Arjun Kashyap I write about AI, software engineering, some product thinking, and the shift toward agentic systems. This is where I publish essays on ho...
There are a lot of capable LLMs: OpenAI, Anthropic, Gemini, Kimi, Meta, and many others. Most of them can generate good outputs and call tools reliably. But they don't behave the same way. A prompt that works well with one model may fail with another. One model might be great at tool calling but bad at structured output. Another might follow complex instructions well but struggle with a specific…
Whitepaper Github repo Agentic SaaS changes the shape of software. Traditional SaaS is mostly request-response: a user acts, the system replies, and the interaction ends. In agentic SaaS, work persists across time. Software begins to monitor, decide, retry, coordinate tools, and escalate on the user’s behalf. As argued in The Future of SaaS Is Agentic , the interface does not disappear, but it…
This essay came together while I was thinking through interfaces, value, and surfaces in Bruges. If you haven't read my previous essay, read it here: The Future of SaaS is Agentic TL;DR: Agentic SaaS does not need a brand-new interface for every workflow. Operations can happen in surfaces people already use like email, chat, or messaging, while insights, control, and security need purpose-built…
TL;DR: The future of SaaS is agentic, but agentic SaaS is not just a chatbot layered on top of APIs and a dashboard. Traditional SaaS was built for users to operate software manually; agentic SaaS shifts that burden to software that can act on behalf of users. That changes both the interface and the architecture: the UI remains, but becomes a layer for intent, supervision, and review, while the…