How to Create a Playbook

the system defaults to time out at one hour for a playbook, and 15 minutes for a connector action keep this in mind when creating playbooks to execute and run playbook action input and outputs are limited to 20mib you should always narrow data down as much as possible for playbook and action performance how to create a playbook use this topic to create playbooks manually or with hero ai (text to playbook) for an overview of playbooks, the canvas, and the playbooks home page, see docid 3h4uaq7pbxjvmdlqlmhhy create a new playbook manually from the navigation menu, click orchestration click playbooks from the playbooks home page task bar, click the plus menu icon, and then select create a new playbook in new playbook window, enter a name for the playbook and (optionally) a description , and then click save the playbook opens add a trigger and actions from the add panel connect actions to define the flow enable the playbook when you are ready to run it configure action inputs and outputs as needed in the action configuration panel test the playbook from the canvas using the docid\ z n fzu9tdqmf3h5dkpxy if you want to import swimlane solution package files ( ssp files), see docid\ j2f6qukefkwhivncuwpd4 enabled playbook toggle to view details about how to enable/disable a playbook, click docid\ dtzbvsf7cf86ihgiguqwt create or modify with hero ai hero ai includes a playbook generator agent that lets you create or modify playbook flows using natural language in canvas open a playbook in canvas if the canvas is empty (new playbook), click start building with hero ai on the canvas if the playbook already has content, open the hero ai companion describe what you want to build (for example "create a playbook that fetches alerts from crowdstrike every 5 minutes, extracts observables, and enriches them with virustotal ") review the generated flow and iterate with follow up prompts when hero ai enters playbook building mode , you can create a new flow or select an existing flow in canvas before asking for modifications if a playbook has multiple flows, select the flow you want to edit in canvas, then ask hero ai to update it if you want to create a new flow, you must deselect any currently selected flow if you need to stop a request while the playbook is being generated, click cancel on the canvas modify an existing flow select the flow you want to change in canvas ask hero ai to update it (for example "add an ip reputation check after the enrichment step and branch if malicious ") review the updated flow and refine as needed ask questions about existing flows the playbook generator agent is not limited to creating or modifying flows — you can also use it to understand what an existing flow does open the hero ai companion from any playbook canvas and ask questions such as "what does this flow do?" "explain the steps in this playbook " "why would this flow branch at the condition step?" hero ai will analyze the selected flow and provide a plain language explanation, making it easier to onboard new team members, audit automation logic, or troubleshoot unexpected behavior prompt tips be explicit about triggers, actions, and data sources use step placement language (e g , "after \[step name]" or "before \[step name]") ask for error handling when external integrations are involved playbook generator agent capabilities and limitations create and modify a playbook (individual flow) or a componentmodify user defined interfaces, aka input and output schemas (for components) publish fields to the properties in the output schema (for components)add a new flow to a playbook or modify an existing flow (for playbooks) add, modify, or delete cron triggers (for playbooks) delete record, flow, and webhook triggers (for playbooks) modify conditions for record, flow, and webhook triggers (for playbooks) add, configure, and delete components available in the tenant add, configure, and delete actions of connectors available in the tenant add or change the asset used by a connector action add, configure, and delete native actions condition, loop, parallel, create/update variable, search records, create record, delete records, scripts, transformations, hero ai, http connect actions with on success, on failure, and on complete connections not supported add, replace, or configure schemas for flow, webhook, record triggers, or playbook button (for playbooks) add or modify existing interfaces, aka intents (for components) enable or disable a flow or trigger via prompt (for playbooks) query application records or answer general turbine usage and documentation questions while in playbook building mode (planned for a future release) mark action inputs as sensitive (for example, the hero ai native action prompt) use variables from assets unless they are mapped to connector actions test or run components/playbooks reference playbook/component runs create or edit multiple flows from a single prompt configure or update connector's retry, delay and limit conditions save, duplicate, copy, export or package components or playbooks mark/unmark component as visible to hero ai, as requiring confirmation to execute, or convert a component into ai agent or vice versa create or modify application, application settings and configurations including fields and their values, and read application records cannot select and group actions into a (sub) component notes and considerations prompts in hero ai native actions, python scripts, and jsonata transformations are not validated and may be incorrect review complex (multi level, multi group) filters in loops, conditions, search records, and trigger conditions to ensure that they are correctly prepared filters in search record action by application fields with predefined list values having more than 10 distinct values have high chances of being incorrect not supported in search records for end to end validation, use the docid\ z n fzu9tdqmf3h5dkpxy