Studio hub
GAFlowise on the live graph. Visual agent builder · trigger → query → transform → action with graph-typed nodes.
What it is
Studio Agents is the drag-and-drop builder for designing AI workflows and running them as live APIs, chat widgets, scheduled jobs, or shareable links. A rich palette of building blocks covers language model steps, knowledge retrieval, document loading, actions across more than seventy business apps, branching logic, custom code, and human approval steps. Each workflow runs with full visibility into cost, usage, and timing, plus version history, saved test sets, and securely encrypted credentials, and connects to the rest of your Product Graph through a shared data model and programmatic access.
See it in the product
Top 4 capabilities
Each capability is the parent of dozens of typed features in the production taxonomy. Hover any feature in Studio to drill into the underlying nodes.
43 features
Studio Agents ships with around eighty building blocks organized into ten categories, from language model steps to knowledge retrieval to business-app actions. Each block has a clear set of inputs, outputs, and settings, an icon, and a readable label, and the catalog is extensible so your team can add its own custom blocks while we ship new ones in regular releases.
14 features
Studio Agents includes more than seventy first-party connectors spanning customer relationship management, email, calendar, chat, ticketing, files, developer tools, analytics, payments, human resources, and finance. Each connector exposes the actions, event triggers, and record lookups it supports, along with its sign-in method and usage limits, and the builder uses this information to generate the right configuration form automatically.
13 features
The toolbar is the persistent control bar above the canvas, offering run, stop, save, version, publish, share, embed, export, import, and settings, plus a live run-status indicator. Settings opens a panel for workflow-wide configuration, including name, description, icon, tags, default trigger, spending limits, usage limits, environment values, approved embedding sites, sharing permissions, and the assistant persona used for chat and embedded experiences.
14 features
The inspector opens whenever you select a block and presents a guided form tailored to that block, with the right input for each setting, including text, numbers, sliders, code, structured data, credential pickers, model pickers, and file uploads. Inline help, default values, and validation keep configuration clear, advanced options cover retries, timeouts, usage limits, and fallbacks, and a preview of the block's most recent successful result lets you iterate without re-running the entire workflow.
More from the Studio hub
Composable dashboards built from graph queries. Refresh as the graph refreshes.
Whiteboard the workspace. Diagram strategy. Map the graph.
JupyterLab on the live graph. `pyramyd.query()` returns a DataFrame in one line · PYRAMYD widgets render inline · Y.Doc multiplayer with the workspace.
Spreadsheet-native views on the live graph. Edits push back to nodes.
Long-form documents co-authored with APEX and grounded in the graph.
Slide decks that refresh from the graph at present time.
30-minute walkthrough. We'll filter the workspace to your category and walk through the top capabilities live.
