Wiring rules an AI agent reads before using Atelier components.
Wiring rules an AI agent reads before using Atelier components.
the agent works on its own branch, and the diff merges only after every test passes.
Animated brand-neutral AI agent run — a Thinking status and short plan, tool calls whose spinners close into checks while a timer counts real seconds, then a markdown answer with citations and a code block that streams in irregular token bursts. Light/dark themes.
AI agent run animation: a prompt sent and answered with visible tool steps. A prompt typed, sent, and answered by an agent that shows its work. A composer opens, a request types itself into it under a colour wave that rides the caret — the last dozen characters run accent into ink behind it — and a round button appears when there is something to send. The shot cuts in close on that button: one frame, 1.9×, with no intermediate value anywhere in the recording, because a zoom onto a button the viewer has watched for four seconds says nothing. A pointer climbs to it and stops dead for three frames before it presses, the field floods, and a second cut hands the frame to the run — a dotted rail with one step lit at a time, each arriving from below, typing two lines about what it is doing, and passing the frame on at a measured 31.4 frames. The composer's scale came off the card's own sub-pixel width, whose edge is five levels of luminance and needs a derivative rather than a threshold; the step cadence off the frames each title's accent burst begins. The field's wash and bloom were fitted to sixteen samples across the frame.
A presentation-only timeline for a multi-step agent / automation run: an ordered rail of steps with tool calls, outputs, errors, retry attempts, optional nested sub-stages, human approval checkpoints, and run-level lifecycle controls (cancel / resume). The app owns the run and every status; the component never executes an agent, generates reasoning, invents confidence, or claims a step succeeded on its own.
the agent works in a sealed cell, and only the diff it wrote gets out.
A component for providing an agent's session context and ensuring remote participants’ audio tracks (microphones and screen share) are audible.
Watch an agent sort a bike shop's messages: each note is read under a blue light, labelled and filed in a pigeonhole. Copy the React code or HTML free.
Run state pill (thinking, working, waiting for approval, done, stopped, error) announced through an aria-live region.
A runtime task summary chip with an optional tray for every task in the thread.
A compact task summary with the current activity and an optional task tray.
AI agent steps animation: a streaming task log with spinner and checkmarks for agent demos. An agent narrating its own work: the prompt lands in a pill, and under it a log writes itself one line at a time — each step running with a faint spinning globe, then flipping to past tense behind a check while the whole column steps up a row so the live line always sits on the centre. When the work is done the column swells and clears, and the last line slides to the middle and becomes the answer. Every proportion and every curve is fitted from frame measurements.
Agent steps drawn on a canvas as an enamel switchboard: patch cords hang with rope physics and a lamp lights per step. React code and HTML, free to copy.
Tailark task-planning agent illustration
Tailark tasks agent illustration
Vertical log of what an AI agent did, one row per step: an icon for the kind of step (think, search, read, tool, write), the title, a detail line, live running state and a done summary.
AI agent tools animation for agent and MCP product demos. The moment somebody hands an agent their tools. A spark writes a line word by word, each new word arriving in the accent and setting to ink behind it; the line is whipped away on three frames of horizontal blur and the next one is written back the other way, the spark walking left and laying words down behind it. A composer fades up underneath, a pointer arrives and presses into the field, the prompt types itself, the attach menu drops from the plus, the connectors submenu opens beside it, and the connectors switch on one at a time before the pointer leaves for send. The reply is deliberately not here — @snapcn/agent-chat already streams one and this hands off to it.
Agent trace is a production-ready ai component from BJORK UI, packaged for shadcn registries.
Tool calls as ruled rows, with state, tool, argument and duration. Expand a row to see its output.
A control for managing media tracks (microphone, camera, screen share) with appropriate icons and loading states.
A toggle button for controlling media tracks (microphone, camera, screen share) with appropriate icons and loading states.
Tailark workflow agent illustration
A typed Anguilla flag component with no-crop 4:3 and 1:1 frames plus SVG, PNG, WebP, and JPEG support.
Showing 313–336 of 27,979
Showing 313–336 of 27,979