Evaluations and notes on AI agents across real-world use cases.

Research

  1. By Arushi Gandhi

    Dont vibe code your software clones

    Why high-fidelity software replicas demand more than surface-level generation.

  2. By Arushi Gandhi

    Evaluating Sovereign AI

    Testing Sarvam models on multilingual ecommerce support tasks with tools, policy constraints, and backend state.

  3. By Abhishek Eswaran

    Tech Support Environment

    The Tham Luang Cave

  4. By Arushi Gandhi

    SalesforceBench

    Can agents actually work inside a simulated Salesforce org?

  5. By Abhishek Eswaran

    Editing is Hard

    Can LLMs edit PPTX reliably?