Scrim UI

Inspiration

Evidence-driven articles on AI interfaces — product breakdowns that analyse a specific app element by element, and decision guides that answer one open question with concrete recommendations. Every claim is grounded in the product’s official docs and paired with a live demo you can copy.

Case study4 components
ChatGPT

The streaming-first chat interface

OpenAI's ChatGPT defined the AI chat surface — streaming reveals, a composer that never leaves view, and citations that appear only once grounded.

Read breakdown
Case study3 components
Claude

Reasoning traces, artifacts and a calmer visual language

Anthropic's Claude mainstreamed the thinking trace, artifacts that turn replies into canvases, and a warm low-contrast palette built for trust.

Read breakdown
Case study3 components
Perplexity

Search and generation in one surface

Perplexity rebuilt search around an LLM — and its UI earns trust through visible tool calls, sentence-level citations and a persistent sources rail.

Read breakdown
Case study3 components
Cursor

The agentic editor that made agent state visible

Cursor turned coding into an agent task — and solved the trust problem with a persistent agent status, auditable tool calls and an explicit approval gate.

Read breakdown
Guide4 components
Decision guide

Streaming vs. waiting for the full reply

Most AI products stream by default — but streaming is a UX decision, not a protocol one. Here is when a streaming reveal earns its place, when a single rendered answer is better, and how to tell the difference.

Read guide
Guide3 components
Decision guide

When should an AI agent pause for approval?

The moment a tool call becomes consequential, an agent needs a human gate. Here is when to pause, what to show in the approval prompt, and how to keep approval from turning into a rubber stamp.

Read guide
Guide4 components
Decision guide

Keeping users oriented during long-running agent tasks

A task that runs for minutes needs more than a spinner: live progress, visible steps, and an escape hatch. Here is how the products that ship long-running agents keep users oriented — and in control.

Read guide
Guide4 components
Decision guide

Interrupting the agent: stop controls done right

Every long-running agent needs a way out — but a stop button that discards work is as bad as none. Here is how real products handle interruption: non-destructively, cleanly, and with the partial work kept.

Read guide

More coming soon — Notion AI, Gemini, Replit and Lovable case studies, plus more decision guides.