Rosenverse
Building impactful AI products for design and product leaders, Part 3: Understand AI architectures: RAG, Agents, Oh My!

Log in or create a free Rosenverse account to watch this video.

Log in Create free account

100s of community videos are available to free members. Conference talks are generally available to Gold members.

Building impactful AI products for design and product leaders, Part 3: Understand AI architectures: RAG, Agents, Oh My!

Wednesday, July 30, 2025 • Rosenfeld Community

This video is featured in the AI and UX playlist.

Share the love for this talk
Building impactful AI products for design and product leaders, Part 3: Understand AI architectures: RAG, Agents, Oh My!
Speakers: Peter Van Dijck
Link:

Summary

Agents, RAG, Memory, Vector Databases, Tool Use, MCP! The sector is rapidly evolving lots of architectures to make AI products more helpful and impactful. Peter van Dijck of Simply Put will share a simple framework that helps you understand how to think about these architectures, how to plan around them, and how to work with engineering teams on them. None of this is rocket science, but the acronyms are many. You don’t need to write code, but you do need to understand what is going on in these systems. You will learn how to think about and understand these complex-seeming architectures, and how to think about new ones as they come out.

Key Insights

  • •

    Large language models are stateless and rely entirely on the provided context window for each response.

  • •

    The context window is essentially a text file aggregating system instructions, user queries, documents, and other relevant data.

  • •

    All modern AI techniques (retrieval, augmented generation, tool use) aim to improve the quality and relevance of this context window.

  • •

    Tool use allows the model to autonomously decide when to invoke external APIs or services based on the input query.

  • •

    Agent models enhance tool use by planning and executing multiple tool calls in an iterative, reasoning loop until a task is complete.

  • •

    Post-training with billions of examples significantly improves models' abilities in reasoning, tool use, and planning.

  • •

    Designing AI products should begin with user needs and the necessary context rather than starting with complex agent architectures.

  • •

    Prompt structure, including semantic content and organization (e.g., XML tags), helps the model parse context effectively but is flexible.

  • •

    Token limits constrain the context window size; modern models like Google’s can handle up to a million tokens, enabling very large context inputs.

  • •

    User-specific data (e.g., PTO policy, employee info) can be integrated into the context window dynamically through backend queries to provide accurate personalized responses.

Notable Quotes

"Models are stateless; they have no memory and forget everything after each response."

"Context design and context engineering mean figuring out and building what needs to go into that text file sent to the model."

"All the complicated-sounding techniques are just ways to put the relevant text into the context window."

"Think of the context window like an intern's briefing document: would the intern be able to answer the question with this information?"

"Tool use lets the model decide itself when to call external APIs or services to get needed information."

"An agent is a model using tools in a loop, making plans, reasoning, and calling tools until it’s done."

"Post-training on billions of examples is like training a dog over and over until it gets really good at reasoning and tool use."

"You never start AI product design from the technology itself; you start from the user outcomes and retro-engineer the needed context."

"Language is hard, and we use anthropomorphic words like reasoning and thinking to describe what the model does technically."

"If you understand how engineers think about these models, you won’t be scared of concepts like synthetic data or tool use."

Ask the Rosenbot
Louis Rosenfeld
Coffee with Lou
2024 • Rosenfeld Community
Bria Alexander
Opening Remarks
2022 • Civic Design 2022
Gold
Abbey Smalley
Today’s Design Ops and Programs Landscape & Career Paths
2023 • DesignOps Summit 2023
Gold
Jim Kalbach
Peace is waged with sticky notes: Mapping Real-World Experiences
2018 • Enterprise Experience 2018
Gold
Christian Bason
Innovating With People: Unleashing the Potential of Civic Design
2021 • Civic Design 2021
Gold
James Rampton
The Basics of Automotive UX & Why Phones Are a Part of That Future
2024 • Rosenfeld Community
Dolly Parikh
Exit Interview #7: Journey of a Social Entrepreneur
2026 • Rosenfeld Community
Erika Kincaid
Connecting the Dots: How to Foster Collaboration and Build a Strong Design Review Culture
2022 • Design at Scale 2022
Gold
John Donmoyer
Shipping your code generation experiments to production
2025 • Designing with AI 2025
Gold
Ignacio Martinez
Fair and Effective Designer Evaluation
2024 • DesignOps Summit 2024
Gold
Shipra Kayan
Make your research synthesis speedy and more collaborative using a canvas
2025 • Rosenfeld Community
Brian T. O’Neill
Does Designing and Researching Data Products Powered by ML/AI and Analytics Call for New UX Methods?
2022 • QuantQual Interest Group
Jess Greco
Creating a Basis for Change: Scaling Design Maturity
2022 • Design at Scale 2022
Gold
Erin Weigel
Get Your Whole Team Testing to Design for Impact
2024 • Rosenfeld Community
Kelly Dern
AI as a Design Partner: How to Get the Most Out of AI Tools to Scale Your Process
2023 • DesignOps Summit 2023
Gold
Marc Majers
Interrupted UX - Add A Dose of Reality To Usability Testing
2022 • Advancing Research 2022
Gold

More Videos

Dave Malouf

"Break your design system components and stress test them to see where they break so you can improve them."

Dave Malouf Amy Thibodeau

Panel: Design Systems and Documentation

November 7, 2017

John Donmoyer

"Starting from scratch is really hard, but also a cool opportunity to throw away painful patterns."

John Donmoyer

Shipping your code generation experiments to production

June 11, 2025

Clara Kliman-Silver

"Trust is paramount; designers want transparency about what the AI is trained on and what data it uses."

Clara Kliman-Silver

UX Futures: The Role of Artificial Intelligence in Design

June 7, 2023

Mark Templeton

"The post-PC era has had more impact on enterprise UX and computing than any other factor in all history."

Mark Templeton

Creating a Legacy: the ultimate experience

June 9, 2017

Sarah Gallimore

"Evan actually spent less than 15 minutes on the essay, and instead of working on homework, he was writing a letter to his significant other back home in Detroit."

Sarah Gallimore

Inspire Progress with Artifacts from the Future

November 18, 2022

Sam Proulx

"Aim to work with at least one person on each platform your product supports, because assistive tech varies."

Sam Proulx

Prototype Reviews, People With Disabilities, and You

December 8, 2021

Anna Nguyen

"We realized that everyone kind of has a different definition of the voice of customer and that we needed to define our own to make it relevant for us."

Anna Nguyen Emily Brogan

Why Our Voice of the Customer is Better Than Yours

March 10, 2022

Anna Poznyakov

"We enable PMs and designers to conduct research rigorously because they are already in contact with customers daily."

Anna Poznyakov Richa Prajapati

Get The Most Out Of Stakeholder Collaboration—and Maximize Your Research Impact

March 12, 2021

Nalini P. Kotamraju

"I have a tagline my team is tired of hearing: about 50% of work is getting it done and 50% is getting it used."

Nalini P. Kotamraju

Two Jobs in One: Being a “Leader who is a Researcher” and a “Researcher who is a Leader"

March 10, 2021