Anthropic engineer:
"You're not supposed to prompt Claude. You're supposed to build a system that prompts itself."
But most people still haven't made that jump
One prompt
One answer
Close the tab
Start over tomorrow
That is the weakest way to use Claude
The real setup is different
claude.md
Plugins nobody installs
Workflows that run without you
Agents that prompt themselves
-> 24% of your window is gone before you type a word
-> 95% of users have never touched the plugins
-> one prompt and closing the tab leaves 90% on the table
If you've been using Claude for months and still start every session from scratch, you have at least 28 untouched features. probably 30
Watch the video instead of another show tonight
Bookmark the article before it gets lost in your feed
BREAKING: MIT just mass released their Al library for free. (Links included)
I went through these and honestly... this is better than most paid courses I've seen.
Here's the full list of books:
Foundations
1. Foundations of Machine Learning Core algorithms explained. Theory meets practice.
2. Understanding Deep Learning Neural networks demystified. Visual explanations included.
3. Machine Learning Systems Production-ready architecture. System design principles.
Advanced Techniques
4. Algorithms for ML Computational thinking simplified. Decision-making frameworks.
5. Deep Learning The definitive textbook. Covers everything deeply.
Reinforcement Learning
6. RL Basics (Sutton & Barto) The classic. Agent training fundamentals.
7. Distributional RL Beyond expected rewards. Advanced theory.
8. Multi-Agent Systems Agents working together. Coordination and competition.
9. Long Game Al Strategic agent design. Future-focused thinking.
Ethics & Probability
10. Fairness in ML Bias detection. Responsible Al practices.
11. Probabilistic ML (Part 1 & 2)
Links: https://t.co/AhDqm9x1QC
Most people pay thousands for bootcamps that teach half of this.
Bookmark it. Start anywhere. Just start.
Repost for others Follow for more insights on Al Agents.
MIT's books on Al
Foundations
1. Foundations of Machine Learning - https://t.co/HxbXfsDIl6
2. Understanding Deep Learning - https://t.co/AyeQav2yzN
3. Machine Learning Systems - https://t.co/0AxGtjBFwA
Advanced Techniques
4. Algorithms for ML - https://t.co/LOjFeK1hut
5. Deep Learning - https://t.co/Ztmu7X6gNM
Reinforcement Learning
6. RL Basics (Sutton & Barto) - https://t.co/HAWxL28df1
7. Distributional RL - https://t.co/VB1zBuSzag
8. Multi-Agent Systems - https://t.co/3tWqJaimYn
9. Long Game Al - https://t.co/vYDuy1XKT2
Ethics & Probability
10. Fairness in ML - https://t.co/B4lAj2ivpF
11. Probabilistic ML (Part 1) - https://t.co/folJrX24sf
12. Probabilistic ML (Part 2) - https://t.co/BMOjc8qSqZ
We love @dominos our favorite around here. But how convenient the day I needed to provide some feedback on how my pizza tasted 😞 and it’s not working! Something was off on the taste of our garlic base
"Your team will swallow you."
That’s what a co-founder, and friend, told me right after we raised $1.2M.
At the time, I didn’t fully get it.
Now I do.
As a founder, two things can happen:
You hire underperformers who drain momentum.
You hire top talent who push you to level up.
If it feels like your team is outgrowing you… maybe they are.
The fix? Never stop growing.
Stay sharp. Structure your life to make time for learning, experimenting, and talking to other founders. Be present in the key conversations and, above all, come prepared with enough insight to add real value.
Neglect that, and your team will become more qualified to make the decisions that shape your future, without you.
And if you're a co-founder, that moment might come before you're even fully vested.
7. In August 2024, Simona Costantini joined us as CMO. From day one, she brought clarity and heart. She gets podcasters—and keeps us grounded in what they actually need.
Meeting her IRL at PodFest in Jan 2025? That’s when this started feeling real.
#northflow#podfest#saas
Just launched: 3 new episode templates in Northflow
Solo
Guest interview
Full workflow (default)
They’re ready to use the moment you sign in—and you can always make them your own later.
Real story: A podcast manager saved 4 hours per client/month using our quick task mode and templates.
That’s 4 hours x 7 clients = a whole workday back.