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

Comments URL: https://news.ycombinator.com/item?id=46971424

Points: 2

# Comments: 0

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

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

This avoids the typical stateless one-shot pattern of current coding agents and enables multi-step changes without losing intermediate reasoning, test failures, or partial progress.

The tool is useful for tasks that require many small, serial modifications: increasing test coverage, large refactors, dependency upgrades guided by release notes, or framework migrations.

Blog post about this: https://anandchowdhary.com/blog/2025/running-claude-code-in-...

Comments URL: https://news.ycombinator.com/item?id=45938517

Points: 170

# Comments: 62

  - yearly themes and quarterly personal OKRs
  - my live location (yes, really)
  - books I read, music I listen to
  - biomarkers, health and fitness data, sleep records

(I don’t work at GitHub but was quoted in the article).