Sanket Dongre / TinkerClaw

I'm building the next interfaces for working with agents.

TinkerClaw is my public workbench for turning interface questions into shipped products, open-source tools, and field notes. I'm exploring what comes after the chat box: voice, ambient reading, screen-aware controls, generated UI, XR, and mixed-reality workspaces.

Builder: SanketCurrent investigation: ScrollMethod: Build in public

Builder note

From investigations to products.

Active

I use this site to document the questions, prototypes, failures, and releases behind my agent-interface work. The output should be inspectable: essays, working demos, open repos, and products people can actually use.

PROBEARTIFACTESSAY
Now shipping#1 Scroll
Next surfacesVoice / XR / GenUI
PromiseBuild, test, publish

What will future agent interfaces feel like, and how do we know when they work?

01

Generative UI for Agents

Interfaces that emerge from model output: forms, panels, timelines, overlays, and task surfaces for agents when chat is the wrong shape.

02

Voice and Ambient Interfaces

Voice, narration, listening, interruption, and background presence as first-class ways to interact with agents. Scroll is the first example.

03

Spatial, XR, and Mixed Reality

Experiments where agents create or control interfaces across screens, rooms, headsets, simulations, and mixed-reality workspaces.

04

Evaluation and Trust

Rubrics, traces, and field notes for deciding whether new agent interfaces are clearer, safer, and less cognitively expensive.

Investigation #1 active

P-001

Scroll

Status: ShippingDomain: Ambient readingPlatform: macOS

Research question

Can a voice-based, screen-aware agent adapt to reading velocity in real time, and reduce cognitive load versus manual LLM querying?

Current artifact

Scroll for Mac: ambient voice narration, velocity-aware summarization, real-time Q&A over screen content, and a one-time purchase model.

What it tests

Screen OCR pipelines / velocity heuristics / low-latency voice / ambient UI / attention alignment

Reading context: active

Narrating

Velocity: 2.4x

Exploration areas.

P.01

Generative UI for Agents

How should agents decide when to answer with text, when to generate an interface, and what shape that interface should take?

P.02

Voice-Based Agent Interfaces

How should people talk to, interrupt, guide, and listen to agents? Scroll explores voice as an ambient reading interface, not just a command channel.

P.03

Ambient and Screen-Aware Interfaces

What happens when agents understand what is visible, where your attention is, and what you are doing before you explicitly ask?

P.04

XR and Mixed-Reality Agent Interfaces

How should agents appear in headsets, rooms, simulations, and spatial workspaces without adding clutter or cognitive load?

P.05

Human-in-the-Loop Agent Interfaces

How should humans inspect, interrupt, approve, roll back, and collaborate with AI systems that can act on their behalf?

P.06

Evaluation, Safety, and Observability

How do we measure agent interface quality, cognitive load, traceability, uncertainty, and failure recovery across modalities?

Artifacts and products.

The current tools stay intact. They now sit beside the research as shipped outputs, experiments, and commercial artifacts from broader agent-interface exploration.

Open artifacts.

Repos, rubrics, examples, and components released from the work. Enough is open to make the thinking inspectable.

About me.

I'm Sanket Dongre. I build TinkerClaw as a public workbench for future agent interfaces: voice, ambient, screen-aware, XR, mixed reality, and Generative UI.

My background sits at the intersection of human-factors visualization, spatial computing, AI agent architecture, and product prototyping. The thread through the work is simple: how should people understand, guide, interrupt, and trust increasingly capable agents?

Scroll is the first concrete investigation in that direction. It uses voice, screen context, and reading behavior to explore a more ambient way to work with AI without forcing everything through a chat box.

Human Factors VisualizationVoice InterfacesXR / Mixed RealityAI Agent ArchitectureProduct Prototyping
NameSanket Dongre
FocusFuture agent interfaces
MethodologyInvestigation → Artifact → Essay
Active investigationScroll
BaseTinkerClaw

Follow the investigations.

Low-volume dispatches: investigation updates, field notes, and new artifacts. No content treadmill.

Investigation status updates when things ship or change

Short observations from active work

New open-source artifacts as they are released