Campaign work alternates between producing something new and deciding what to change. The connection between those jobs matters: a creative brief should reflect the audience evidence, and the next test should reflect what the previous one taught you. Otherwise more output just gives you more assets to explain.
The library covers ICP definition, ad concepts, copy variations, content reuse, reporting, and ad-account automation. Start with a brief and a reviewable deliverable. Move toward connected workflows when you have a clear reporting definition, a decision rule, and someone responsible for approving changes to spend.
From an audience to a campaign test
Define the audience
Write the buying situation, relevant pains, exclusions, and evidence. Use actual customer information you are permitted to share.
Open the ICP prompt →Draft different angles
Supply the offer and approved proof. Ask for variations that test different reasons to respond, then edit the selected copy.
Open the ad-copy prompt →Develop the creative concept
Turn the chosen angle into a concept with a clear message and intended audience. Follow the playbook's tools and review the final asset before publishing.
Open the creative workflow →
Connect the brief, the test, and the decision
Write the audience, offer, desired response, and evidence into the brief. Include examples of past creative with enough context to explain why they matter. Ask for distinct angles tied to distinct hypotheses, then choose the ones worth testing. Ten headlines that make the same promise are one idea wearing ten shirts.
When reviewing performance, define the reporting period and the denominator before drawing a conclusion. Compare equivalent audiences and conversion events. A campaign with cheaper leads may still produce fewer qualified opportunities; keep the metric tied to the decision you need to make.
Translate the analysis into a proposed action with a reason, an owner, and a condition for revisiting it. That might be a new creative test, a landing-page change, or a budget adjustment. Keep the source figures beside the recommendation so another person can check it.
Keep creative review and budget approval separate
Review creative for claims, customer fit, and brand voice before it reaches an ad account. Check that any statistic or customer quote came from approved material. A persuasive line can still be unsupported, and a model will not know which promise your sales team can fulfill.
Treat spend-changing actions as a separate workflow with explicit permissions. The ad-automation playbooks describe their APIs, setup, and approval steps. A useful analysis does not by itself justify a live change to bids, budgets, or targeting.
Keep a test log that records the hypothesis, the change, the measurement window, and the result. Review that log when writing the next brief. The useful repetition is learning from the last test, not generating another batch because the tool makes it easy.
Use cases for Demand Generation
Complete workflows with their implementation tools listed below. Follow each playbook's setup and review steps.
The Ideal Customer Profile (ICP) Template, AI-Scored in Clay
Turn an ideal customer profile template into a live scoring rubric: pull a target account list, enrich it with the signals an AI can read, then score every account against your ICP with a reason and a risk you can audit.
Tools: Clay, Apollo.io, Claude, HubSpotHow to Identify Website Visitors and Trigger Same-Day Outreach
Identify the anonymous website visitors on your site, filter to ICP fits, and trigger a personalized touch the same day, while the intent is still warm.
Tools: RB2B, Clay, Slack, SmartleadCold Email Personalization at Scale, From Real Research
Cold email personalization at volume: research each prospect automatically and generate one genuinely personalized email per person, then send at scale without sounding like a mail merge.
Tools: Clay, Apollo.io, Claude, SmartleadGenerate LinkedIn Ad Angles, Hooks, and Creative Concepts
Turn your positioning and real customer language into a slate of genuinely distinct LinkedIn ad angles, hooks, and creative concepts ready to test.
Tools: Claude, Claude web search, Google SheetsVideo Prospecting at Scale Without Capping at 20 a Day
Scale video prospecting past the 20-a-day ceiling: record one base video and have AI personalize the opening and on-screen details per prospect, so each recipient gets a video that feels made for them.
Tools: Sendspark, HeyGen, Clay, SmartleadWeekly Competitor Intel Digest, Run by a Claude Routine
You know the competitive-intel chore: someone is supposed to track what competitors shipped this week, and that someone is slammed. This hands the whole job to a Claude Routine that researches with web search, keeps only the moves that change a deal, and drops a cited digest in Slack every week. Nobody owns the chore, and there is no glue to keep alive.
Tools: Claude web search, Claude Routines, Slack (via MCP)Turn One Webinar Into 15+ Content Assets
Turn a single webinar transcript into 15+ ready-to-edit assets: a blog post, social posts, emails, clip scripts, and a FAQ, from one reviewed outline.
Tools: Fathom, Claude, Google DriveLead Enrichment and Routing with a Claude Agent
Lead enrichment is the other half of speed-to-lead, and most teams lose it in a queue. Fire every form fill into a Claude agent that enriches the lead with web research, scores it against your ICP, writes the record to HubSpot over MCP, and pings the right rep in Slack, in seconds. No n8n workflow, no Zapier, no human triaging a queue.
Tools: Claude web research, Claude Code, HubSpot (via MCP), Slack (via MCP)Automate Google Ads Management with AI
Most Google Ads accounts run on a human exporting a report, then clicking. Wire yours to a Claude agent instead: it reads the account through the Google Ads API, writes its own weekly diagnosis, mines the search-terms report for wasted spend, and executes only the changes you approve by ticking a checkbox, negatives, bids, budgets, and pauses, the same week, not next month.
Tools: Google Ads API (GAQL), Google Analytics 4, Claude Code, Claude Code Routines, Google Ads (mutate API)Automate LinkedIn Ads Management with AI
Most LinkedIn ad accounts run on a human reading a dashboard, then clicking. Wire yours to a Claude agent on a weekly routine instead: every Monday it ranks the changes worth making, and executes the ones you approve, bids, budgets, pauses, launches, and audience edits, the same day you approve them, not days later.
Tools: LinkedIn Marketing API, Claude Code, Claude Code Routines, LinkedIn Campaign ManagerThe RevOps Dashboard That Reconciles: A Claude Agent Builds One Number Set from CRM, Ads, Product, and Billing
Every team has three tools that each report 'pipeline' and none of them agree, so the revops dashboard becomes a weekly argument about whose number is right. This play makes the definitions the product: a metric definitions file names one formula, one source of truth, and one owner per metric, and a Claude agent reads the CRM, ad platforms, product usage, and billing over MCP every Monday, computes each metric exactly as written, shows the delta between what each tool claims and what the definition says, and writes one static page plus a Slack diff. No BI license, no dashboard nobody opens. One number set, with the disagreements on the page instead of in the meeting.
Tools: HubSpot or Salesforce (via MCP), LinkedIn and Google Ads exports, Product usage and billing (Stripe via MCP, or a warehouse), metrics.md (the definitions file), Claude Code, A static HTML page + Slack (via MCP)AI Video Ads from One Point of View: A Claude Code Pipeline That Cuts Ten Variants a Week
Most B2B video ads die in the queue: one script, one edit, three weeks, one variant that nobody wanted to test because it cost too much to make. This play turns AI video ads into a pipeline instead. Claude writes a hook matrix from your point of view and your customers' own words, scripts each hook at 6, 15, and 30 seconds with a caption track, and renders the cuts from HTML scenes you own, so ten named variants ship into a test on Monday and the losers cost nothing to kill.
Tools: Your point of view and customer language, Claude Code, Hyperframes, HeyGen or Tavus (optional), LinkedIn Campaign Manager or Meta Ads Manager, The ads skillsPut Recurring GTM Work on Autopilot with Claude Routines
Every GTM team has a list of recurring chores that quietly slip: the Monday pipeline-risk read, the competitor check, the CRM-hygiene sweep. A Claude Routine runs each one on a schedule as a cloud agent, so the work shows up whether or not anyone remembered it.
Tools: Claude web search / MCP, Claude Routines, Slack / your CRMAI Lead Scoring: Score Your Whole Database with a Claude Agent
Most lead scores are a points system someone built in 2021 and nobody trusts, so reps triage the queue by gut anyway. This play replaces it with a Claude agent that scores every lead in your CRM against a three-part model, fit, intent, and engagement, writes the score and a one-line reason back over MCP, re-scores nightly on a Routine, and routes by rule. The reason line is what makes reps stop ignoring the number.
Tools: HubSpot (via MCP), Claude Code, Claude Routines, Slack (via MCP)Skills for Demand Generation
Reusable procedures for the tool or runtime named on each card. Check the setup before adding one to your workflow.
B2B Cold Email Templates in Your Brand Voice
Writes short, relevance-first B2B cold emails in your voice and gives you the cold email templates to start from. Opens with a real observation, not a generic compliment, and refuses to invent personalization.
LinkedIn Ads Optimization Skill for Claude
Reads a LinkedIn ad account by layer and format, flags what moved week over week, and returns a ranked, evidence-backed list of changes to approve. It classifies before it counts and proposes, never executes.
Google Ads Optimization Skill for Claude
Reads a Google Ads account through the API, writes a dated diagnosis, mines the search-terms report for negatives, and returns a ranked, evidence-backed list of typed changes to approve. It categorizes before it counts and proposes, never executes.
ICP Framework Builder: Turn Your Wins and Losses Into a Scoring Rubric
Feeds Claude what you sell plus a dozen recent won and lost deals and gets back an ICP framework a new hire could apply without judgment: measurable disqualifiers, weighted attributes that sum to 100, tier cut-offs, and a back-test against the deals you gave it.
Prompts for Demand Generation
Individual tasks with required inputs and example outputs. Each prompt lists the assistants it supports.
Define Your ICP and Buyer Personas
Distill real win/loss evidence into an ICP, a buying-committee map, and a scoring model your whole team can act on, built on disqualifiers, not aspiration.
Works with: Claude, ChatGPT, GeminiWrite a Cold Email That Earns a Reply
Produce a tight, relevance-first cold email with one clear ask, built around the prospect's trigger not your pitch, sub-90 words, no fluff, no fabrication.
Works with: Claude, ChatGPT, GeminiCold Email Sequence Template (Multi-Touch)
A cold email sequence template as a prompt: generate a value-led, multi-touch cadence where each touch adds a new angle, not a nag, with personalization tags and a test plan baked in.
Works with: Claude, ChatGPT, GeminiGenerate Ad Copy Variations for a Campaign
Produce genuinely distinct ad variations across testable angles, on-brand and within character limits, plus a test plan and visual ideas for the top angles.
Works with: Claude, ChatGPT, GeminiAI Content Repurposing: One Transcript Into a Content Engine
AI content repurposing that turns one transcript into a blog post, social posts, an email, pull-quotes, and clip ideas, keeping the original point of view and grounded in the source.
Works with: Claude, ChatGPT, GeminiGuides for your chosen assistant
Follow the guide for the tool you use. A shared workflow directory does not change the setup requirements of an individual playbook.
Claude
- Prompting Claude: what actually moves the needle →The things that reliably improve Claude's output are mostly structural: paste the real source material instead of describing it, state the goal, audience, constraints, and exact output format, show an example of the shape you want, and put long context first with the instruction last.
- Claude Artifacts: interactive outputs you can ship →A Claude Artifact is a standalone output, a document, a chunk of code, an interactive page, a diagram, that Claude renders in a panel beside the chat instead of burying it in the conversation.
- Web search in Claude: answers beyond the cutoff →Web search lets Claude pull current information from the live web and cite the sources it used, instead of relying only on what it learned in training.
- The Claude API: a quickstart →The Claude API lets your own software call Claude, instead of you typing in the app.
- Claude vs Gemini for GTM: home-field advantage vs the away game →If your GTM runs inside Google Workspace, Gmail, Sheets, Docs, Meet, Gemini has a real home-field advantage: it is already in the side panel of every app you open, on the Google AI Pro plan.
- How to measure the ROI of Claude in GTM (a model you can defend) →To measure AI ROI in a GTM org, keep three separate ledgers instead of one blended number: a time ledger (minutes per play before and after, timed on real instances), an output ledger (more of the work that touches pipeline, like accounts researched and same-day follow-ups), and a pipeline ledger (meetings, conversion, and cycle time for a pilot cohort against a holdout).
ChatGPT & Codex
- ChatGPT file uploads and data analysis: check the spreadsheet →Give ChatGPT the source file, metric definitions, desired output and validation checks.
- ChatGPT search and deep research: from sources to a decision →Use search for focused current questions and deep research for an investigation across sources.
- ChatGPT Projects: keep the right context around the work →A ChatGPT Project keeps related chats, files, instructions and sources together.
- Writing with ChatGPT: drafts, documents and focused revisions →Use Chat for a short drafting conversation and Work when you need a finished document, presentation or PDF.
Frequently asked questions
What is a useful first demand-gen task?
An audience brief and a set of ad-copy variations. The inputs are concrete, and you can review the output before anything reaches an audience or changes spend.
Can these workflows manage ad accounts?
Some published playbooks include ad-platform APIs and approved changes. Check their required tools and permissions. Start with analysis and proposed actions before allowing a workflow to change a live account.
How do I get useful creative variation?
Ask for different hypotheses, not just different wording. Supply the audience, the offer, approved evidence, and what the previous test taught you. Keep the selected idea specific enough to measure.
Where do ChatGPT and Codex fit?
The supporting guides cover ChatGPT research, writing, and data analysis, plus Codex project work where relevant. Full automation playbooks remain labeled with their own tool stacks; shared placement does not make every implementation interchangeable.