anandchowdhary
Joined 12 years ago
Karma
333
Submissions
128
Member since
Oct 21
Recent submissions
Comment · 1 month ago
Slack does the same thing:
> Get started using the Slack MCP server by setting up a connection with an available partner
https://slack.com/help/articles/48855576908307-Guide-to-Mode...
Comment · 7 months ago
Sycamore | Palo Alto | Full-time | https://sycamore.so
Founded by Sri Viswanath, former CTO of Atlassian, Sycamore enables organizations to build, deploy, and orchestrate AI agents with security, governance, and human oversight. The platform captures and compounds organizational intelligence over time, enabling systems that continuously improve.
We recently raised a $65M seed from Coatue & Lightspeed.
We're hiring across several roles:
- Applied AI Engineer: Deploy AI solutions with customers
- Product Engineer: Build user-facing product experiences
- Forward Deployment Engineer: Deploy AI solutions directly with customers
- Data Systems Engineer: Build pipelines and power data-driven products
- Staff Software Engineer: Lead core system architecture
- Cloud Platform Engineer: Run cloud infrastructure and developer systems
- Security Engineer: Secure systems and data
- Research Scientist: Advance the science of agentic systems
- Engineering Intern: Build and ship real features alongside the team
More info and apply: https://sycamore.so/careers
Comment · 9 months ago
I’m at https://anandchowdhary.com - it’s all open source!
Comment · 11 months ago
Nah - as you'll see from my work from a pre-coding agents age, I like emoji :)
Here are receipts some from 2020: - https://github.com/AnandChowdhary/bsc-thesis - https://github.com/AnandChowdhary/slack-netlify-trigger - https://github.com/AnandChowdhary/analytics-icons
Comment · 11 months ago
It does `claude -p "This is the prompt" --dangerously-skip-permissions --output-format json`
Comment · 11 months ago
I don't know if this is true.
For example, you can spend a few hours writing a really good set of initial tests that cover 10% of your codebase, and another few hours with an AGENTS.md that gives the LLM enough context about the rest of the codebase. But after that, there's a free* lunch because the agent can write all the other tests for you using that initial set and the context.
This also works with "here's how I created the Slack API integration, please create the Teams integration now" because it has enough to learn from, so that's free* too. This kind of pattern recognition means that prompting is O(1) but the model can do O(n) from that (I know, terrible analogy).
*Also literally becomes free as the cost of tokens approaches zero
Comment · 11 months ago
For letting me know! Would you like to create a PR? Otherwise I'll add you as a Co-Authored-By!
Comment · 11 months ago
Indeed the case - luckily my codebase had some tests already and a pretty decent CLAUDE.md file so I got results I’m happy with.
Comment · 11 months ago
No, you're right. It was a pretty collaborative effort with me and Claude!
Comment · 11 months ago
It sends a flag that dangerously allows Claude to just do whatever it wants and only give us the final answer. It doesn't do the back-and-forth or ask questions.
Comment · 2 years ago
maybe I do... we'd never know!
He is currently part of the founding team of Sycamore, the trusted agent operating system for the enterprise.
Previously, he built and sold FirstQuadrant, an AI sales platform funded by Y Combinator; rent-to-own furniture with interior design startup Pabio, and accessibility technology company Oswald Labs.
More on https://anandchowdhary.com
Social: @AnandChowdhary
YC verification: https://www.ycombinator.com/verify/6nqqqo3s7fjgs0b4