Crash Course in AI Product Design from Google Search + Maps Designer, Elizabeth Laraki
Product Growth Podcast
Safeguards for Non-Deterministic AI Outputs
Elizabeth and Aakash discuss auditing training data, human-in-the-loop checks, and UI cues to show what AI added.
Today’s Episode
Everyone’s building AI products wrong.
They’re sprinkling AI on top like fairy dust. Adding chat interfaces to everything. Ignoring 70 years of design principles.
Elizabeth Laraki was one of 4 designers on Google Search in 2006. One of 2 designers on Google Maps in 2007. She helped create products used by billions—products whose designs barely changed for 15+ years because they nailed it from the start.
Today she breaks down exactly how to design AI features that users actually love.
----
Check out the conversation on Apple, Spotify and YouTube.
Brought to you by:
* Vanta: Automate compliance, manage risk, and prove trust
* Kameleoon: Leading AI experimentation platform
* The AI PM Certificate: Get $550 off with ‘AAKASH550C7’
* The AI Evals Course for PMs: Get $1155 off with code ‘ag-evals’
----
Timestamps:
00:00:00 - Intro
00:01:52 - Elizabeth's background at Google
00:04:19 - Google's AI search integration
00:06:19 - Designing image & video for AI
00:09:44 - AI image expander disaster
00:16:05 - Ads
00:17:50 - AI safeguards & human-in-the-loop
00:18:28 - 3-step AI design process
00:31:29 - Ads
00:33:25 - Designing AI voice interfaces
00:38:25 - Designing beyond chat
00:41:52 - AI design tools for designers
00:44:49 - Live design: LinkedIn for AI
00:57:04 - Google Maps redesign story
01:04:14 - Google Maps India landmarks
01:10:09 - Where to find Elizabeth
01:12:00 - Outro
----
Key Takeaways
1. The Core Design Process Hasn't Changed: Define the product (who, what tasks, what needs), Design it (features, architecture, flows), Build it (UIs, brand). Don't skip to "let's add a chatbot" because you have API access. The fundamentals still apply for AI.
2. AI Adds Non-Deterministic Risk: Traditional software is deterministic - click A, get B every time. AI is non-deterministic with unpredictable outputs. Elizabeth's image expander added a bra strap that wasn't in the original photo. Completely unintentional, completely unacceptable.
3. Work With Research on Safeguards: Audit training data for bias. Build evals that flag sensitive content (human bodies, faces, private information). Show A/B options for ambiguous cases. Make AI's work visible in the UI so users can scrutinize changes.
4. Start With Jobs To Be Done: Don't ask "We have GPT-4, what should we build?" Ask "What painful workflow takes users hours?" Descript mapped video editing lifecycle and baked AI into each job: remove filler words, edit from transcript, create clips, write titles.
5. Map User Context, Not Just Needs: ChatGPT voice in car with three kids? Perfect - nobody's looking at screen. Meta Ray-Bans reading Spanish menu item by item? Terrible - should ask "What are you in the mood for?" Same AI, different context requires different design.
6. Emerge From Ambiguity First: For "LinkedIn for AI," Elizabeth mapped 4 possible directions, picked Matchmaking, identified AI's unlock (personality patterns vs keyword matching), mapped separate UIs for job seekers and employers. Only then touch pixels.
7. Chat Fails for Complex Tasks: Elizabeth tried creating Madrid itinerary in ChatGPT. Every change regenerated everything with new hallucinations. Chat works for Q&A but fails for document creation, visual tasks, multi-step workflows that need persistent editable outputs.
8. Make Chat Supporting, Not Primary: Photoshop embeds AI in existing canvas tools. Google Search shows AI summaries inline in normal results. Cove gives canvas with multiple AI conversations in parallel. Chat is a tool, not THE interface.
9. Stop Adding AI Sprinkles: Elizabeth: "I can't help but think of this massive container of AI sprinkles everybody's shoving on top." Twitter/X + Grok, Amazon + Rufus, Apple Photos all feel forced. Ask three questions: Is this solving a real problem? Does chat make sense? Can you show your work?
10. Google Maps India Innovation: Researched how Indians actually navigate (by landmarks, not street names). Identified which landmarks work (visible from street level like temples, petrol stations). Redesigned entire directions system around that insight. That's design, whether AI or not.
----
Where to Find Elizabeth Laraki
----
Related Content
Podcasts:
What it means to be Design-Led
Complete Tutorial to AI Prototyping
5 AI Agents Every PM Should Build
Newsletters:
Ultimate Guide to Product Design
Ultimate Guide to AI Prototyping
How to Work With Design for Success
----
P.S. More than 85% of you aren’t subscribed yet. If you can subscribe on YouTube, follow on Apple & Spotify, my commitment to you is that we’ll continue making this content better.
----
If you want to advertise, email productgrowthppp at gmail.
This is a public episode. If you'd like to discuss this with other subscribers or get access to bonus episodes, visit www.news.aakashg.com/subscribe
The AI-powered Podcast Player
