164 posts tagged with "Playbook"

Using Claude only as a question-and-answer chatbot is like buying a powerful computer and using it only as a calculator. The real value appears when you organise Claude around your actual workflow — and give each part of that workflow a proper home instead of one giant prompt.

Context is the scarce resource in every coding agent session. Instructions, file reads, tool schemas, MCP servers, and your chat history all compete for the same window — and quality degrades before the hard limit. Part II covers how Cursor and Claude Code expect you to structure rules, skills, and session hygiene.

One disciplined agent is leverage. Ten undisciplined agents are a tax. Part IV covers parallel execution, cloud delegation, independent review, and the failure patterns that turn agentic coding into expensive thrash.

Ask-and-pray prompts turn frontier models into expensive autocomplete. The teams that ship consistently do the opposite: they force research and a reviewable plan before any file write. This article is Part I of a four-part series on working with coding agents in production.

Without a check the agent can run, “looks done” is the only stop signal — and you become the verification loop. Part III covers how Cursor and Claude Code turn tests, builds, screenshots, and hooks into an oracle that stays honest even when context degrades.

Leads are not the goal. Engaged leads—people who raise their hand because something valuable made your offer relevant—are the goal. $100M Leads is Hormozi’s operating manual for advertising without mystique: there are only four core ways to let anyone know about anything, then four ways to get other people to do it for you. Master the Core Four at enough skill and volume, and lead scarcity becomes a choice, not a sentence.

Most acquisition problems are misdiagnosed as “marketing” or “sales” problems. Hormozi’s blunt thesis in $100M Offers: if strangers do not feel stupid saying no, your offer is weak—and no amount of clever ads, CRM sequences or closing scripts will save a commodity package. The book is Volume I of an acquisition stack: before leads and money models, engineer an offer so differentiated that price comparison becomes irrational.

Most sales advice is folklore: hire “hunters,” run motivational Monday, blame marketing for lead quality. Mark Roberge—MIT-trained engineer turned HubSpot’s first head of sales—built a formulaic, inspectable system that helped take HubSpot from early startup to roughly $100M: hire with a scorecard, train to a methodology, coach from metrics, generate demand inbound, align sales and marketing with SLAs, and run experiments like an engineering org. The Sales Acceleration Formula is the field manual for that machine.

Most “hard talks” fail because people argue inside the wrong conversation. Stone, Patton and Heen’s Difficult Conversations (third edition) shows that every tough exchange is actually three conversations at once: What Happened?, Feelings, and Identity. Shift from a battle stance to a learning stance, begin from the third story, and jointly map contribution—not blame. This guide walks the full book structure for practitioners in consulting, leadership and complex delivery.

Like it or not, you are a negotiator. You discuss fees with procurement, align sponsors on AI programme scope, settle vendor SLAs, and navigate internal priority fights that look like zero-sum battles but rarely are. Most people default to positional bargaining: take a stance, defend it, concede in small steps, split the difference. Fisher, Ury and Patton’s Getting to Yes—developed at the Harvard Negotiation Project and refined across decades of diplomacy, law, labour and business—offers a third path: principled negotiation. Decide issues on their merits, not through a contest of wills. Be soft on people, hard on the problem. Focus on interests, invent options, insist on objective criteria, and protect yourself with a real BATNA.