Importing and Exporting Flows

Importing and Exporting Flows

Every flow you build can be exported to a JSON file and imported into another agent. This lets you copy a working flow from a test agent to production, share flow templates across domains, and keep local backups before making big changes.

What Gets Exported

An exported file contains the full flow definition:

  • All states (nodes), including their instructions and tool configurations.
  • All transitions between states, including descriptions.
  • Routing configuration for Call Routing states.
  • Info collection field definitions and their actions.
  • Comfort message overrides (if configured).

The file does not include anything specific to a single agent: voice settings, company knowledge, phone numbers, or integration credentials. Those stay with the agent you import into, so you cannot accidentally overwrite another agent's setup.

Exporting a Flow

  1. Open the agent whose flow you want to copy.
  2. Go to the Flows tab.
  3. Click Export in the flow toolbar.
  4. The browser downloads a file named flows-<agentId>.json.

Save it somewhere you will remember. The file is plain JSON and safe to open in any editor if you want to inspect it, though hand-editing is not necessary for normal use.

Importing a Flow

  1. Open the target agent and go to the Flows tab.
  2. Click Import in the flow toolbar.
  3. Select a previously exported JSON file.
  4. The importer validates the file and loads the flow into the editor.
  5. Review the states, transitions, and tools. Save to commit the change.
Info
Importing replaces the current flow on the agent. If you want to keep the existing flow, export it first so you have a backup you can restore. 

What to Check After Importing

A flow is independent of the agent, but it assumes the target agent has the right integrations and data. After importing, verify:

  • Integrations — if the flow uses Calendly or Heartland tools, confirm those integrations are enabled on the new agent's domain.
  • Knowledge Base — if the flow has a Knowledge Base search tool, the new agent needs its own active Knowledge Base.
  • Extensions and phone numbers — Call Routing destinations from one domain will not resolve on another. Update them to the new domain's extensions.
  • Company info — prompts that reference "our Monday hours" or "our address" rely on the agent's training data. Make sure the target agent has equivalent content.

Common Use Cases

  • Test → production. Build and iterate on a test agent, then export and import into the production agent when ready.
  • Template reuse. Keep a library of exported flows ("basic lead capture," "after-hours router," "multi-location triage") and import them as starting points for new agents.
  • Backups before a big change. Export the current flow, make the edit, and keep the old file as a one-click rollback.

Validation Errors on Import

If the file was edited by hand or came from an older version, the importer may flag format issues. The editor converts older formats automatically on save when it can. If you see a hard error, the safest fix is to re-export from the source agent on the current version and try again.


Still have questions? Submit a ticket and we will help you move flows between environments.
    • Related Articles

    • Building Conversation Flows

      A flow is the conversation blueprint for your AI Agent. It defines the stages of a phone call, what the agent does at each stage, which tools it can use, and when the conversation moves forward. Think of it like a flowchart: each box is a stage the ...
    • Zapier Post-Call Automation

      Zapier is the fastest way to turn an AI Agent call into action somewhere else — a row in a spreadsheet, a lead in a CRM, a message in Slack, a task in a project tracker — without writing any code. This article walks through the end-to-end setup using ...
    • State based vs Prompt Engineering

      There are two ways to control how your AI Agent behaves on a call: write one long system prompt that tries to cover every situation, or build a flow with states that change the agent's focus as the conversation moves forward. This article explains ...
    • Call Summaries

      Every AI Agent call generates a full transcript and a short AI-written summary. The summary is the piece most teams actually read — a two-to-four-sentence recap of why the caller called, what was discussed, and how it ended. This article explains ...