Skip to main content

Run a workflow

This page describes running a template or a saved workflow—not designing one. For the builder form and the AI design assistant, see Workflow Builder and Workflow Builder agent.

Start a run​

  1. Go to the Workflows tab in Nomic.
  2. Choose a workflow—Nomic templates are listed alongside your organization’s workflows (cloned or created from scratch).
  3. Start the run. You may be prompted for requested files (per-run inputs defined in the workflow). Attach or select files from project context as instructed.
  4. Wait for the Background Agent or interactive session to finish, depending on mode (below). You can often send follow-up prompts after the first pass to go deeper (especially for reviews).

Workflows respect the same permissions as the rest of Nomic: the agent only sees files you can access in the project or session.

Requested files vs context​

  • Requested files — Picked each time you run the workflow (this submittal, this drawing set). Described on the workflow card and in the run UI.
  • Context (configured in the builder) — Persistent files, folders, or tags attached to the workflow so every run sees the same reference material (for example, master specifications or firm standards).

If something is missing, the UI usually reflects what the workflow author asked for—good workflow descriptions on the card reduce back-and-forth.

Assistant modes​

Workflow authors pick how the agent runs:

  • Standard — Fast, conversational turns. Best for shorter tasks or when the user is iterating live with the agent.
  • Deep Research — More thorough reasoning and tool use before answering; suited to complex questions that pull from many files.
  • Background Agent — Runs autonomously until the workflow completes—ideal for long-running work: full drawing sets, submittal packages, multi-step reviews, or anything that should not block on each intermediate message.

Many review templates default to Background Agent because consistency and completeness matter more than instant replies.

Outputs and follow-ups​

Workflow runs produce artifacts—documents, tables, or drawing-review outputs—shown in the artifact panel. You can download (Excel, JSON, PDF markups where applicable) and often iterate: send another prompt to tighten scope, add checks, or resolve follow-ups without losing prior context.

Cost and duration

Long runs use more tokens and time. See Models & pricing for rough per-run expectations; scope projects and context to avoid pulling in unnecessary files.