World Congress 2026 Europe Jul 10, 2026 Session details

Giving AI eyes: How to build a dashboard you can't see

Josh Hobson

Stop your LLM from generating broken, overlapping user interfaces. Learn how to build a client-side feedback loop that gives AI the spatial awareness to self-correct layout mistakes.

Pause
Mute Enter Fullscreen
#1 about 6 min

Understanding the challenge of dashboards generated by blind AI

Developers tolerate faulty code generation but end users abandon applications when AI visual output algorithmically fails.

#2 about 6 min

Improving spatial awareness and structural layout for generated widgets

Providing metrics like gridline attachment and center of mass helps AI automatically fix overlapping layout structures.

#3 about 4 min

Verifying analytical reality and preventing empty dashboard data states

Exposing domain context and active filter boundaries prevents language models from generating charts with missing data.

#4 about 7 min

Enforcing visual integrity and readable information density limits

Converting data points into client-side pixel density metrics prevents unreadable charts with excessively clustered data segments.

#5 about 2 min

Reducing expensive language model iteration cycles for end users

Creating client-side visual linting rules enables reliable one-shot dashboard generation without repetitive manual prompting execution loops.

#6 about 3 min

Integrating embedded dashboards and future browser based agent protocols

Embedded UI layout libraries avoid server-side dependencies while evolving alongside emerging intelligent web standards like WebMCP.

#7 about 3 min

Addressing audience questions on feedback mechanisms and browser integration

Fine-grained quality scores guide AI UI adjustments while a dedicated browser harness processes generation tasks locally.

Matching moments

5:43 min

Pushing back against predictable AI interfaces

1:44 min

Replacing complex BI dashboards with live LLM queries

Jordan Tigani Jordan Tigani · World Congress 2026 Europe

1:47 min

Extracting AI capabilities into predictable dashboard interfaces

Osmar Matos Osmar Matos · World Congress 2026 Europe

9:45 min

AI agents replacing traditional web interfaces

4:28 min

Exploring artificial intelligence as a solution for web accessibility

Chris Heilmann +2 · LIVE

2:21 min

Transitioning from AI co-pilots to AI-native products

Jordan Tigani Jordan Tigani · World Congress 2026 Europe

Upcoming sessions on this topic

Open session

World Congress 2026 North America

You Can’t Re-Run Sunlight: Designing ML Data Architectures for Physical AI

An Phan

Senior Data Infrastructure Engineer @ Hippo Harvest

An Phan
Open session

World Congress 2026 North America

Closing the Visibility Gap: Lessons from Safety Critical Agentic Systems

Vivek Pandit

Principal Engineer at Cadence

Vivek Pandit
Open session

World Congress 2026 North America

No Single Model to Rule Them All: Building Resilient AI Agents Across Open & Closed LLMs

Emmanuel Acheampong

Senior Manager Developer Relations at Crusoe AI

Emmanuel Acheampong
Open session

World Congress 2026 North America

Small LLM in your Browser: Huge Opportunities for Web Applications

Daniel Ostrovsky

UI/UX Architect at Payoneer | AI Architect | Full Cycle Development Expert | Public Speaker | Open Source Contributor |

Daniel Ostrovsky
Open session

World Congress 2026 North America

Understanding LLM Architectures: Inside the Design of Modern Models

Jofia Jose Prakash

Director - AI & Governance at Humanity + AI, Inc

Jofia Jose Prakash
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