More Marketing Against The Grain episodes

From AI Babysitter to AI Leader thumbnail

From AI Babysitter to AI Leader

Published 10 Nov 2026

Duration: 00:36:57

Define AI playbooks with triggers, inputs, steps, and outputs to automate work reliably without constant supervision.

Episode Description

Free Guide: Build your First Skill File in 30 minutes https://clickhubspot.com/liyf Ep. 468 What if you could triple your team's productivity just by...

Overview

Rachel Woods from AMP explains a framework for building AI playbooks - structured, step-by-step processes that allow AI to perform work reliably without constant human supervision. Each playbook is defined by four components: a trigger that initiates the work, inputs the AI needs before starting, specific steps to follow, and a defined output or deliverable. She demonstrates this with a project planning playbook that, in her company's use, has "tripled the velocity of my team and how we plan and execute projects."

Woods introduces "playbook stacking," where one playbook triggers or collaborates with others to form larger systems. She illustrates this with a sales enablement example: a playbook that answers team questions from a knowledge base in Slack, escalates unknowns to a manager with a proposed answer, and then updates the guide once the manager approves. She also emphasizes "own the playbook, rent the tech," recommending teams store playbooks in GitHub or similar tools rather than locking them inside a single AI platform.

Woods frames a progression from casual AI user to "AI operator" - someone who architects and owns the systems. She advises starting with small, low-stakes playbooks (meeting recaps, weekly reports) before scaling, and notes that the goal is to move from babysitting AI to trusting it to run in the background.

What If

  • What if you playbooked your project planning so AI drafts the full timeline and task list while you sleep?

    • Move: Define a trigger (e.g., a new project pitch document), inputs (scope, constraints, deadline), steps (one-three-one brainstorm, timeline build, task assignment), and output (a project-management-tool entry). Store the playbook in GitHub, not inside the AI chat.
    • Why Now? Woods reports her playbook has "tripled the velocity of my team and how we plan and execute projects." As a solo operator, the same structure lets you offload the repetitive planning layer without hiring.
    • Expected Upside (proposal): You could recover the hours currently spent breaking projects into tasks and instead focus on execution and client work, with AI flagging sub-tasks it can already start on because it holds the full context.
  • What if you built a self-updating knowledge base so product questions get answered in minutes instead of days?

    • Move: Create a question-answering playbook that pulls from your docs, answers in a channel (Slack, email), and - when it does not know - escalates with a proposed answer rather than guessing. Add a second playbook that updates the source doc once you approve the correction.
    • Why Now? Woods' team reduced a response that took "probably 10, 15 minutes, maybe" plus waiting for someone to be available to "a minute," and eliminated the "organizational debt" of stale FAQs. For a solo developer, this means prospects and users get accurate answers after hours without you being on call.
    • Expected Upside (possibility): You could cut support-response latency dramatically and keep documentation current automatically, freeing time for feature development.
  • What if you stacked a morning-routine playbook with a weekly-reporting playbook so your operational overhead runs itself?

    • Move: Build a small "todaying" playbook (Woods uses that keyword to kick off her morning routine) that pulls from other playbooks, and a separate weekly-report playbook that compiles metrics and drafts the manager update. Store both in a file system you control.
    • Why Now? Woods recommends starting with "small little things" like meeting recaps and Friday updates before tackling complex systems, and advises figuring out "how you can save a couple hours in your week to week." For a solo operator, automating these two bookends of the workday removes the highest-friction daily and weekly tasks.
    • Expected Upside (proposal): You could reclaim the time currently spent assembling status updates and morning planning, redirecting it to revenue-generating work.

Takeaway

  • Write your first playbook using the four-part template - trigger, inputs, steps, outputs - for the single most repetitive task in your week (e.g., drafting a weekly status report). Keep the steps explicit: "the more specific, the better".

  • Store every playbook as a plain-text file in GitHub or a shared drive, not inside the AI chat interface. This implements "own the playbook, rent the tech" and lets you migrate tools without losing your systems.

  • Embed a "one three one" step in any planning or ideation playbook so the AI identifies the core problem, generates three approaches, then recommends one. This prevents the AI from defaulting to its first, often shallow, idea.

  • Add an explicit escalation branch to every playbook: when the AI does not know the answer, it must propose one and tag you for approval rather than fabricating a response. Pair it with a second playbook that updates your source document once you approve.

  • Start with two small, low-stakes playbooks (a morning-routine trigger and a meeting-recap summarizer) before attempting complex multi-playbook stacks. Woods advises beginning with "small little things" so the habit and reliability build before you scale.

Recent Episodes of Marketing Against The Grain

17 Nov 2026 I Fully Automated my Video Editing With Claude & Cursor

AI models like Opus 5.5 now enable marketers to automate video editing and animation, allowing rapid production of high-quality short-form content through iterative skill refinement and local tool integration.

More Marketing Against The Grain episodes