Everyone at Sierra uses an internal agent called Pinecone to automate 90% of our coding, analytics, and busywork. I can't go back to any other way of working.
Pinecone:
* Runs an agentic harness in our internal cloud.
* Talks to all our tools (Slack, Github, Linear, GSuite, Clickhouse, Gong, etc.)
* Lets you pick any model. Especially useful this week!
* Can spin up a local version of all of Sierra to test its work.
* Is accessible over mobile, Slack, Github, and Web and is collaborative.
@neilrahilly and team cooked on this. In this post, they share lessons learned from building and scaling Pinecone to the whole company.
Pilots use checklists.
Surgeons use checklists.
Now my niece does too.
She has reached the age of how-to questions.
So I built her https://t.co/jJt7tMg8ec. You tell it what you want to do, what your limits are, and what you already have. It gives you an actionable checklist.
Whenever I see this, I am confused, how does this solve gap?
Make 50% seats reserved and see if they get filled?
Gender specific events donโt solve anything, just increase the divide.
We noticed a gap and We are trying to do something about it.
AI & Women is our first women only event.
A panel + A hands-on and cobuild workshop.
A room designed so nobody has to think twice before walking in.
5th July. Bengaluru.
Food and drinks on the house.
Tag someone you should feel part of this.
https://t.co/PQRE8T6MsN
I am seeing a lot of startups trying to be context or connector layer for different tools on top of Claude/Codex.
I don't think it is going to be an easy fight, Claude and OpenAI are gonna be the layer for context, connectors, memory.
India had a semi conductor fab factory in Punjab and it got burnt in a fire and was never rebuilt, and we were earlier than most countries.
Punjab with a semiconductor centre would have been very different.
Should we feel proud that Tata worked so hard and invested so much in a watch making factory in 1984, instead of doing something revolutionary and investing in semiconductors?
They had the capital, the govt backing and countries like Japan could have helped if we had asked them nicely.
But They decided to play it safe and launch watches instead, a tech that has been around forever?
Considering that TSMC was founded in 1987 and Koreans too were taking baby steps, it is a nice what if scenario, where our semiconductor future could have been very different had Tata decided to take that direction instead of making watches.
The playbook to launching your startup:
Monaco launched less than 4 months ago. I work with our customers every day planning their launches. This is the high-level playbook we follow: