Playbooks & agent-assist

“Playbook” means two different things in Zubby, and it is worth getting the distinction straight up front:

• Outbound Playbooks (Dashboard → Playbooks) - a library of pre-built automations you install in one click. Each one becomes a real, editable journey that runs on a trigger (cart abandoned, back in stock, post-purchase…).
• Agent Playbooks (Playbooks → Agent) - step-by-step procedures the live chat agent follows inside a conversation when a trigger matches. This is the in-chat counterpart to the outbound library, and the foundation of agent-assist.

Outbound Playbooks (the automations library)

The Playbooks tab is a catalog of curated recovery and retention automations - fourteen templates across four categories. Each card shows the trigger, the full channel sequence with delays, the category, and an illustrative impact estimate. A search box and category filter pills (each pill shows its template count) sit above the grid; search matches titles, descriptions, triggers, and channels, so typing whatsapp instantly narrows to the WhatsApp-first flows.

Recovery

• Cart Rescue · 3-touch recovery - email now, SMS at 6h (only with SMS consent), final email with an optional approved discount at 24h.
• Checkout Rescue · payment-step dropoff - two fast, low-friction emails for shoppers who reached checkout but never paid - the warmest leads in the funnel.
• Cart Rescue · WhatsApp-first - a short, personal WhatsApp nudge 30 minutes after abandonment (requires a connected WhatsApp sender and opt-in), with an email fallback at 18 hours.

Growth

• Browse Abandonment · high-intent viewers - two gentle touches for shoppers who viewed a product repeatedly but never added to cart.
• Price Drop · wishlist & viewers - instant web push plus a price-comparison email the moment a watched product gets cheaper.
• Back in Stock · instant push - web push the second inventory returns, with an email chaser 30 minutes later - push beats email to the phone on fast-selling restocks.

Retention

• Win-back · 30-day dormant - re-engages shoppers with no activity in 30+ days.
• Win-back · 60-day WhatsApp - a personal WhatsApp check-in for long-dormant, opted-in shoppers, with an email fallback three days later.
• Back in Stock · subscriber blast - emails every subscriber the moment inventory flips from zero to positive.
• Replenishment · reorder reminder - nudges consumable buyers to reorder right before their predicted run-out date, based on purchase cadence.
• VIP Thank-You · big spenders - a white-glove, no-discount thank-you for orders above a configurable value floor (default 200).
• Birthday Reward - a warm greeting and a small gift code on the shopper's actual birthday.

Onboarding

• Welcome Series · first-time shoppers - a warm intro, a concierge/quiz nudge, and a social-proof email over five days.
• Post-Purchase Thank-You - a single human thank-you and review request after fulfilment.

Preview the copy before you install

Every card has a Preview message copy expander that reveals the complete subject line and body of every step - including the {{variables}} that are filled per shopper at send time - to help you review its intended message before installation. The installed journey can generate fresh copy from its instructions, so a template preview does not lock every sent sentence. Review the saved step instructions and a controlled received message before wider use.

Installing a playbook

Click Install playbook and Zubby creates a real journey plus its steps from the template, then drops you into the journey editor to tune it. Installed playbooks run exactly like hand-built journeys - they are not a separate system. Afterward the card shows an Installed badge with the journey's status, live performance tiles - Enrolled, Sent, and Converted, straight from the journey's enrollments and executions - and an Open & edit button that jumps to the journey. That means the catalog doubles as a scoreboard: you can see which installed playbooks are earning their keep without leaving the page.

Build a custom playbook

Don't see what you need? The Build a custom playbook form at the top of the tab creates an editable draft journey from a name, a trigger, a first channel, and an optional opening message. The trigger list follows all seventeen journey triggers, including delivery, first purchase, review, and loyalty events. See thetrigger and channel guidefor their data prerequisites. A trigger in the list does not mean your platform produces its event. The first channel can be email, SMS, web push, or WhatsApp. Save creates the draft and opens it on the Automations tab, where you add more steps with the normal editor.

Agent Playbooks (live-chat procedures)

The Playbooks → Agent tab is where you author the procedures the AI follows mid-conversation. A classic example: “When a shopper asks about returns - confirm the order number, state the policy from a Locked Fact, then offer to start the return.” A matched playbook is injected into the conversation as an ordered procedure the agent must work through.

Anatomy of an agent playbook

• Name - for your reference (e.g. “Returns help”).
• Trigger type - one of:
  • Always on - runs on every conversation.
  • Keyword match - fires when the message contains any of your comma-separated keywords (e.g. return, refund, exchange).
  • Page type - fires on a specific widget page: product, collection, cart, checkout, order status, post-purchase, account, or home.
• Priority - 0–100; higher wins when several playbooks could match.
• Steps - the ordered procedure (up to 15 steps, 400 characters each). Steps reference tools by intent, e.g. “Confirm the shopper's order number with get_order_status.”
• Active - inactive playbooks are saved but never matched.

Pair playbooks with Locked Facts

Playbook steps tell the agent what to do; they are not the place for exact policy wording. When a step needs precise language (a refund window, a warranty term), point it at a Locked Fact so the agent quotes the approved text rather than improvising. See Training for how facts are managed. Each step is sanitized before it is injected, so playbooks cannot be used to smuggle prompt instructions.

Agent-assist for human reps

When a conversation is handed off to a person, the AI stays on as a co-pilot in the inbox. Reps get:

• Suggest reply - a context-aware draft built from the transcript, shopper profile, and your knowledge base, ready to edit and send.
• Canned replies - insert a saved snippet with a keyboard shortcut.
• Sensitive-language flags - the AI warns before you send a risky commitment (for example promising a refund) so wording stays safe.

Full detail on the rep experience lives in the human handoff and inbox guides.

Product-finder quizzes

Quizzes are guided-selling flows a shopper can take outside the chat, included from the Growth plan up. Open Quizzes in the sidebar, generate a draft from your catalog in one click or create one by hand, then review every question: each answer maps to catalog filters, so the result page shows matching products.

1. Generate or create a quiz and edit the title, questions, and answers.
2. Check each answer’s filter mapping against your catalog.
3. Publish, then share or embed the quiz link on your storefront.
4. Take the published quiz in a fresh browser session and confirm the product grid, the recorded completion, and the quiz answer on the shopper’s profile.

Answers are saved as shopper preferences you can target in segments and journeys, and orders from quiz takers are tracked for attribution.

Outbound vs. agent playbooks at a glance

Related

• Human handoff & agent-assist
• How the AI agent works
• Journeys - what installed playbooks become
• Rules engine - for merchandising and objection controls
• Training & Locked Facts