Playbooks
A playbook is a reusable method that the agent reads before it starts and then follows. Playbooks make your firm’s methodology, templates and sign-off rules the default way the agent works.


What a playbook contains
Section titled “What a playbook contains”A playbook says when it applies, what information it needs, the steps to follow, the moments that need approval, and what counts as done.
- Name: a recognizable workstream, such as “GP to Intacct: vendor and AP migration”.
- Scope: when the playbook applies. The agent matches requests against it. Name the systems, the action or the recurrence.
- Prerequisites: what must be in place before work starts, such as system access, source files and client decisions. The agent checks the project’s files first and asks you for whatever is still missing in one message.
- Phases: the steps of the method in order, each with a title and its activities, owners and outputs.
- Deliverables: what the work produces, such as a field mapping, a reconciliation report or a cutover runbook.
- Sign-off: who approves the result and what they check, for example “The client approves the reconciliation report before cutover.” The agent stops at each sign-off.
Use a built-in playbook
Section titled “Use a built-in playbook”superglue ships with five playbooks that cover the common workstreams:
| Playbook | When it applies |
|---|---|
| Start a project | Set up a client project from connected email or from your description |
| Migrate data | Plan or carry out a migration, define mappings and transformations, validate the result |
| Build an integration | Build tools that read, write, or move data, one-off or recurring |
| Create an MCP server | Expose selected tools to an MCP client such as Claude or Langdock |
| Set up a support agent | Set up an agent that works on a client’s tickets and asks you before it changes anything |
They appear on the session start screen. Select one, or describe the task and let the agent match it.
Built-in playbooks are read-only. To adapt one, ask the agent to copy it into a new playbook and change the copy.
Write your own playbook
Section titled “Write your own playbook”- Open Brain › Playbooks and select New playbook.
- Describe the method to the agent. You can also ask the agent to draft one from a completed engagement: “Turn the way we ran the Contoso vendor migration into a playbook for GP to Intacct migrations.”
- In each phase, name the tools, connections and Brain files that the phase uses, and say when the agent should read each file.
Naming resources gives the agent context. It does not restrict the agent from other permitted resources.


Edit and download
Section titled “Edit and download”- A playbook opens as one formatted document in your organization’s design system. Editors change it in place, and it saves on its own.
- Download saves it as PDF or Word in the same branding, or as Markdown, so you can hand it to a colleague or a client.
Improve playbooks from real work
Section titled “Improve playbooks from real work”After a run, ask the agent what it would change. When a session revealed a reusable correction, such as a code translation the target always needs, the agent proposes adding it.
Corrections that apply to one client stay in that project. Corrections that apply to the method go into the playbook.
The playbook editor has an agent sidebar. Ask it to tighten wording, add an approval step, or reconcile the playbook with a newer template.
Share playbooks with the team
Section titled “Share playbooks with the team”Playbooks are organization resources and follow the same access rules as tools and connections.
Give every consultant Viewer access to the firm’s playbooks, and Editor access to the people who own the methodology. See Role-based access control.