond "prompt engineering" and embark on a journey to truly master the art and science of communicating with AI. Are you ready to unlock the conversation?
01
Non-technical or semi-technical professionals (throughout knowledge work) looking to gain an upper hand in this AI moment.
02
Anyone who has felt the gap between AI's potential, what they hear about what it can do, and their ability to access the upside.
03
NOT for engineers who already use LLM copilots every day. NOT for people looking for quick prompt templates.
Instead of AI prompt templates, learn conversational design patterns
You'll learn about the cognitive architecture that underpins not just LLMs, but the way that products and apps are built around them. These patterns will work across AI models and will continue working as systems evolve.
Instead of treating ChatGPT like a magic answer box, you'll make it a constant companion
It's hard for even the most AI-passionate people to integrate and reliably, consistency use AI products. I'll give you systems, shortcuts, and methods for making it second nature -- we'll build your AI muscle.
Instead of getting frustrated, you'll know how to iterate your way to results
"Why does it hallucinate here, but not there? When should I restart a conversation versus redirect it? Why does it sometimes forget what we just discussed? How does its sourcing work? When is more context good versus bad?"
You'll know. And you'll know what to do next.
Instead of being left behind, you'll get and stay ahead of the AI curve
You'll master the art of progressive refinement, building complex outputs and systems, and be able to leverage all of this to be top .5% in your field -- whether that's at work, with a hobby, with a side project, or with something personal.
Live sessions
Learn directly from Sherveen Mashayekhi in a real-time, interactive format.
Lifetime access
Go back to course content and recordings whenever you need to.
Community of peers
Stay accountable and share insights with like-minded professionals.
Certificate of completion
Share your new skills with your employer or on LinkedIn.
Maven Guarantee
This course is backed by the Maven Guarantee. Students are eligible for a full refund up until the halfway point of the course.
How to Talk to AI: Work & Productivity
3 live sessions • 9 lessons • 8 projects
May
21
May
22
May
23
4.9 (5)
Katie Kilbourne
Andrew Kim
Founder & CEO @ Free Agency; Product Leader @ Stella (AI job matching), Toptal
Sherveen has been a product leader and founder in tech for over a decade, but more importantly, is a long-time obsessive about startups.
He's a first adopter of AI tools and sits in exclusive circles of founders + venture capitalists building the cutting edge of applied AI products. He's the host of three shows + podcasts about early stage tech: The Feedback Loop, Three Course Founders, and The Sherveen Show, where he talks multiple times a week with the most exciting technologists, CEOs, and investors building the future.
See more: https://youtube.com/@sherveenshow
Be the first to know about upcoming cohorts
3 day intensive, 4.5 hours live
3 days of live classes
3:00pm - 4:30pm EST
Access recordings forever
Can't make it to the live classes or want to watch them again later? We'll make each day's content available same-day for all students.
Daily projects (optional)
Theory into practice
There will be several projects and optional group workshops to turn the content into usable muscle - attend live for instructor feedback, or access projects, examples, and templates at your own pace - including permanent access after the course ends.
Active hands-on learning
This course builds on live workshops and hands-on projects
Interactive and project-based
You’ll be interacting with other learners through breakout rooms and project teams
Learn with a cohort of peers
Join a community of like-minded people who want to learn and grow alongside you
Be the first to know about upcoming cohorts