A master prompt is your Constitution for working with AI.
It sets the laws.
You revisit it. Amend it. Let it evolve as your taste sharpens.
It's not a prompt. It's how you think on paper.
how to use obsidian + claude code to build a 24/7 personal operating system and build your startup:
1. write everything in markdown (daily notes, projects, beliefs, people, meetings)
2. link your notes together so they mirror how your brain actually thinks.
3. install obsidian cli so claude code can read your entire vault + the relationships.
4. stop reexplaining projects every session. use reference files instead.
5. build custom slash commands:
/context → load your full life + work state
/trace → see how an idea evolved over months
/connect → bridge two domains you’ve been circling
/ideas → generate startup ideas from your vault
/graduate → promote daily thoughts into real assets
6. keep a strict rule: human writes the vault. agents read it, suggest, execute.
7. let claude aka clode surface patterns you’ve been unconsciously circling for years.
8. delegate from inside your notes. one sentence in obsidian → agent handles the rest.
9. treat writing as leverage.the more you write, the more context your agents have.
10. understand this:markdown files are the oxygen of llms.
i really enjoyed seeing how to use obsidian thanks to @internetvin
vin uses ai like a thinking partner wired into his life’s work.
99.99% of people won’t do this because it requires reflection + setup.
but once the vault exists, the agent stops being generic.
it starts thinking in your voice.
episode is live on @startupideaspod (more there)
this one is different. send this tweet to a friend.
im still processing how game changer obsidian + claude code is, maybe you too
watch
You're working on AI powered applications – there's limited time and resources, and you have to pick the best path forward.
https://t.co/PpH9maUPQM
In tech, we're all familiar with the concept of a great "product thinker" – someone who always knows what to work on, what tradeoffs are worth making, what metrics to look at, etc. Where others only see problems, they seem to naturally find solutions.
But AI is a total blackbox. The rules are changing – how do you navigate these product decisions when the inner workings of your product are shrouded in uncertainty?
Companies are currently locked in a fierce arms race, scrambling to find developers and product leaders who can help them successfully incorporate ai into their products before a competitor does it better.
Among the already scarce technical talent in AI, finding even one person with that special product sense is even rarer.
This course aims to do the impossible: Show anyone with the technical skills how to develop that other more mysterious sense of how to improve products, specifically in the context of RAG.
Your instructors, Dan and Jason, are AI product consultants with experience at companies like Google, Meta, Stitch Fix, and a dozen more, ranging from startups to Fortune 100 enterprises. When companies are struggling to make progress, they hire Jason and Dan to help their AI teams find "the path" forward.
After taking this course, you'll walk away with:
* A community of other operators and AI product thinkers
* The ability to identify high-impact tasks and prioritize effectively
* The necessary skills to make informed tradeoffs and choose relevant metrics
* An improved sense for focusing on what matters most in AI product development
* Knowledge of navigating AI product decisions in uncertain environment
Here is the improved text:
Plus, you'll also develop a technical understanding of:
* How to cold start your evaluation pipeline for retrieval
* The limitations of embedding models and how to think about rerankers and fine-tuning
* Retrieval metrics and how to use them to quickly run experiments and test instead of guessing at what will perform well
Introducing Supermemory - an AI hub for all your bookmarks and notes.
content you consume often gets lost. put it in your second brain to make use of it.
me and my friends have been working on this open source project for months now - but the story is actually crazy 🧵
Testing AI Products is similar to any software testing.
• Do you have ANY type of tests?
• Your app's language is unclear, did you write a controlled vocabulary?
• How would you know when there is a regression?
• Observability?
• How do you interview your users?
Test early