How to set up Claude Cowork so it actually works like an AI chief of staff (not just another chatbot):
1. Most people open Cowork, type a message, and get generic output. It's not a Claude problem. It's a setup problem. Cowork needs context before it can help you. Who you are. How you work. What you're building. Your team. Your priorities. Give it that, and every session feels like picking up a conversation with an executive assistant.
2. The setup has three layers:
a) Global instructions (who you are, how you work, what Claude should never do).
b) Connectors (Slack, Gmail, Google Calendar, Notion)
c) And a folder structure on your computer that acts as Claude's long-term memory. That combination is what takes it from generic to personalized.
3. Skills are the real leverage. A skill is a markdown file that tells Claude exactly how to do one thing well. Write my newsletter. Coach me on a decision. Review a case study. Each skill lives in its own folder with context, examples, and a definition of what success looks like.
4. We built a CEO coach skill in the video below. Gave it business context, leadership style, company goals. Then tested it with a real decision: should we increase our newsletter from once to twice a week? It came back with trade-offs, second-order consequences, and risk assessment.
5. Then we built a multi-agent advisory board. Five subagents, each with a defined persona:
a) the operator
b) the skeptic
c) the customer advocate
d) the finance partner
e) the legal/risk advisor.
You feed it a decision. Each agent evaluates independently. The main agent synthesizes the feedback. It's like having a board meeting on demand.
6. Third skill: a thought leadership content pipeline. Topic scoring, idea capture, distribution cadence, tone calibration. All built from your actual expertise and audience. Designed so an executive can go from idea to published post without starting from scratch every time.
7. The workspace map is what ties it all together. It's a top-level file that shows Claude how to navigate your entire setup. Which folders exist, what skills live where, how to invoke them. Without it, Claude has to search for everything. With it, Claude goes straight to what it needs.
8. Everything you build is portable. The folder structure works in Cowork, Claude Code, and Codex. Push it to a private GitHub repo and you can access it from your phone through Claude Code, or use Claude Dispatch.
9. The pattern is repeatable. Pick a task you do often. Create a folder. Build a skill. Add examples of what success looks like, and what a bad output looks like. Test it. Workshop it. Move on to the next one. Each skill is like onboarding a new employee who never forgets and never needs to be re-trained.
The people who invest in this setup now are the ones who will have a 10x advantage when these tools get even better. And they're getting better fast.
I sat down with @alexlieberman on Human In The Loop and we built all three of these live from scratch. Full breakdown in the video below..
I tried to explain this as clear as possible for my non-developer crowd.
Send it to someone who should be using Cowork but isn't yet. Or bookmark it to level up when you're ready.
Watch 👇🏼
One of the most active roll-ups?
Since leaving McKinsey, Luis and his team have done over 30 acquisitions (seven last December) by consolidating fire safety businesses.
They do $8M+ in EBITDA, with the goal to double it over the next 12-18 months.
Snow notes:
0:00 From rural Mexico to more than 30 acquisitions
4:00 Buy-and-build thesis
6:45 Funding the first deals
11:55 The 100-day integration playbook
19:00 Using AI to scale operations and service quality
32:05 Deal sourcing at scale without spam
37:05 Managing risk, customer concentration, and diligence
44:35 Takeaways for other buyers
53:00 Hold vs sell and capital discipline
How to find business ideas:
1. Go to Flippa.
2. Filter sites doing $10K+/m.
3. Pick a product idea that has demand.
4. Check reviews.
5. Build with better features.
Do SEO and make money...
This Claude + Slack + Sonic 3 setup saves me 2 hours daily.
I'm an engineer at @cartesia ($100M raised) and here's how it works:
→ Claude pulls updates from my Slack channels
→ summarizes everything
→ Sonic 3 converts to natural voice
→ sends audio briefing to my DMs
Takes just 60 seconds to listen
Then I added emotion tags and it sounds like an actual morning show host.
Complete Tutorial 👇
It’s been a few weeks since we brought GPT-5 to Microsoft 365 Copilot, and it’s quickly become part of my everyday workflow, adding a new layer of intelligence spanning all my apps.
Here are 5 prompts that show what’s now possible:
In it’s heyday, Goldman’s special situations group was the navy SEALs of money making. Today’s guest, Alan Waxman, used to run that group before leaving to build Sixth Street, now a $115b behemoth.
SSG heads were sometimes of the more brainy, nerdy variety. Not Waxman. He is a force of nature and energy who apparently would pound around the SSG office, loudly and enthusiastically asking people “who is going to make us some money today?!”
When I asked another SSG alum about Alan, he said his main memory was his remarkable nose for talent. Once, the smartest guy at SSG (which is saying something) was a mere entry level associate, 6 or 7 rungs in the hierarchy below Waxman. But, Waxman immediately recognized the raw talent and was joined to this associate at the hip.
Under Waxman and his team, SSG produced an insane (so insane I can’t quote it!) percent of Goldman’s bottom line. In creating Sixth Street with his partners and team, he sought to recreate and expand the magic of the SSG days. Here, in his first interview of this type, he shares the entire story.
I found Alan to be a singular force. His team is ridiculously talented, and nobody leaves (they’ve never lost a senior person). They’ve even built a unique pool of capital called Tao that sits atop the rest of the firm…tens of billions that can go anywhere and do anything as a permanent pool of money with no restrictions, other than to earn the highest risk adjusted returns possible. Sounds a lot like SSG.
This was one of my favorite conversations this year. I hope you enjoy. Face the tiger!
Timestamps
0:00 Intro
0:38 The Formative Goldman Sachs Experience
5:58 Unitizing Risk and Return
10:09 Facing the Tiger: Culture and Values
24:55 The Genesis of Sixth Street
34:09 Spotify and Airbnb Investments
37:52 The Flexibility of TAO
41:42 COVID-19: Playing Offense
44:42 Analyzing Risk and Business Models
48:35 Investing in Sports and Live Experiences
54:44 Developing Investment Themes
58:16 Personal Development and Firm Culture
1:19:00 The Future of Sixth Street
1:21:52 The Kindest Thing
Roger Federer’s commencement speech wasn’t just a viral moment. It was masterful - The Athletic Dr Fed well deserved @rogerfederer https://t.co/nH8eeWtnQY
New short course: Evaluating AI Agents! Evals are important for driving AI system improvements, and in this course you'll learn to systematically assess and improve an AI agent’s performance. This is built in partnership with @arizeai and taught by @JohnGilhuly, Head of Developer Relations, and @amankhan, Director of Product.
I've often found evals to be a critical tool in the agent development process - they can be the difference between picking the right thing to work on vs. wasting weeks of effort. Whether you’re building a shopping assistant, coding agent, or research assistant, having a structured evaluation process helps you refine its performance systematically, rather than relying on random trial and error.
This course shows you how to structure your evals to assess the performance of each component of an agent and its end-to-end performance. For each component, you select the appropriate evaluators, test examples, and performance metrics. This helps you identify areas for improvement both during development and in production. (If you're familiar with error analysis in supervised learning, think of this as adapting those ideas to agentic workflows.)
In this course, you'll build an AI agent, and add observability to visualize and debug its steps. You’ll learn about code-based evals, in which you write code explicitly to test a certain step, as well as LLM-as-a-Judge evals, in which you prompt an LLM to efficiently come up with ways to evaluate more open-ended outputs.
In detail, you’ll:
- Understand key differences between evaluating LLM-based systems and traditional software testing.
- Add observability to an agent by collecting traces of the steps taken by the agent and visualizing them
- Choose the appropriate evaluator - code-based, LLM-as-a-Judge, human-annotation based - for each component.
- Compute a convergence score to evaluate if your agent can respond to a query in an efficient number of steps.
- Run structured experiments to improve the agent’s performance by exploring changes to the prompt, LLM model, or the agent’s logic.
- Understand how to deploy these evaluation techniques to monitor the agent’s performance in production.
By the end of this course, you’ll know how to trace AI agents, systematically evaluate them, and improve their performance.
Please sign up here: https://t.co/hTNCM8xuYn
Why AI Won't Cause Unemployment
Marc Andreessen
Reposted Jan 24, 2025
"In retrospect, I wish I had known more about the hazards and difficulties of [running] a business." -- George McGovern
Fears about new technology replacing human labor and causing overall unemployment have raged across industrialized societies for hundreds of years, despite a nearly continual rise in both jobs and wages in capitalist economies. The jobs apocalypse is always right around the corner; just ask the Luddites.
We had two such anti-technology jobs moral panics in the last 20 years — “outsourcing” enabled by the Internet in the 2000’s, and “robots” in the 2010’s. The result was the best national and global economy in human history in pre-COVID 2019, with the most jobs at the highest wages ever.
Now we’re heading into the third such panic of the new century with AI, coupled with a continuous drumbeat of demand for Communist-inspired Universal Basic Income. “This time is different; AI is different,” they say, but is it?
Normally I would make the standard arguments against technologically-driven unemployment — see good summaries by Henry Hazlitt (chapter 7) and Frédéric Bastiat (his metaphor directly relevant to AI). And I will come back and make those arguments soon. But I don’t even think the standand arguments are needed, since another problem will block the progress of AI across most of the economy first.
Which is: AI is already illegal for most of the economy, and will be for virtually all of the economy.
How do I know that? Because technology is already illegal in most of the economy, and that is becoming steadily more true over time.
How do I know that? Because, [see chart].
This chart shows price changes, adjusted for inflation, across a dozen major sectors of the economy.
As you can see, we actually live in two different economies.
The lines in blue are the sectors where technological innovation is allowed to push down prices while increasing quality. The lines in red are the sectors where technological innovation is not permitted to push down prices; in fact, the prices of education, health care, and housing as well as anything provided or controlled by the government are going to the moon, even as those sectors are technologically stagnant.
We are heading into a world where a flat screen TV that covers your entire wall costs $100, and a four year college degree costs $1 million, and nobody has anything even resembling a proposal on how to systemically fix this.
Why? The sectors in red are heavily regulated and controlled and bottlenecked by the government and by those industries themselves. Those industries are monopolies, oligopolies, and cartels, with extensive formal government regulation as well as regulatory capture, price fixing, Soviet style price setting, occupational licensing, and every other barrier to improvement and change you can possibly imagine. Technological innovation in those sectors is virtually forbidden now.
Whereas the sectors in blue are less regulated, technology whips through them, pushing down prices and raising quality every year.
Note the emotional loading of the interplay of production and consumption here. What do we get mad about? With our consumer hat on, we get mad about price increases — the red sectors. With our producer hat on, we get mad about technological disruption — the blue sectors. Well, pick one; as this chart shows, you can’t have your cake and eat it too.
Now think about what happens over time. The prices of regulated, non-technological products rise; the prices of less regulated, technologically-powered products fall. Which eats the economy? The regulated sectors continuously grow as a percentage of GDP; the less regulated sectors shrink. At the limit, 99% of the economy will be the regulated, non-technological sectors, which is precisely where we are headed.
Therefore AI cannot cause overall unemployment to rise, even if the Luddite arguments are right this time. AI is simply already illegal across most of the economy, soon to be virtually all of the economy.
Hindustan Unilever Limited (HUL), India’s largest FMCG company, is introducing a new approach to deliver its products directly to retail outlets - the direct-to-Kirana model, which could replace the traditional distribution system.
Volvo posted a 3 min and 46 second ad on Instagram, shot by Hoyte Van Hoytema, the cinematographer of Interstellar and Oppenheimer.
It goes against every single rule you can think about as a social lead. Length. Format. Over-produced.
Every comment under the ad said it immediately put Volvo in their consideration set. It's fucking fantastic.
Excited to announce our $50M Series B led by Andreessen Horowitz.
Link to our manifesto here: https://t.co/FsYer8Hn8r
In 1999, Salesforce brought software to the cloud. In 2024, 11x is killing traditional software as we know it, and unleashing the era of digital workers.
So, what sets 11x apart?
- We don’t build software. We build digital workers.
- We don’t sell tools. We sell work outcomes.
- We're turning code into labor, starting with GTM teams.
Since our series A announcement a few weeks ago, we have accelerated growth, doubled headcount, acquired Opkit to accelerate our AI Voice development, moved to SF, rolled out an entirely agentic version of Alice, and partnered with some of the world’s largest enterprises and most sophisticated GTM teams. It's still day 1.
Grateful to our customers, team, and investors. We are hiring cracked engineers and operators in San Francisco - [email protected] ❤️
Federer, Murray, Djokovic, Ruud, Monfils, Medvedev, Rublev, & more share their thoughts on Rafa Nadal in honor of his retirement announcement
Gael: “He’s a very caring person. An unbelievable champion and legend. For me he’s the ultimate fighter” 🥹
Mil gracias a todos
Many thanks to all
Merci beaucoup à tous
Grazie mille à tutti
谢谢大家
شكرا لكم جميعا
תודה לכולכם
Obrigado a todos
Vielen Dank euch allen
Tack alla
Хвала свима
Gràcies a tots