“Investors have only two emotions: fear and greed. Complexity triggers fear. Simplicity, clarity, and confidence trigger greed. Most decks are fear machines”.

Khosla Ventures is one of the few funds that has written down exactly how it wants to be pitched. The material lives in four documents: Vinod Khosla’s ACS framework, Zack Schildhorn’s pitch framing guide (Advisor at Khosla Ventures), KV’s official five-question pitch essay and the internal deck “Pitch the way VCs think”.

I extracted every rule from all four and condensed them into a single markdown file. Drop it into a Claude Project and Claude becomes your pitch agent: it interviews you, writes the twenty headlines that carry your narrative, builds the deck inside KV constraints, reviews your existing deck with the same rubric a partner would use and stress-tests you with hostile questions before a real partner does.

Inside you will find:

1. How to Present to Investors (The ACS Framework)

2. How to Frame a Pitch That Actually Lands (The Six Ps)

3. How to Solve the Pitch Problem (The 5 Questions Khosla Wants Answered)

4. Pitch the Way VCs Think (Fear, Greed and the 5-Second Rule)

5. The Pitch Agent File: Every Rule in One Markdown

6. How to Run the Agent: From Blank Page to Investor-Ready Deck

This issue is available exclusively to paid subscribers!

Paid subscribers unlock the full library: 200+ decks, 10,000+ investors, AI Agent playbooks, and fresh high-signal content every week.

Here’s a good place to start:

🤖 AI Agent Templates
↳ The McKinsey Slide Playbook for Claude — how to build consulting-grade presentations in minutes.

📈 Startup Playbooks
↳ The AI Founders Playbook — lessons from Sequoia, OpenAI, Nvidia, and LangChain on building AI startups from zero.

🎯 The Deck Library
↳ 27 Most Promising AI Startup Pitch Decks Backed by Top Investors — the best-funded AI startups of 2025, slide by slide.

💰 Investor Database & Tools
↳ The Family Office List — 1,000 family offices actively writing cheques. Used by 5,000+ founders raising their round.

Not subscribed yet? Try it free for 7 days and unlock this guide, plus our full premium library:

Get 7-Day Free Trial

We’re already 70,000+ founders and operators inside!

Let’s begin!

Read more

For twenty years the only answer was to hire. But Claude Fable 5 is back and changed the math!

You can now build the team without hiring it. Not a folder of chatbots you paste prompts into, but a back office with named roles, its own memory, access to the tools you already use. Boom, you have fifteen people who never sleep, never drop a thread and never send anything without your sign-off.

Inside you will find:

1. The Setup

2. Customer & Support: Triage Tickets and Turn Them Into Insight

3. People & HR: Hire and Onboard Without the Busywork

4. Operations: Never Lose a Decision or a Doc Again

5. Marketing: A Content and Distribution Engine That Runs Itself

6. Sales & Revenue: Catch Buying Intent and Never Drop a Thread

7. Finance & Legal: Books, Runway and Contracts Under Control

This issue is available exclusively to paid subscribers!

Paid subscribers unlock the full library: 200+ decks, 10,000+ investors, AI Agent playbooks, and fresh high-signal content every week.

Here’s a good place to start:

🤖 AI Agent Templates
↳ The McKinsey Slide Playbook for Claude — how to build consulting-grade presentations in minutes.

📈 Startup Playbooks
↳ The AI Founders Playbook — lessons from Sequoia, OpenAI, Nvidia, and LangChain on building AI startups from zero.

🎯 The Deck Library
↳ 27 Most Promising AI Startup Pitch Decks Backed by Top Investors — the best-funded AI startups of 2025, slide by slide.

💰 Investor Database & Tools
↳ The Family Office List — 1,000 family offices actively writing cheques. Used by 5,000+ founders raising their round.

Not subscribed yet? Try it free for 7 days and unlock this guide, plus our full premium library:

Get 7-Day Free Trial

We’re already 70,000+ founders and operators inside!

Let’s begin!

Read more

Loops are the new thing.

A loop is a system, not a message. You give it a task and a written definition of what “good” looks like, it produces an attempt, checks that attempt against the definition, and if it falls short, it revises itself and checks again on its own, before any of it reaches you.

Most founders are one step behind this without realizing it. They open Claude, retype some version of the request they made last week, get a decent single answer and call it progress.

That’s a longer conversation, not a loop, and it costs you the same afternoon every single week.

Inside you will find:

1. What Makes a Loop Actually Work: The Loop.md Framework

2. 10 Loops Every Founder Should Be Running

3. How to Actually Turn a Loop On

4. How to Build a Loop of Your Own

Attio is the AI CRM that compounds revenue around the clock.

It gives your team the foundation for moving fast, staying sharp, and scaling without breaking. Every customer signal, from emails and meetings to product usage, billing, support, and agent activity, is synced from day one, giving you a live picture of every account.

With Attio, you’ll get:

• Revenue agents, workflows, and automations across every stage of your motion

• Instant answers to anything you Ask Attio about your business

• Access to your customer data wherever you work, through Attio’s MCP, API, and App SDK

30,000+ teams use Attio to drive more revenue at scale. Are you one of them?

Try Attio Now!

Want more? Paid subscribers unlock the full library: 200+ decks, 10,000+ investors, AI Agent playbooks, and fresh high-signal content every week.

Here’s a good place to start:

🤖 AI Agent Templates
↳ The McKinsey Slide Playbook for Claude — how to build consulting-grade presentations in minutes.

📈 Startup Playbooks
↳ The AI Founders Playbook — lessons from Sequoia, OpenAI, Nvidia, and LangChain on building AI startups from zero.

🎯 The Deck Library
↳ 27 Most Promising AI Startup Pitch Decks Backed by Top Investors — the best-funded AI startups of 2025, slide by slide.

💰 Investor Database & Tools
↳ The Family Office List — 1,000 family offices actively writing cheques. Used by 5,000+ founders raising their round.

Get 7-Day Free Trial

Read more

Claude Tag is the latest release of Anthropic. It works like this: someone types @Claude into a Slack channel, hands it a task and goes back to work (Slack is where it starts. Anthropic has made it clear that this shared-coworker model is coming to the other places teams work, too).

Claude breaks the request into stages, works through them with the tools it has access to, posts a running checklist in the thread and drops the result back for the whole channel to see. You tag a coworker and a coworker delivers.

That coworker is Claude Tag. It puts Claude inside Slack as a member of the channel rather than a chatbot you visit in a separate tab. One Claude per channel, shared by everyone in it, that remembers what the channel is working on. It will write or merge pull requests, run data analysis, draft the investor update, or help resolve an incident. And if you let it, it speaks up on its own.

Until now, working with Claude meant a private window: one person, one chat, one task, every session from a blank slate. Claude Tag turns that into a teammate the whole team shares.

Inside you will find:

1. What Actually Changes When @Claude Has Its Own Identity

2. The One-Time Setup: Four Steps to Put @Claude in Your Workspace

3. How to Scope What @Claude Can Do

4. The Founder Use Cases: What to Actually Tag @Claude Into

5. How to Switch On Ambient Mode Without Turning It Into Noise

6. How to Migrate Off the Old Claude in Slack Before It’s Switched Off

Want more? Paid subscribers unlock the full library: 200+ decks, 10,000+ investors, AI Agent playbooks, and fresh high-signal content every week.

Here’s a good place to start:

🤖 AI Agent Templates
↳ The McKinsey Slide Playbook for Claude — how to build consulting-grade presentations in minutes.

📈 Startup Playbooks
↳ The AI Founders Playbook — lessons from Sequoia, OpenAI, Nvidia, and LangChain on building AI startups from zero.

🎯 The Deck Library
↳ 27 Most Promising AI Startup Pitch Decks Backed by Top Investors — the best-funded AI startups of 2025, slide by slide.

💰 Investor Database & Tools
↳ The Family Office List — 1,000 family offices actively writing cheques. Used by 5,000+ founders raising their round.

Get 7-Day Free Trial

Read more

You’re doing your content backwards.

Open Claude. Type a prompt. Get something passable. Post it.

The result looks like this:

I’m sorry if your content sounds like this, but its pure AI slop…

After a few months you will have posts that could belong to any company in their category. The problem isn’t Claude. It’s that there’s nothing upstream of it telling it who you are, who you’re talking to, or why anyone should care.

That upstream layer is brand strategy: your ICP, your positioning, your voice, your message hierarchy. Without it you’re not building a brand.

This guide builds both.

First, a complete brand strategy session inside Claude, one sitting, four outputs, done. Then it wires those outputs into a content machine so everything you publish compounds instead of starting from zero every Monday.

Inside you’ll find:

1. Why your content sounds like everyone else’s AI slop (and how to fix it today)

2. Build your brand strategy with Claude: the 5-layer system

3. The Claude Project that holds it all together

4. Wire your brand into the content machine

5. The 6 agents that run the whole thing

Attio is the AI CRM that compounds revenue around the clock.

It gives your team the foundation for moving fast, staying sharp, and scaling without breaking. Every customer signal, from emails and meetings to product usage, billing, support, and agent activity, is synced from day one, giving you a live picture of every account.

With Attio, you’ll get:

• Revenue agents, workflows, and automations across every stage of your motion

• Instant answers to anything you Ask Attio about your business

• Access to your customer data wherever you work, through Attio’s MCP, API, and App SDK

30,000+ teams use Attio to drive more revenue at scale. Are you one of them?

Try Attio Now!

👋 Just a quick note before you continue!

Building great AI systems and agents is quickly becoming one of the most important advantages a startup can have. So we’ve been building non-stop and this will become a much bigger part of PMF going forward.

From now on, as a premium subscriber, you’ll get access not just to the best resources on fundraising and growth (160+ Playbooks, 65+ Success Stories, 30+ Pitch Deck Collections, 25+ Investor Resources), but also:

• 🤖 3+ New AI agent Templates Every Week

• 📚 A Growing Library of 20+ AI Agents

Get 7 day free trial

We’re already 70,000+ founders and operators inside!

The rest of the article is only available to premium subscribers.

Let’s begin!

Read more

But there’s a class of market research that customer conversations don’t cover: the structural shifts in a market that happen too slowly to surface in a single interview, the TAM assumptions that feel solid until someone runs the bottom-up math, the whitespace a competitor left open that no individual customer can see because they’re inside the problem.

That’s where Claude earns its place. Not replacing the conversations but rather sitting above them, connecting signals across sources a single founder couldn’t read fast enough and telling you whether the numbers you’re building on are real.

Inside you will find:

1. How to Build the Research Project That Knows Your Market

2. How to Size the Market and Find Your Entry Wedge

3. How to Map the Buyers Who Actually Hold the Budget

4. How to Read the Market Landscape Before It Becomes Obvious

5. How to Know What the Market Will Actually Pay

6. How to Test Your Positioning Before You’ve Built Anything

7. The CLAUDE.md That Runs Your Market Research Stack

👋 Just a quick note before you continue!

Building great AI systems and agents is quickly becoming one of the most important advantages a startup can have. So we’ve been building non-stop and this will become a much bigger part of PMF going forward.

From now on, as a premium subscriber, you’ll get access not just to the best resources on fundraising and growth (160+ Playbooks, 65+ Success Stories, 30+ Pitch Deck Collections, 25+ Investor Resources), but also:

• 🤖 3+ New AI agent Templates Every Week

• 📚 A Growing Library of 20+ AI Agents

Get 7 day free trial

We’re already 70,000+ founders and operators inside!

The rest of the article is only available to premium subscribers.

Let’s begin!

Read more

Most startups can’t rely on inbound.

You have to build the list yourself, research the right partners, find the paths in, write the emails, track every conversation and keep it all moving in parallel without losing any thread.

And once you’re in conversations, the operational signals matter as much as the pitch. How fast you follow up after a meeting, how specific your outreach is, how ready your data room is when someone asks, how consistently you keep investors warm even when there’s nothing to report.

This newsletter builds the system that handles both.

Inside you will find:

1. How to Build the Context That Runs Your Entire Raise

2. How to Find the 40 Funds Worth Your Time

3. How to Map Every Warm Intro Before You Send a Single Email

4. How to Write Outreach That Reads Like It Was Written for That Investor Specifically

5. How to Run the Pipeline Without Losing a Thread

6. How to Build a Data Room That Answers Questions Before They’re Asked

7. How to Keep Every Investor Warm (Including the Ones Who Said No)

👋 Just a quick note before you continue!

Building great AI systems and agents is quickly becoming one of the most important advantages a startup can have. So we’ve been building non-stop and this will become a much bigger part of PMF going forward.

From now on, as a premium subscriber, you’ll get access not just to the best resources on fundraising and growth (160+ Playbooks, 65+ Success Stories, 30+ Pitch Deck Collections, 25+ Investor Resources), but also:

• 🤖 3+ New AI agent Templates Every Week

• 📚 A Growing Library of 20+ AI Agents

Get 7 day free trial

We’re already 70,000+ founders and operators inside!

The rest of the article is only available to premium subscribers.

Let’s begin!

Read more

Since the skills.md launch, the open-source community has been packaging workflows, domain expertise and professional judgment into SKILL.md files and pushing them to public GitHub repositories.

By early 2026, over 1.6 million of them had been indexed, spanning 23 occupation groups and 867 job categories. There’s a marketplace that catalogues them all and most founders have never opened it.

I went through it and pulled the skills that actually matter if you’re building a startup — what they do and how to use them.

Inside you will find:

1. What SkillsMP Is and Why It’s the App Store Moment for Claude

2. The Two Skills That Handle Your Entire Fundraising Workflow

3. How to Know Your Market Better Than Any Analyst You Could Hire

4. The Four-Voice Council That Ends Decision Paralysis

5. Three Skills That Run Your Growth Engine on Autopilot

6. The Executive Coach in Your Terminal

👋 Just a quick note before you continue!

Building great AI systems and agents is quickly becoming one of the most important advantages a startup can have. So we’ve been building non-stop and this will become a much bigger part of PMF going forward.

From now on, as a premium subscriber, you’ll get access not just to the best resources on fundraising and growth (160+ Playbooks, 65+ Success Stories, 30+ Pitch Deck Collections, 25+ Investor Resources), but also:

• 🤖 3+ New AI agent Templates Every Week

• 📚 A Growing Library of 20+ AI Agents

Get 7 day free trial

We’re already 70,000+ founders and operators inside!

The rest of the article is only available to premium subscribers.

Let’s begin!

Read more

McKinsey generates $16 billion a year. Not because they hire people smarter than you. Their median hire is a 26-year-old with a good GPA and no industry experience.

What McKinsey does is take that 26-year-old and spend two years systematically installing a set of analytical frameworks into how they think.

By the time that person sits across from your CEO, they're not winging it. They're running a methodology that's been refined across 50 years and tens of thousands of engagements.

That methodology is what clients are buying when they write a $2M check. Not the analyst. The framework the analyst is running.

The frameworks are not secret. Minto published the Pyramid Principle. Martin and Lafley published Playing to Win. Kaplan and Norton published the Balanced Scorecard. Gadiesh and Gilbert published Profit Pool analysis in the Harvard Business Review. The intellectual infrastructure of elite consulting has been in print for decades.

The barrier was never access to the ideas, it was the time and organizational infrastructure required to operationalize them on a live problem, under deadline pressure, for a specific client situation.

Claude Opus 4.8 removes that barrier. This guide gives you 12 skills built directly on the frameworks McKinsey trains its consultants on not paraphrased, not simplified, but operationalized with the prompt logic that makes them work on your actual problems. The intellectual foundation, why the framework works, and exactly how to run it.

This is what $2M used to buy.

Inside you will find 12 skills:

01 — Problem Framing (McKinsey Issue Tree + Minto’s SCR)

02 — Financial Modeling & Analysis (McKinsey Value Driver Tree)

03 — Market & Competitive Intelligence (Profit Pool Analysis + Porter’s Five Forces)

04 — Document Synthesis at Scale (Minto Pyramid + McKinsey “So What” Discipline)

05 — Primary Research Synthesis (Grounded Theory + Argyris Espoused Theory vs. Theory in Use)

06 — Hypothesis Generation & Stress-Testing (McKinsey Hypothesis-Driven Problem Solving + Heuer’s Competing Hypotheses)

07 — Strategic Choice (Playing to Win — Martin & Lafley + Porter’s Strategic Coherence)

08 — Execution Planning (McKinsey 7-S + Bain’s RAPID + Bossidy & Charan’s Execution Standard)

09 — KPI Architecture & Value Realization (Kaplan-Norton Balanced Scorecard + McKinsey Value Capture)

10 — War-Gaming & Risk Pressure-Testing (Shell Scenario Planning via McKinsey + Game Theory Applied to Competitive Dynamics)

11 — Executive Communication (Minto’s Pyramid Principle + SCR + Aristotelian Rhetoric)

12 — Proposal & SOW Writing (SPIN Selling + CEB/Gartner Insight Selling + McKinsey Engagement Economics)

👋 Just a quick note before you continue!

Building great AI systems and agents is quickly becoming one of the most important advantages a startup can have. So we’ve been building non-stop and this will become a much bigger part of PMF going forward.

From now on, as a premium subscriber, you’ll get access not just to the best resources on fundraising and growth (160+ Playbooks, 65+ Success Stories, 30+ Pitch Deck Collections, 25+ Investor Resources), but also:

• 🤖 3+ New AI agent Templates Every Week

• 📚 A Growing Library of 20+ AI Agents

Get 7 day free trial

We’re already 70,000+ founders and operators inside!

The rest of the article is only available to premium subscribers.

Let’s begin!

Read more

What none of them solve is the question after that. Why did it drop? Which users? What changed?

That gap is not a dashboard problem but rather an intepretive one. And it’s the reason you can have Mixpanel, Amplitude and a perfectly instrumented product and still spend Monday morning clicking through filters without arriving at a decision.

Inside you will find:

1. How to Set Up the Analytics Project

2. How to Get Your Data In

3. How to Define Your Metrics So Claude Never Guesses

4. How to Run a Funnel and Activation Analysis Without a Data Team

5. How to Build Retention Cohorts and Read What They’re Telling You

6. How to Investigate a Churn Spike in Under 30 Minutes

7. How to Run the Monday Briefing

Attio is the AI CRM that compounds revenue around the clock.

It gives your team the foundation for moving fast, staying sharp, and scaling without breaking. Every customer signal, from emails and meetings to product usage, billing, support, and agent activity, is synced from day one, giving you a live picture of every account.

With Attio, you’ll get:

• Revenue agents, workflows, and automations across every stage of your motion

• Instant answers to anything you Ask Attio about your business

• Access to your customer data wherever you work, through Attio’s MCP, API, and App SDK

30,000+ teams use Attio to drive more revenue at scale. Are you one of them?

Try Attio Now!

👋 Just a quick note before you continue!

Building great AI systems and agents is quickly becoming one of the most important advantages a startup can have. So we’ve been building non-stop and this will become a much bigger part of PMF going forward.

From now on, as a premium subscriber, you’ll get access not just to the best resources on fundraising and growth (160+ Playbooks, 65+ Success Stories, 30+ Pitch Deck Collections, 25+ Investor Resources), but also:

• 🤖 3+ New AI agent Templates Every Week

• 📚 A Growing Library of 20+ AI Agents

Get 7 day free trial

We’re already 70,000+ founders and operators inside!

The rest of the article is only available to premium subscribers.

Let’s begin!

Read more

Email is one of the best channels a founder can build.

You own the list, the algorithm doesn’t change and the economics compound: every subscriber you keep is a subscriber you don’t have to buy again.

Most founders know this and still don’t do it well. They send a broadcast when they have something to say, skip weeks when they don’t and treat the list as a megaphone instead of a system. The newsletter doesn’t convert, they conclude and go back to spending money on ads.

The problem is the absence of infrastructure:

• a clear editorial position

• a welcome sequence that earns the relationship in the first seven days

• a segmentation logic that sends the right message to the right person

• a subject line process that learns over time instead of guessing every time

This guide helps you building that infrastructure, starting with a Claude interview that extracts your brand, audience and strategy in 30 minutes. Everything else follows from that document.

Inside you will find:

1. Why Email Is the Channel Most Founders Are Sitting On Without Knowing It

2. The Claude Interview: Extract Your Brand, Audience and Strategy

3. The B2B Path: How to Build a Vertical Newsletter That Generates Pipeline

4. The B2C and PLG Path: Sequences That Convert and Retain

5. How to Stop Treating Your List as One Audience

6. How to Run A/B Tests That Actually Learn

👋 Just a quick note before you continue!

Building great AI systems and agents is quickly becoming one of the most important advantages a startup can have. So we’ve been building non-stop and this will become a much bigger part of PMF going forward.

From now on, as a premium subscriber, you’ll get access not just to the best resources on fundraising and growth (160+ Playbooks, 65+ Success Stories, 30+ Pitch Deck Collections, 25+ Investor Resources), but also:

• 🤖 3+ New AI agent Templates Every Week

• 📚 A Growing Library of 20+ AI Agents

Get 7 day free trial

We’re already 70,000+ founders and operators inside!

The rest of the article is only available to premium subscribers.

Let’s begin!

Read more

Acquiring a new customer costs five to seven times more than retaining an existing one.

Most early-stage SaaS founders know this and still spend 80% of their time on acquisition figuring out retention is broken only when the churn line starts eating into the revenue chart.

You already know what’s happening in the product. What you don’t have is visibility into what’s happening inside individual accounts: which companies are getting value, which ones are drifting or which renewals will surprise you.

Inside you will find:

1. How to Build Your First Customer Health Score

2. How to Spot Churn Before the Account Decides

3. How to Onboard New Customers So They Actually Stay

4. How to Prepare for Every Account Review Call

5. What to Do When an Account Goes Red

6. The CLAUDE.md That Runs the Whole System

👋 Just a quick note before you continue!

Building great AI systems and agents is quickly becoming one of the most important advantages a startup can have. So we’ve been building non-stop and this will become a much bigger part of PMF going forward.

From now on, as a premium subscriber, you’ll get access not just to the best resources on fundraising and growth (160+ Playbooks, 65+ Success Stories, 30+ Pitch Deck Collections, 25+ Investor Resources), but also:

• 🤖 3+ New AI agent Templates Every Week

• 📚 A Growing Library of 20+ AI Agents

We’re already 70,000+ founders and operators inside!

Get 7 day free trial

The rest of the article is only available to premium subscribers.

Let’s begin!

Read more

Most product managers use Claude the same way they use Google. They type a vague question and as a result they get a generic answer.

Claude doesn’t know what you’re building or your context. The PMs who get real value out of Claude treat it differently. They:

• set it up like a new colleague

• give it the brief before they ask it to do the work

• bring it into the problem at the thinking stage rather than at the writing stage

• use it across every function of the job (not just PRDs)

Inside you will find:

1. How to Set Up Claude So It Actually Knows Your Product

2. How to Run Discovery Without a Research Team

3. How to Write PRDs That Don’t Come Back Full of Questions

4. How to Prioritize and Defend Your Roadmap

5. How to Run Retrospectives That Actually Change Something

6. How to Plan a Launch

👋 Just a quick note before you continue!

Building great AI systems and agents is quickly becoming one of the most important advantages a startup can have. So we’ve been building non-stop and this will become a much bigger part of PMF going forward.

From now on, as a premium subscriber, you’ll get access not just to the best resources on fundraising and growth (160+ Playbooks, 65+ Success Stories, 30+ Pitch Deck Collections, 25+ Investor Resources), but also:

• 🤖 3+ New AI agent Templates Every Week

• 📚 A Growing Library of 20+ AI Agents

Get 7 day free trial

We’re already 70,000+ founders and operators inside

The rest of the article is only available to premium subscribers.

Let’s begin!

Read more

Everyone does customer interviews. That part is not the problem.

The problem is what you walk out with. You get on a call, the customer talks for forty minutes, you nod, you take notes and you hang up with a feeling. The real signal was in there: the moment they mentioned a workaround they’ve been using for two years, the throwaway comment about their boss, the thing they said at minute thirty-eight that contradicted everything they said in the first ten minutes. You heard it. You didn’t catch it.

The insight that changes a roadmap decision is almost never the one the customer leads with. It’s buried. It requires pattern recognition across ten conversations, not one.

Claude fixes the part between the conversation and the decision. With the right setup it helps you:

• Ask the right questions based on your specific product hypotheses

• Process every transcript into structured signal in minutes

• Find the patterns that repeat across 10-20 interviews

• Turn the research into concrete product decisions

This guide builds that system with the exact prompts for each step.

Inside you will find:

1. How to Set Up Your Research Project

2. How to Write the Context Files Without Staring at a Blank Page

3. How to Build the Interview Guide with Claude

4. How to Process a Transcript in 5 Minutes

5. How to Find Patterns Across Interviews

6. How to Extract Jobs-to-be-Done

7. How to Turn Insights into Decisions

👋 Just a quick note before you continue!

Building great AI systems and agents is quickly becoming one of the most important advantages a startup can have. So we’ve been building non-stop and this will become a much bigger part of PMF going forward.

From now on, as a premium subscriber, you’ll get access not just to the best resources on fundraising and growth (160+ Playbooks, 65+ Success Stories, 30+ Pitch Deck Collections, 25+ Investor Resources), but also:

• 🤖 3+ New AI agent Templates Every Week

• 📚 A Growing Library of 20+ AI Agents

Get 7 day free trial

We’re already 70,000+ founders and operators inside

The rest of the article is only available to premium subscribers.

Let’s begin!

Read more

The CFO function is 40 hours a month of mechanical work: pulling data, reconciling numbers, explaining variances, building scenarios, formatting reports. At earlier stages, none of it requires a seasoned finance executive.

Claude can run most of that layer. The setup takes less than an hour.

Inside you will find:

1. How to Build Your CFO Context in 20 Minutes

2. How to Run Your Weekly Finance Check

3. How to Close the Month Without a Finance Team

4. How to Build and Update a Rolling Forecast

5. How to Model Scenarios

6. The Strategic Decisions Prompts

7. How to Write Investor Updates

👋 Just a quick note before you continue!

Building great AI systems and agents is quickly becoming one of the most important advantages a startup can have. So we’ve been building non-stop and this will become a much bigger part of PMF going forward.

From now on, as a premium subscriber, you’ll get access not just to the best resources on fundraising and growth (160+ Playbooks, 65+ Success Stories, 30+ Pitch Deck Collections, 25+ Investor Resources), but also:

• 🤖 3+ New AI agent Templates Every Week

• 📚 A Growing Library of 20+ AI Agents

Get 7 day free trial

We’re already 70,000+ founders and operators inside!

The rest of the article is only available to premium subscribers.

Let’s begin!

Read more

Most founders use Claude like Google: open a tab, ask a question, close it. Next session they start from zero.

A skill changes that. It’s a persistent context system (installed once and loaded automatically on every run) that gives Claude your brand voice, your ICP, your positioning, and your competitive context before you type a word.

There are a hundred of these skills, built for founders, across every startup function. They live in public GitHub repositories, they’re free to install, and most founders don’t know they exist.

Inside you will find:

1. You’re Using Claude at 20% — Here’s What the Other 80% Looks Like

2. The 100 Founder Skills, Mapped by Function

3. The Three Skills You Install First

4. How Skills Share Context Across Your Entire Stack

5. Where to Start in the Next 30 Minutes

Launch fast. Design beautifully. Build your company’s website on Framer.

Framer helps teams design, build, and launch their marketing sites lightning fast.

With the ability to publish hundreds of CMS pages in a single click, operate at a global scale with seamless localization, and even host unified content across multiple domains, teams have never been able to ship faster.

Trusted by companies like Miro, Bilt, and Perplexity.

• Speed without chaos: ship pages and updates faster without turning the site into a fragile set of one-off hacks

• Reduce dependency: shift routine brand and marketing work out of product engineering queues.

• Production-grade foundation: Run real marketing systems (CMS, SEO, performance optimization) with governance and collaboration

👉 Build your company’s site on Framer today

Apply to Claim Your Free Year

👋 Just a quick note before you continue!

Building great AI systems and agents is quickly becoming one of the most important advantages a startup can have. So we’ve been building non-stop and this will become a much bigger part of PMF going forward.

From now on, as a premium subscriber, you’ll get access not just to the best resources on fundraising and growth (160+ Playbooks, 65+ Success Stories, 30+ Pitch Deck Collections, 25+ Investor Resources), but also:

• 🤖 3+ New AI agent Templates Every Week

• 📚 A Growing Library of 20+ AI Agents

We’re already 75,000+ founders and operators inside!

Get 7 day free trial

The rest of the article is only available to premium subscribers.

Let’s begin!

Read more

Series A investors see between 300 and 500 decks a year.

The typical decision on whether to keep reading happens before the fifth slide. The content in slides six through twenty-five rarely changes that decision. What changes it is whether the argument in the first four is coherent enough to make someone want the rest.

BCG solved this as a system. Two layers, ten rules, one framework their consultants learn in the first six months on the job. The first layer governs the story from end to end. The second governs every individual slide inside it. When both layers are followed, the argument is impossible to miss.

Inside you will find:

1. The BCG Framework: What It Is and Why It Works

2. How to Set Up the Claude Project

3. How to Make Claude Apply the BCG Framework

4. How to Input Your Startup the Right Way

5. How to Set Your Own Design System

6. How to Generate Your BCG-Style Pitch

7. How to Use Claude’s Output in Gamma, Google Slides or PowerPoint

8. The Complete Startup Pitch (Practical Example)

9. Bonus: Real BCG Decks to Study

👋 Just a quick note before you continue!

Building great AI systems and agents is quickly becoming one of the most important advantages a startup can have. So we’ve been building non-stop and this will become a much bigger part of PMF going forward.

From now on, as a premium subscriber, you’ll get access not just to the best resources on fundraising and growth (160+ Playbooks, 65+ Success Stories, 30+ Pitch Deck Collections, 25+ Investor Resources), but also:

• 🤖 3+ New AI agent Templates Every Week

• 📚 A Growing Library of 20+ AI Agents

We’re already 70,000+ founders and operators inside.

Get 7 day free trial

The rest of the article is only available to premium subscribers.

Let’s begin!

Read more

Imagine having Marc Andreessen on speed dial.

Ask him whether to raise now or wait. Whether to rebuild for AI or add features. Whether the big tech competitor that just announced your product is a threat or a validation. Most founders will never get that access. But with Claude, you can get surprisingly close.

Marc has published more than almost any investor alive. 20 years of thinking on markets, startups and technology, all sitting in public, mostly unread.

This guide teaches you how to scrape it all into one folder, load it into Claude Code with a system prompt that grounds every response in his actual writing and interrogate it like an advisor. Not a chatbot guessing what Marc sounds like. An agent that cites the source file before it answers.

📚 By the end you’ll have the scraper, the system prompt, and real examples of founder questions with Marc-style outputs grounded in his actual catalog.

Inside you will find:

1. Why Marc’s Public Catalog Is More Useful Than a VC Call

2. How to Scrape Five Sources Into One Folder With Claude Code

3. The System Prompt That Makes Claude Respond Like Marc

4. Which Questions the Agent Answers Best

5. Five Real Founder Questions

👋 Just a quick note before you continue!

Building great AI systems and agents is quickly becoming one of the most important advantages a startup can have. So we’ve been building non-stop and this will become a much bigger part of PMF going forward.

From now on, as a premium subscriber, you’ll get access not just to the best resources on fundraising and growth (160+ Playbooks, 65+ Success Stories, 30+ Pitch Deck Collections, 25+ Investor Resources), but also:

• 🤖 3+ New AI agent Templates Every Week

• 📚 A Growing Library of 20+ AI Agents

We’re already 70,000+ founders and operators inside.

Get 7 day free trial

The rest of the article is only available to premium subscribers.

Let’s begin!

Read more

P.S. At the end, premium subscribers will find an exclusive discount to try cubic!

Today, I want to show you how the fastest engineering teams I know actually ship code today.

Writing code used to be the bottleneck. With AI, that’s stopped being true. Teams are shipping ten or twenty times more code than they were a year ago, and review is what can’t keep up. Senior engineers don’t have time to read every PR properly, so bugs slip through and team standards quietly erode. The faster you ship, the harder it gets to know what’s actually in your own codebase.

cubic is the AI code reviewer the most advanced engineering teams in the world rely on.

To be concrete: cubic doesn’t write code. It’s a specialised layer that reviews it.

If you’re writing code for production at scale, you need a dedicated reviewer. Code-writing agents have their own blind spots, and they’re not built to review their own work. You need something that understands your team, runs different models from your coding agent, and is purpose-built for review.

You still use your coding agent of choice (Claude, Codex, Cursor) for the writing. cubic is what runs after, replacing whatever you were using to review AI-written code before, whether that was you eyeballing the diff or another tool.

Internally, we’re a team of five. We outperform teams that have raised 100x more than we have. Our reviewer ranks #1 on every independent code review benchmark, beating every other competitor by a wide margin.

Between the two, the same workflow keeps showing up. We see how the best engineering teams in the world ship, and we ship the same way ourselves.

📚 That's what I want to walk through here. The loop, roughly: set up your repo so your agent works the way you do, plan before you prompt, let the agent write, have a different agent review, ship and let a deeper agent review run overnight.

Inside you will find:

1. Before You Prompt Anything

2. Planning Before Coding

3. Letting the Agent Build

4. The Review Loop

5. In the PR, Go Deeper

6. Overnight Review

7. The Full Loop

8. BONUS: exclusive discount to try cubic!

Let’s start at the beginning.

1. Before You Prompt Anything

The goal at this stage is simple: give your agent enough context that it doesn’t have to guess. Your repo layout, team conventions, standards, all in a place it can read once and refer back to.

Get this right and every prompt downstream gets shorter and better. Skip it and you’ll be re-explaining yourself in every conversation.

This is the boring part, but it matters.

Put an AGENTS.md (or CLAUDE.md) at the root of your repo. Mine has:

• Repo layout, the directories that actually matter

• Build, test, and lint commands

• Engineering conventions we follow

• A short list of “do not do this” rules

• What “done” actually looks like for our codebase

Your agent reads it once and stops asking you the same questions in every prompt.

One thing worth doing on top of that: hook up the cubic MCP to your coding agent.

cubic learns from how your senior engineers review code. With the MCP connected, your agent already knows what your team cares about before it writes a line. “What would the senior reviewer flag here?” becomes something the agent can answer, not guess at.

2. Planning Before Coding

Use Plan mode. In Cursor that’s Shift+Tab, or /plan.

Let the agent interview you first. The temptation is to drop one giant prompt in and hope. Resist it. A five-minute back-and-forth gets you better output than a perfectly worded one-shot.

One thing that’s underrated: dictation. There are a bunch of tools for it, I use Willow Voice. You talk a lot faster than you type, so you can dump way more context into the plan and actually have a high-speed back-and-forth with the agent instead of laboriously typing each turn.

Break work into thin slices: plan, approve, implement, test, cleanup. Each one’s a small conversation.

A few less obvious things I do here.

One of the biggest weaknesses of today’s AI agents, even the best ones, is design. They’re bad at it. Drop a design problem on them cold and the output usually looks like every other AI-generated UI on the internet right now.

The thing they are good at is copying. Give them strong references and they perform much better.

So for any UI work, I solve the design problem before I solve the code problem. I point an MCP like Mobbin at the plan so the agent has real reference designs to pull from instead of guessing. Then I have it sketch low-fidelity ASCII diagrams of the layout before any real code gets written. Way easier to argue about structure on a wireframe than in a 600-line diff.

The last one isn’t design-specific: match the model to the task. Big model for architecture, cheaper model for the grind.

3. Letting the Agent Build

Once the plan is in place, you can let the agent run most of the loop itself. Models are good enough now to self-debug.

Have it run your app locally, see what breaks, and iterate until the build is green and the tests pass. You don’t need to sit there feeding it each compile error by hand.

If there’s a UI involved, ask the agent to take screenshots of what it’s built as it goes. It’s surprisingly good at catching its own mistakes when it can actually see the output instead of just diffing text.

When it says it’s done, do one last check: does the output actually respect the ASCII diagrams and references from the plan? Drift happens, especially in longer sessions. If it drifted, send it back and have it fix the gap.

4. The Review Loop

There are two real problems with shipping AI-written code.

• The first is the obvious one: agents make mistakes. They hallucinate APIs. They write insecure patterns. They write queries that look fine and run for ten seconds in production. You can’t catch all of that in a 30-second diff skim, especially when you’re shipping ten of these a day.

• The second is more subtle: agents don’t know your context. They don’t know you’re on an MVP where speed matters more than perfection, or that this service is a critical path that can’t go down. They don’t know the standards your team has spent years settling on.

This is where cubic comes in. You don’t run the review yourself. You tell your coding agent to call the cubic CLI when it’s done writing, and the two agents iterate together until there’s nothing left to flag. A different agent (different models, different blind spots) reviews the diff, hands the issues back to your coding agent, and your coding agent fixes them. Fully agentic. You don’t sit there driving it.

I think the different-model bit is the most underrated part of all this. If the same model that wrote the code also reviews it, you’ll miss the same bugs twice. The blind spots are identical. You want a different reviewer on the other side.

cubic actually does this for you automatically. We detect which model wrote the code and route the review to a different one. If we see Opus generated the diff, we’ll review it with Codex. If it was Codex, we’ll review with Opus. You don’t have to think about it.

But the part that really moves the needle is that cubic knows your team. It syncs your standards, the patterns your senior engineers actually flag in review, the bits specific to your repo. You don’t get a generic review, you get one that reflects what your team actually cares about.

By the time the loop finishes, the diff is already cleaned up. You step in to approve or push back, not to do the review yourself.

5. In the PR, Go Deeper

Push to GitHub.

cubic’s GitHub agents do a heavier pass than the CLI. More context, more thinking time.

Use the cubic skill in your IDE to talk back to the comments. Same loop as before, just with a more thorough reviewer on the other end.

6. Overnight Review

Merge your PR. Ship it. Go home.

Once you merge, cubic kicks off a deeper review on whatever just landed in main. It runs for hours, up to twelve of them, doing codebase-level analysis. Cross-file logic, security holes, the kind of bug you only catch with full-repo context. Things a 90-second PR review just can’t surface.

If it finds something, there’s a fix PR waiting for you in the morning.

It’s the kind of compute budget you only get when nobody’s waiting on the answer.

7. The Full Loop

End to end, this is how we ship:

1. Setup: AGENTS.md, environment, cubic MCP connected

2. Plan: plan mode, let the agent interview you, thin slices

3. Write: coding agent does it

4. Local review: cubic CLI before you push

5. PR review: cubic GitHub agents go deeper

6. Merge

7. Overnight: cubic deep review runs while you sleep

8. Morning: merge the fix PR if there is one

Writing and reviewing are both jobs for agents now. What’s left for you is judgment, and the call on whether to actually ship.

If you take one thing from this, take this: don’t let the same model that wrote your code be the one signing off on it.

8. BONUS: exclusive discount to try cubic! (for Paid subscribers)

Read more