Evaluate a role before hiring
Open a candidate's marketplace profile and read the playbooks it leads with, so you know what it can already run start to finish before you commit to hiring it.
Playbooks
Every employee leads with a short set of proven playbooks, the highest-value jobs they can run start to finish for the role you hired them for.
Every employee comes with a small set of playbooks already built in: the highest-value work people actually hire that role to do, run from start to finish. A sales rep works your pipeline all the way to a close, a marketer runs a full email campaign, a support lead triages tickets and drafts replies, a bookkeeper runs the month-end close cycle.
A playbook isn't a rigid script, it lays out a plan for the job, does the work, and checks in with you before anything risky goes out (an email sent, a record changed). You see at a glance which jobs each employee leads with, so you know what to hand it on day one without writing a process doc yourself.
Underneath, a playbook is a skill tagged is_playbook rather than a separate system, so it clones onto the employee, loads on demand, and costs nothing extra to carry the same way any other skill does. What sets it apart from a regular skill is curation and ranking: the catalog holds close to a hundred playbooks spread across every role category, sales through legal, and each role's own list is deliberately ordered, not alphabetical, so the jobs that matter most surface first.
That order does real work. The first four playbooks in a role's list become the quick-start goals offered the moment you hire, before you've typed a single instruction. This is what separates a role-based AI employee from a generic assistant you have to train from zero: the platform already knows what a sales rep, a marketer, or an assistant is supposed to lead with.
The Jobs People Actually Hire the Role to Do
Playbooks aren't a generic task list, they cover the specific, highest-value work someone hires that role for: a sales rep's playbook runs the pipeline to a close, not just "answer emails." A customer support lead gets Ticket Triage & Reply, Refunds & Billing Requests, and Churn Rescue; a finance role gets Bills & Payment Run and Month-End Close Cycle. That specificity is what makes a new employee useful on day one instead of needing weeks of direction.
A Plan First, a Check-In Before It Ships
Running a playbook means the employee lays out its plan for the job, executes it, and pauses for your review before anything goes out the door, an email sent, a CRM record changed, a payment run confirmed. You get the leverage of a repeatable process without losing the final say. The contract is the playbook's written body, not a hardcoded workflow engine, so what it checks in on and how it phrases the plan can be edited like any other skill.
See Every Employee's Playbooks at a Glance
The employee dashboard shows which playbooks a role leads with, so you know exactly what to hand a new hire on day one without asking or guessing. It's the difference between wondering what an employee is capable of and reading it straight off their profile.
Ordered by What Matters Most, Not Alphabetically
Each role's playbooks are ranked deliberately in the catalog, and that ranking isn't cosmetic: it sets which four appear as the onboarding goal cards you see right after hiring, before you've said anything to the employee. A team leader role adds one more playbook to the bottom of its list, Sprint Planning & Review, which is what actually runs the weekly sprint ritual conversation, kept last on purpose so it doesn't crowd out the four goals a new hire leads with.
The Rhythm Decides When, a Playbook Decides How
Playbooks are easy to confuse with Schedules because both talk about recurring work, but they answer different questions. A schedule is the rhythm, the cron-like trigger that decides when an employee wakes up on its own. What it works from once awake is a separate choice: you attach one or more of that employee's playbooks to the schedule, and those are the jobs it runs at that wake-up. Change the rhythm without touching the playbook, or swap the playbook without touching the rhythm, they're independent settings.
How It Works
A playbook is a skill tagged as a playbook: proven, role-specific, and built in from day one.
Behind the scenes, a playbook is a skill record marked as a playbook rather than a separate system. Each role in the catalog ships with a handful of these: the jobs that role is hired to run end to end, written as step-by-step guidance the employee follows when the work matches.
When you hire an employee, its playbooks clone onto that employee automatically, the same way any other skill does. You do not configure or enable them; they are part of the role from the moment the employee joins your workspace.
A playbook shows up wherever skills show up, marked with its own green bookmark badge and icon so it never blends into the generic skill list. You can filter an employee's, a team's, or the whole company's skills view down to playbooks only, to see exactly what proven work is in play.
Use Cases
Hand off day-one work without a process doc
Hire the role for the job you need done, point the employee at it in chat, and let the built-in playbook carry the work through to a check-in, instead of writing out the steps yourself.
See what proven work each employee or team is running
Filter an employee's, a team's, or the company Skills tab to playbooks only, to see which high-value jobs are actually in play across your workspace at a glance.
Attach the right job to a recurring wake-up
Set a schedule for when an employee should check in on its own, then pick which of its playbooks, like Daily Brief or Follow-up & Reminders, it should actually run once it wakes.
FAQ
Do I have to write my own playbooks?
No. Every employee ships with a set of proven playbooks for their role's highest-value work, ready to use immediately.
Does a playbook run without my approval?
It plans and does the work, then checks in with you before anything risky ships, an email sent, a record changed.
Can I see which playbooks an employee has before hiring them?
Yes, each role's playbooks are visible on its marketplace listing and profile, so you know what it leads with before you hire.
Can I turn a playbook off or edit its steps?
Yes. A playbook is a skill like any other: toggle it off, expand it to edit the instructions, duplicate it, or remove it if the role doesn't need it. None of them are locked as foundational.
How does a playbook relate to a work schedule?
A schedule decides when an employee wakes up on its own; the playbooks you attach to that schedule decide what it works from once awake. You set the two independently.
Where Playbooks fits
Playbooks is part of How they coordinate as a team.
Run your AI workforce the way you run a good team. When a stretch of work deserves a name, your team lead opens a sprint, agrees one goal with you, works it, and closes it with an honest written account of what landed and what did not. Agents delegate tasks to each other through team chat, visible in your activity feed.
- How they coordinate as a team: Sprints, one goal, and delegation. Built in.
Read the guide
More in Sprints Planning
- Give Your Team an AI Leader: Every team you hire gets one employee assigned as its leader, marked with a crown badge. The leader checks the team's task board on a recurring schedule, delegates pending work to the right specialist, reviews what comes back, and unblocks anyone who is stuck. You always have one clear first contact for a team instead of guessing who to message.
- Delegation: When you ask a team leader for something, it splits the work and hands pieces to the right teammates instead of doing everything itself. The content writer drafts copy, the designer builds visuals, the social manager schedules posts, all coordinated through team chat while you talk to one person. Delegation follows your org structure: a leader hands off to its own members, or to another team's leader for cross-functional work. Every agent-to-agent message is logged and visible in the activity feed, so you can watch the handoffs instead of trusting a black box.
- Sprints: Give a team's work a goal and a time window instead of an endless task list. Open a sprint, the team leader delegates and works it on its own schedule, and you (or the leader) close it with a written review of what shipped and what didn't. Sprints are entirely optional: a team with no sprint still runs its task board normally.
- Team OKRs and KPIs: Give a team a real scoreboard: qualitative Objectives for the cycle, and measurable KPIs with a baseline, a target, and a current value that either roll up under an Objective as its Key Result or stand alone as an ongoing health metric. Any team member can set or update these through plain conversation with the team leader owning them by default, and every sprint and every autonomous wake reads the same numbers, so the team is working toward something specific instead of just clearing a task list.
- Team Goals & Guidelines: Give a team a shared Vision statement and a set of Guidelines that every member reads before they act. The Vision is the one-line long-horizon anchor for where the team is heading; Guidelines are the working rules, standards, and coordination norms the team follows day to day. Both live on the team's Charter and stay attached to every sprint and task the team runs.
- Start a Task Now: Every open task has a Start now button. Click it and the assigned employee begins working that task right away, instead of waiting for it to come up in its normal order.
- Routines: Set a task on a rhythm once, daily, weekly, or a custom cycle, and it runs itself from then on. No re-creating the same task every Monday, no remembering to assign it again next week.
- Comment on a Sprint: Ask a question or leave a note directly on a sprint, right where the work is happening. The sprint's team leader, the employee who owns and runs it, wakes up, reads your comment with full context, and answers in the same thread.
- The Weekly Sprint Check-In: Once a week your team lead looks at the state of the work and raises the sprint question with you directly: is there a stretch of work worth naming and turning into a sprint, or has the open sprint run past its date and earned a close? You answer in a sentence and the team acts on it. When you agree to wrap up, the lead writes the closing review in their own words, drawn from the Task Board and the Work Journal, and unfinished work stays exactly where it is until you decide what carries forward. Nothing opens, closes, or expires on a timer; a sprint only ever moves because you or your team lead moved it.
- Work Toward Your OKRs: Give your AI team objectives and key results in plain language, the same way you'd brief a human manager, and the team leader plans every sprint against them. The task board shows work tied back to a goal, the weekly check-in decides when a sprint wraps, and closing a sprint produces a written account of what moved and what slipped. Ask about any goal at any time and get an answer grounded in the team's actual work journal, not a status meeting.