Kortshut
Designing a context-first operating system.
An ongoing exploration of AI-native workflows, and what computing looks like when context matters more than the apps you're in. This is a record of how the thinking is evolving, not a finished product.
Focus areas
- Product Strategy
- AI Workflow Design
- macOS Product Design
- Information Architecture
- Human–AI Interaction
- Design Systems
- AI-Assisted Development
The shift
LLMs didn't remove the work. They moved where it happens.
The bottleneck was no longer writing. It became assembling enough context for the AI to produce something useful.
Every design review, engineering task, research session, and strategy doc followed the same loop: grab some information, screenshot, copy text, switch apps, rebuild the context, prompt an AI, go back to work, and do it again.
The models got better fast. The workflow didn't. Kortshut started as an attempt to cut that friction.
Observation
Computers organize work around files and applications. People organize work around context.
A designer isn't thinking about Figma. They're thinking about redesigning onboarding. A developer isn't thinking about Finder. They're thinking about fixing a bug, using notes, screenshots, logs, and earlier discussions.
Today's operating systems know where files live. They don't know why those files belong together. That gap became the basis for every product decision that followed.
Early hypothesis
“If we make AI easier to access, people will work faster.”
Early concepts chased faster prompting, keyboard shortcuts, AI launchers, and a better clipboard. They made things quicker, but missed the bigger problem.
The real bottleneck wasn't opening AI. It was rebuilding context before every conversation.
Research & continuous discovery
Kortshut evolved through steady observation and dogfooding, not a fixed philosophy.
The same patterns kept surfacing: screenshots became temporary memory; clipboard contents disappeared despite remaining valuable; users repeatedly rebuilt the same prompt context; AI quality depended more on context than prompt wording; and keyboard shortcuts only mattered when attached to repeatable workflows.
That shifted the product away from “AI utilities” toward workflow orchestration.
Why context, not prompts
Early versions leaned on prompts. What we saw was that people cared far less about prompts than about outcomes. The better question turned out to be: how fast can someone gather everything the AI needs without breaking their flow? That still guides the roadmap.
Exploration 01 — Persistent context
What if copied information wasn't disposable, but persistent working memory?
Instead of treating the clipboard as throwaway, we explored it as working memory that sticks around. Past clipboard items, screenshots, and saved references became reusable pieces of context rather than temporary scraps.
The goal wasn't to remember what had been copied. It was to recover the thinking behind it.
Exploration 02 — Workflow shortcuts
Keyboard shortcuts were never the point. They were a way into repeatable workflows.
The real design challenge shifted from cutting clicks to protecting focus.
The workflow, compressed
We stopped designing around prompts.
- Initial belief
- Prompts were the primary unit of interaction.
- Observation
- Users repeated workflows more consistently than prompts.
- Current direction
- Design around reusable workflows that naturally contain prompting.
The clipboard became working memory.
- The shift
- Copied content stopped being transient and became searchable, referenceable, and context-aware.
- Status
- This remains an active area of product exploration.
What we chose not to build
Kortshut deliberately avoids becoming another chatbot, launcher, note-taking app, or prompt marketplace. Those already exist. The opening is in connecting them through context.
Designed while adopting AI
Kortshut was designed while leaning on AI throughout. Claude Code, Cursor, Codex, Google Stitch, and Figma AI sped up prototyping, implementation, and experimentation. They shortened the loop between a hypothesis and a real test, without replacing the design thinking.
How my thinking changed
Open questions
- Should context be assembled manually, or inferred automatically?
- Is the clipboard the right primitive, or is context itself the primitive?
- When does automation become invisible enough to feel natural?
- How should AI balance initiative with user control?
An active exploration
Kortshut remains an active exploration into that problem. Rather than documenting a finished product, this case study documents an evolving way of thinking about human–computer interaction in an AI-native world.
The product remains alive. The thinking continues.