WeAreDevelopers Logo WeAreDevelopers
Sign in
For You LIVE
World Congress 2026 Europe • Jul 10, 2026 • Session details

Design Patterns For AI Products in 2026

Vitaly Friedman

Stop defaulting to lazy text boxes. The endless AI chat is dead. Discover intent-driven design patterns that operate silently in the background and rebuild user trust.

Pause
Mute Enter Fullscreen
#1 about 1 min

Designing artificial intelligence experiences for restrictive public sector environments

Structuring artificial intelligence integrations requires analyzing how users actually behave rather than focusing solely on technical capability.

#2 about 3 min

Evolution of digital interfaces and web capabilities over time

Historical user interfaces showcase how early spatial interactions and multi-service integrations influenced modern expectations for data presentation.

#3 about 2 min

Frustrations with modern puzzles and conversational text box interfaces

Endless verification puzzles and unstructured text prompts force users into annoying cycles of waiting and guessing.

#4 about 2 min

Improving efficiency with pattern recognition and canvas interfaces

Visual search and spatial canvas interfaces provide natural ways to explore data without complex text prompts.

#5 about 2 min

The shift from human prompt engineering to AI-generated prompts

Allowing language models to construct their own optimal prompts based on basic user intent yields better results.

#6 about 2 min

Automating tedious workflows while retaining traditional filter controls

Integrating artificial intelligence with classic sorting and filtering mechanisms accelerates complex data manipulation without removing user control.

#7 about 3 min

Analyzing the illusion of productivity and AI-induced workload increases

Introducing agents often leads to more time spent cleaning up errors rather than unlocking genuine efficiency gains.

#8 about 4 min

Growing consumer distrust and the declining brand reputation of AI

Users and brands increasingly reject artificial intelligence artifacts in favor of authenticity and human verification.

#9 about 2 min

Identifying core user complaints regarding AI unpredictability and latency

User research reveals severe frustration with silent assumptions, hallucinated facts, and unreliable agent outputs.

#10 about 3 min

Designing contextual scaffolding and co-pilots within existing user workflows

Positioning conversational assistants directly alongside user tasks prevents the friction of constantly toggling between different interfaces.

#11 about 1 min

Building trust through direct source verification and verifiable citations

Search engines must prioritize citing exact source fragments to establish reliability and combat model hallucinations.

#12 about 3 min

Exploring deep integrations with multimodal cursor and voice interactions

Combining pointer context with voice commands allows users to seamlessly express complex fluid intents without text inputs.

#13 about 2 min

Eliminating manual prompt engineering by delegating intent to AI

Translating user intent directly into customized outputs like audio podcasts removes the need for complex manual prompting.

#14 about 2 min

Structuring user intent using tactical pre-prompts and task builders

Providing users with distinct conversational planning steps and preset tasks dramatically lowers the barrier to entry.

#15 about 2 min

Applying traditional UI controls and filters to AI outputs

Enhancing generated results with standard dropdowns and filter buttons empowers users to manipulate data intuitively.

#16 about 1 min

Implementing asynchronous request queuing to prevent user workflow interruptions

Allowing users to stack requests in a continuous queue eliminates frustrating idle periods during generation processes.

#17 about 2 min

Replacing prompt modifications with visual sliders and precision knobs

Swapping text-based iterations for multidimensional sliders empowers rapid experimentation and batch generation across varied logical dimensions.

#18 about 1 min

Merging multiple inputs and adjusting weightings via spatial canvases

Letting users visually combine multiple data sources on a single coordinate plane enables nuanced risk tolerance blending.

#19 about 2 min

Embedding artificial intelligence directly within enterprise data grids

Designing interactive spreadsheet cells that surface analytical assumptions significantly boosts confidence in automated financial reporting.

#20 about 3 min

Maintaining human accountability in AI-assisted enterprise interface design

Despite advanced agent frameworks, ultimate responsibility for critical operational decisions must remain exclusively with human operators.

Matching moments

2:11 min

The shift from predictable UX to adaptive AI experiences

Madalena Costa Madalena Costa · Europe 2026 Virtual

3:07 min

Adapting product design for proactive and agentic AI

Ekaterina Streltsova Ekaterina Streltsova · Europe 2026 Virtual

4:38 min

Designing user experiences defensively against AI application failures

Krzysztof Cieślak Krzysztof Cieślak · World Congress 2024

1:25 min

Expanding AI across the product development lifecycle

Daniel Geisel Daniel Geisel +1 · World Congress 2026 Europe

3:46 min

Designing AI interfaces for user autonomy and control

Christoph Bräunlein Christoph Bräunlein +3 · World Congress 2025

5:43 min

Pushing back against predictable AI interfaces

More from World Congress 2026 Europe

Building the Nervous System of AI - Michael Kagan (NVIDIA) thumbnail
29:17
3 months ago

Building the Nervous System of AI - Michael Kagan (NVIDIA)

Michael Kagan, Sead Ahmetović

Five Things in Tech that Matter Now - WeAreDevelopers World Congress 2026 Closing Keynote thumbnail
19:41
3 months ago

Five Things in Tech that Matter Now - WeAreDevelopers World Congress 2026 Closing Keynote

Christian Heilmann

The Sound of Your Secrets: Teaching Your Model to Spy, So You Can Learn to Defend thumbnail
32:06
3 months ago

The Sound of Your Secrets: Teaching Your Model to Spy, So You Can Learn to Defend

David vonThenen

Super scaling for the Super Bowl: How to survive 30 million users hitting your backend in 30 minutes thumbnail
35:13
3 months ago

Super scaling for the Super Bowl: How to survive 30 million users hitting your backend in 30 minutes

Irina Branovic

Running Secure Life Science Research at Scale using Hybrid GPU HPC and Kubernetes 🧬 thumbnail
24:23
3 months ago

Running Secure Life Science Research at Scale using Hybrid GPU HPC and Kubernetes 🧬

Jeremy Murray

Angstfreude - AI and Corporate Culture - The Thrill and the Threat thumbnail
30:26
3 months ago

Angstfreude - AI and Corporate Culture - The Thrill and the Threat

Axel Ebert, Karin Krobath

Related videos

Designing AI-first products: When the interface is no longer the product thumbnail
20:10
Europe 2026 Virtual • 3 months ago

Designing AI-first products: When the interface is no longer the product

Ekaterina Streltsova

AI-Driven Interfaces: Designing the New Grammar of Interaction thumbnail
36:14
Europe 2026 Virtual • 3 months ago

AI-Driven Interfaces: Designing the New Grammar of Interaction

Markus Nissl

Designing the intelligence layer: The future of products beyond interfaces thumbnail
24:21
Europe 2026 Virtual • 3 months ago

Designing the intelligence layer: The future of products beyond interfaces

Madalena Costa

The age of agency: When products start to think and act thumbnail
24:21
Europe 2026 Virtual • 3 months ago

The age of agency: When products start to think and act

Madalena Costa

The integrated AI experience: A New Paradigm in an Agentic World thumbnail
30:20
World Congress 2026 Europe • 3 months ago

The integrated AI experience: A New Paradigm in an Agentic World

Loredana Crisan, Markus Rautert, Stefan Ostwald, Anna Heim

Insight into AI-Driven Design thumbnail
14:29
World Congress 2024 • about 2 years ago

Insight into AI-Driven Design

Madalena Costa

Related articles

From learning to earning

Jobs that call for the skills explored in this talk.