Skip to content
Sayam Jain
CV

Blog

What I learn while building: build logs, postmortems, and notes on shipping AI features that hold up.

All posts

  1. Evals before vibes

    An eval is a fixed set of inputs and expected outcomes that you can rerun after every prompt or model change. I compare two prompts on 24 synthetic WhatsApp cases, grade them in code, and check an AI judge against labels I wrote by hand.

    ai · evals · llm · testing

  2. Not every AI feature needs an agent

    Use a workflow when you already know the steps. Let code handle selection, validation and execution, and let the model handle the parts that need language understanding. Use an agent when the next step genuinely depends on what it discovers.

    ai · agents · llm · architecture

  3. Giving my portfolio its own address

    I moved my portfolio to sayamjain.com by connecting the domain to Vercel, choosing one canonical address and redirecting the old URL. I also verified the new domain in Google Search Console, submitted my sitemap and started a Change of Address.

    seo · next.js · vercel

Have an interesting product, engineering challenge, or collaboration in mind?