Ready to design Intelligent Interfaces? We built a FigJam template with these seven lenses that you can use today:

🔗 sche.ma/toolkit

Do these lenses resonate with your work? How could you see using this toolkit?

#IntelligentInterfaces #AIUX

Lens 7: Persona Interrogation 🤖

An embodied AI partner—tutor, coach, therapist, creative collaborator. Focuses on depth over speed, building continuity through memory and consistent character. You can inspect, modify, delete memories in real-time.

Lens 6: Signal Monitoring 🚨

High-volume event streams where milliseconds count. AI classifies signals, executes pre-authorized responses, escalates edge cases. Critical for fraud detection, incident response, industrial safety—anywhere rapid response matters.

Lens 5: Ecosystems Exploration 🌐

Complex systems as dynamic causal graphs. You adjust parameters and watch ripple effects unfold. AI reveals downstream impacts and high-leverage intervention points. Suitable for supply chains, climate modeling, epidemiology.

Lens 4: Landscape Generation 🗺️

Knowledge becomes explorable terrain. Topics cluster together, similarity creates distance, zoom changes detail level. AI scouts promising areas while you navigate. Perfect for research databases, drug discovery, any vast information space.

Lens 3: Goal Planning 🎯

Organize work around outcomes in a strategic hierarchy. You set the high-level goals, AI suggests sub-goals and execution plans. Every metric connects back to what actually matters. Works beautifully for OKRs and strategy management.

Lens 2: Process Completion ⚡

Workflows become living playbooks instead of static checklists. Clear swim lanes show what’s human-only, AI-only, or collaborative. Great for CI/CD pipelines, CRM workflows, approvals—AI handles routine work, you handle the decisions.

Lens 1: Artifact Creation 🎨

Turn any creative surface into a collaborative workspace. You write, AI does inline generation and refactoring. GitHub Copilot is a perfect example—intelligence woven directly into the creative process.

Intelligent Interfaces are built on four layers that work together:

🧠 Intelligence Layer (language, vision, world models)
📚 Knowledge Layer (structured data)
⚙️ Automation Layer (workflows & integrations)
🎛️ Interface Layer (collaboration lenses)

Whether managing agents or co-creating artifacts or navigating physical and digital worlds, we need to come up with the new idioms for how people experience AI.

The only thing that is certain is that nothing will be the same.

Let’s build. #AI #design

We need to dream up entirely new ways for people to work together with AI that didn’t exist before.

It’s about being intentional about the world we want. Not fitting the world into the AI narrative. It isn’t about the technology alone—but how it can empower us to be better. More human.

We’re at the vanguard of something entirely new with AI.

The old language of interfaces—buttons, menus, dashboards—isn’t enough to envision, let alone create, what’s emerging.

We’re in uncharted territory where the only path forward is creativity.

Another experiment—dynamic flocking swarm algorithm with emergent behavior.

This one took only 2 prompts.

vibecoding keeps getting better.

#vibecoding #creativecoding

Thread inspired by excellent reporting from @ctrlzee.bsky.social: www.fastcompany.com/91341731/jon...

The real opportunity isn’t another input method or device.

It’s fundamentally reorienting interfaces around collaboration—where AI amplifies human creativity and judgment rather than replacing it.

That’s the paradigm shift: from operating AI to thinking with AI.

#HumanAI #FutureOfWork

But here's where I disagree with the #ZeroUI narrative:
Visual interfaces aren't disappearing. They’re becoming multimodal.

At @schemadesign.com we’re exploring #IntelligentInterfaces that respond to intent, not just commands, and adapt seamlessly across voice, gesture, context, and visual.I

Jony Ive talks about 3 major modalities in computing history:

- Command line
- GUI (mouse, folders, windows)
- Mobile (voice, multitouch, gestures, haptics)

Any other forms we’ve seen are just “tributaries.”

Now he’s betting on a fourth.

(via @ctrlzee.bsky.social at @fastcompany.com)

From a developer’s perspective, interfaces have become increasingly abstracted from source code.

Yet paradoxically, every UI evolution has reduced layers of abstraction for humans, getting us closer to directly manipulating content vs. wrestling with the machine.