Skip to content
Scrim UI

The pattern library

Patterns

Start from a complete AI screen, then remix it. Each of the 12 patterns ships as one React + Tailwind file built from this library’s components.

AI Chat339 lines

The canonical chat interface — sidebar, streaming messages, prompt input with model selector, and sources.

8 components

Conversation SidebarResponse VersionsStreaming MessagePrompt InputContext PickerPrompt Input + Model SelectorCitation UISource Card
AI Research Assistant159 lines

A research flow that shows search tool calls, reasoning, sources and a cited final answer.

4 components

Search Tool CallThinking / ReasoningCitation UISource Card
AI Coding Agent162 lines

A coding run with agent status, tool calls, diffs and a human-in-the-loop approval gate.

3 components

Agent StatusTool CallApproval Request
AI Voice Assistant267 lines

A voice-first conversation — live waveform states, a recording input, a spoken transcript and a typed fallback.

5 components

Voice InputVoice WaveformVoice ConversationStreaming MessagePrompt Input
Model & Memory Preferences199 lines

A preferences screen that picks the model, reasoning level and tools, and manages persistent memory.

4 components

Model SelectorReasoning LevelTool ToggleMemory List
Artifact Workspace417 lines

Chat on the left, generated output on the right — artifacts open from the answer, stream, version, and fail without breaking the conversation.

5 components

Conversation SidebarStreaming MessageResponse VersionsPrompt InputArtifact Preview
Document Q&A Workspace327 lines

Ask your own documents — upload and parse, cited answers with inspectable passages, an honest not-found state, and a visible context budget.

7 components

File UploadContext FilesContext UsageCitation UISource ListStreaming MessagePrompt Input
Structured Extraction & Review333 lines

Upload a document, watch fields fill in, then review the flagged ones — per-field confidence, corrections that keep the original, export earned.

4 components

File UploadAgent StatusConfidence AnswerInline Correction
Image Generation Studio211 lines

A one-screen generation studio — prompt composer and model picker beside a feed of queued, staged, blocked and ready image results with variants.

3 components

Generated Media ResultPrompt InputModel Selector
Multi-agent Ops Console257 lines

Watch a fleet of agents at once — parallel statuses, an inspectable handoff, a waiting approval, a failed child run, and per-run plus fleet cost.

3 components

Agent Run TimelineAgent StatusAgent Handoff
Customer Support Copilot284 lines

Grounded reply drafts with citations, honest low-confidence answers, inline corrections, an approval gate on refunds, and a rating row on every draft.

8 components

Conversation SidebarContext PickerCitation UISource ListConfidence AnswerInline CorrectionApproval RequestResponse Rating
Generative UI Dashboard399 lines

The model assembles a dashboard from a controlled widget registry — streamed props, an unsupported-request fallback, and widget clicks that re-enter the chat.

5 components

Generative UITool CallArtifact PreviewError & RetryPrompt Input