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
Panel Discussion: Communicating the Value of DesignOps
2018 • DesignOps Summit 2018
Gold
Uday Gajendar
Theme One Intro
2023 • Enterprise UX 2023
Gold
Taylor Jennings
Repository Retrospective: Learnings from Introducing a Central Place for UX Research
2022 • Advancing Research 2022
Gold
Frances Yllana
D.E.A.R.R. Diaries (Discipline, Experience, Architecture, Reflection + Revolution)
2022 • Civic Design 2022
Gold
Bria Alexander
Opening Remarks
2023 • DesignOps Summit 2023
Gold
Jacqui Frey
Flow and Superfluidity for Design Orgs
2018 • DesignOps Summit 2018
Gold
Saara Kamppari-Miller
Theme Three Intro
2022 • DesignOps Summit 2022
Gold
Nick Lewis
Designing and building low-carbon websites independently
2025 • Climate UX Interest Group
Kristen Guth, Ph.D.
Out of the FOG: A Non-traditional Research Approach to Alignment
2023 • Advancing Research 2023
Gold
Tricia Wang
SCALE: Discussion
2018 • Enterprise Experience 2018
Gold
Sarah Auslander
Incremental Steps to Drive Radical Innovation in Policy Design
2022 • Civic Design 2022
Gold
Roberta Dombrowski
5 Reasons to Bring your Recruiting in House
2021 • DesignOps Summit 2021
Gold
Shivanjali M.
From Fragmented to Fluent: The Linguistic Approach to Research Knowledge
2026 • Rosenfeld Community
Lisa Gironda
Opener: Chief of Staff–An unexpected journey
2024 • DesignOps Summit 2020
Gold
Alana Washington
Theme 1: Introduction and Provocation
2024 • DesignOps Summit 2020
Gold
Alexandra Schmidt
Why Ethics Can't Save Tech
2022 • Civic Design 2022
Gold

More Videos

Amy Parness

"Sustainability is a long haul; you have to stay stubborn and not take no for an answer in a bad way."

Amy Parness

Scaling Sustainability: Complementary strategies that drive long-term success

May 29, 2025

Jessica Norris

"If a goal isn’t met it’s not all down to you; it’s a team effort and often influenced by many external factors."

Jessica Norris

ADHD: A DesignOps Superpower

September 9, 2022

"Burnout isn’t just an individual issue; managers must actively help employees say no and manage workload."

DesignOps and The Great Talent War of 2021

August 19, 2021

Ana Ferreira

"Asynchronous communication allows us hours of deep and focused work."

Ana Ferreira

Designing Distributed: Leading Doist’s Fully Remote Design Team in Six Countries

January 8, 2024

Steve Portigal

"Pilot projects with evangelists inside the company make ethnography manageable and successful."

Steve Portigal Chris Chapo Kelly Goto Christian Rohrer

Discussion

May 13, 2015

Maria Giudice

"This is the Oh s**t moment for the tech industry—designers became highly valued assets."

Maria Giudice

Empowering change: Reigniting purpose, passion and impact in research

March 13, 2025

Megan Blocker

"Having data to debate and measure research’s organizational impact is critical to escalating our influence."

Megan Blocker Lada Gorlenko Fatimah Richmond Molly Stevens

What UX research maturity looks like and how we get there [Advancing Research Community Workshop Series]

November 9, 2023

Jorge Arango

"Design is often seen as a production function but can and should be a strategic partner in organizational transformation."

Jorge Arango

Meeting of the Waters: Designing for Successful Inorganic Growth

August 12, 2021

JJ Kercher

"Design systems weren’t built until inconsistent experiences across teams made it undeniable."

JJ Kercher

A Roadmap for Maturing Design in the Enterprise

June 15, 2018