An AI agent's run in one line: a dot-matrix orb, a verb that rolls to each tool it calls, the live call streaming underneath, then a summary that opens to every step.
An AI agent's run in one line: a dot-matrix orb, a verb that rolls to each tool it calls, the live call streaming underneath, then a summary that opens to every step.
Agent thinking and tool calls, task progress, approvals, and a final run summary.
Example usage of Agent Run.
Vertical timeline of agent tool steps with status icons, tool badges, mono query detail lines, durations, and a raw log link.
A full-screen agent session block with transcript, controls, and I/O media tiles.
A Wrenfield start screen for an agent app: recent sessions down the side, one prompt box with attachments, a model key and a mode key, suggested tasks that fill the prompt when picked and the latest runs with their state, where a run that waits is allowed or denied in place. Behind it a field of mono glyphs shows in a soft lens that follows the pointer, and a press on empty space sends a ripple through it. Plug your agent into onSend, onApprove and onDeny.
A timeline of tool calls with status, arguments, results, and parallel sub-steps.
Example usage of Agent Steps.
A prompt types itself and branches out into three agents, each with a role and overlapping tool logos
Example usage of Agent Tree.
Organizes missions, thinking, tool execution, human approval, and evidence into one continuous agent product page.
A Ferrowick agent workspace: sessions grouped by day with a search that go into a sheet on phones, a thread where thinking, tool calls that open to their input and result, result cards and a request waiting for Allow or Deny arrive as the agent works, and a composer that takes photos and files, tools and skills, queues what you write while the agent answers and sets how hard it thinks on a ramp of five dots you tap or drag. Plug your agent into onSend, onApprove and onDeny.
Two agents edit a brief like teammates: a named pointer glides to a paragraph and its suggestion types itself in as a tracked change, a margin comment arrives after a typing mark, and a table lists every change.
A day of agents at a glance: totals that roll between Today and 7 days, requests approved in place, a fleet whose rows unfold their sub-agents, and when the last request leaves a check draws itself where the list was.
Showcase card for an AI agent or assistant with avatar, name, description, capability badges, sample conversation preview, stats row, and action buttons. Perfect for agent directories and AI product pages.
A composed, app-controlled AI agent workspace that composes Agent Run Timeline + Tool Call Activity + AI Response Stream + Source Citation Rail into one realistic full page; the app owns every state and it never simulates a model.
A whole assistant screen: starter cards, reasoning, tool calls, an approval before it emails anyone, and a streamed answer, with past conversations beside it.
Floating AI assistant with document-aware writing actions and local chat history.
Interactive 3D badge component with Atropos effect, customizable branding, QR code, and AI avatar support
Two ring framed panels under a centered heading listing what the assistant does and never does, closed by a contractual footnote.
Feature grid section showcasing AI capabilities. Each card includes an icon, title, description, and a mini chat bubble preview demonstrating the capability.
Chat home with a sidebar of grouped chat history, a header model menu with copy link and share buttons, a composer with research, image and reasoning toggles, a connect tools row and three starter cards.
Recruiting assistant with a searchable sidebar, a welcome composer with Attach, Upload images and tone select, four feature cards and a Conversations column with rename and delete menus on wide screens.
Finance assistant with a workspace menu, sidebar navigation with a Budget badge, a trial card, a model banner above the composer, attach, image and receipt buttons and three prompt cards that a Refresh button swaps.
Showing 25–48 of 468