World Congress 2026 Europe - Virtual Stage • Jul 2, 2026 • Session details

AI-Driven Interfaces: Designing the New Grammar of Interaction

Markus Nissl

The chatbox is a severely limiting interface for AI. Modern systems demand a new grammar of collaboration. Discover 12 UI patterns to build interfaces users actually trust.

Pause
Mute Enter Fullscreen
#1 about 5 min

Limitations of chat interfaces in generative artificial intelligence

The standard chat window restricts visibility into autonomous model actions and complex decisions.

#2 about 4 min

Shifting user interaction from predictable commands to collaboration

Unpredictable generative responses require a new design language built around permission and trust gradients.

#3 about 5 min

Communicating response confidence and citing generated sources visually

Confidence lenses and explicit source citations help users gauge the reliability of synthesized answers.

#4 about 2 min

Setting boundaries and requesting verification before autonomous execution

Pausing for user confirmation via bounding boxes or diffs prevents unwanted system actions.

#5 about 3 min

Branching explorations and merging selective outputs in workflows

Generating multiple options and composing the best elements provides users with precise creative control.

#6 about 3 min

Managing agent autonomy levels and execution budget constraints

Trust contracts are established by limiting agent actions through explicit autonomy dials and resource budgets.

#7 about 4 min

Aligning models by storing corrections and editable user memory

Allowing users to inspect and edit saved preferences ensures models adapt accurately to personal workflows.

#8 about 2 min

Replaying asynchronous agent actions through visual activity logs

Visual summaries and version logs reveal what autonomous agents accomplished while the user was away.

#9 about 3 min

Choreographing interface wait times during prolonged model generation

Streaming thought processes prevents users from misinterpreting long processing times as software bugs.

#10 about 4 min

Transferring context and providing detailed receipts for execution

Temporal handoffs and cost receipts create transparent audit trails for completed generative tasks.

#11 about 7 min

Designing accessible interfaces and anticipating spatial memory patterns

Future interface designs will require multimodal accessibility and spatial layouts to manage disparate agent outputs.

Matching moments

1:32 min

Architectural patterns for developing robust generative AI applications

Julián Duque Julián Duque · World Congress 2025

3:46 min

Designing AI interfaces for user autonomy and control

Christoph Bräunlein Christoph Bräunlein +3 · World Congress 2025

2:43 min

Moving past chat interfaces to domain-specific artificial intelligence modalities

Kris Rasmussen Kris Rasmussen +1 · World Congress 2024

2:11 min

The shift from predictable UX to adaptive AI experiences

Madalena Costa Madalena Costa · Europe 2026 Virtual

1:44 min

Summarizing developer experience and artificial intelligence companions

Robert Hoffmann Robert Hoffmann +1 · LIVE

3:22 min

Comparing AI agents with generative models and chatbots

Xavier Sala Presas Xavier Sala Presas · Europe 2026 Virtual

Upcoming sessions on this topic

Open session

World Congress 2026 North America

AI That Argues With Itself: Building Self-Debating Systems That Catch Their Own Bugs

Shreya Singhal

AI Applied Scientist at Claritev

Shreya Singhal
Open session

World Congress 2026 North America

Designing APIs That Survive AI Agents at Scale

Phani Pendurthi

Mastercard, Principal Software Engineer

Phani Pendurthi
Open session

World Congress 2026 North America

Building Stuff with GenAI - The Open Minded Workshop beyond OpenAI

Andreas Erben

CTO for Applied AI and Metaverse at daenet

Andreas Erben
Open session

World Congress 2026 North America

When Agents Became Users: Rearchitecting Identity and Permissions for AI at Scale

Yoav Gal, Dor Cohen

Yoav Gal
Dor Cohen
Open session

World Congress 2026 North America

AI Agents are Only as Smart as their Context: Building a Real-Time Context Engine at Intuit

Bharat Patel

Lead Software Engineer at Intuit

Bharat Patel
Open session

World Congress 2026 North America

Beyond the Code: Human-AI Synergies in Product Development

Ajita Kanchivakam Ananth

Staff Technical Program Manager at Google

Ajita Kanchivakam Ananth