11/10/2025
Building conversational AI into your app? Start here.
Natural language interfaces are changing how we interact with software—making tools faster, more flexible, and easier to use across platforms. But building a reliable, intuitive experience takes more than just plugging in an LLM.
Over a 3-part blog series, Sujan Kapadia, Chief AI Officer, shares how to go from basic command parsing to a conversational chat interface, covering architecture, prompt design, and the human experience of using AI in real tools.
Here's a quick recap of what you'll learn:
Part 1: From Natural Language to Action
How to translate user input into structured commands using LLMs and JSON—no heavy frameworks needed.
https://ow.ly/5rXc50XncUK
Part 2: Making Chat Feel Human
How to add conversation history and context-awareness to your assistant—plus trade-offs in prompt design and model performance.
https://ow.ly/V7qy50XncUO
Part 3: Natural Language vs Graphical UX
Where chat shines, where rich UIs still win, and how to combine both for a better experience.
https://ow.ly/vkF150XncUL
Whether you're experimenting with agents or building full-featured assistants, this series offers hands-on insight from the engineering trenches.
What We’re Building When I recently paired with Claude Code to build a text-based to-do app (code available on Github, disclaimer: mostly generated by Claude), I wanted to add a simple natural language interface. In this post, we’ll build that feature using TypeScript, Node, and an OpenAI model,...