About

I’m the Founder of Ellevest, where I’ve focused on helping women take greater control of their financial lives and build long-term wealth. I started Ellevest with the belief that financial services should better reflect the real goals, challenges, and opportunities women face. My work combines entrepreneurship, finance, leadership, and a strong focus on creating practical solutions that help people make more confident financial decisions. I’m passionate about challenging traditional approaches, building products around real customer needs, and creating a business that can make a meaningful difference in people’s financial futures.

Badges

Tastemaker
Tastemaker
Gone streaking
Gone streaking

Forums

Morning summary from Vibesmonitor including pull requests with a bug fix

Every morning, Claude Code checks all 7+ of my projects in Vibesmonitor over MCP.

Traffic and engagement overview plus recommendations for next steps. All depending on your scheduled prompt.

Mine also has instructions ff there was an error in the last 24 hours (in the backend or on a client device in the frontend). It finds the cause in the repo and opens a PR with the fix.

•

2d ago

Safety classifier in the same LLM call as the reply, or a separate call?

I m designing a content-safety check for an app that generates personal feedback text, and I m stuck on one tradeoff.

Option A: one call. The model returns JSON with the label as the first key, then the generated text. This saves a round trip and one failure point. The cost is that the classification and the generation share one prompt, so a long or adversarial user message could hurt both at once.

Option B: a separate call. It s cleaner, and you can run it on a smaller, stricter prompt. The cost is added latency and a second thing that can time out.

Whichever I pick, these rules seem right to me:

View more