Pranav Dhoolia·Feb 24How To Cut Your API Spend by 61% Without Removing a Single Tool8 Meetings vs. 24 Meetings: The Only Change Was Adding 4 Constraints
Pranav Dhoolia·Feb 3How to Tell If Your AI Agent Costs More Than the Team It ReplacedOn paper, it was perfect. But within a month, they were babysitting a piece of software!
Pranav Dhoolia·Feb 2Why an AI Agent Opened 7 Browser Tabs to Answer This One-Line QuestionIt Took Just 500 Made-up Tickets to Find What 50,000 Real Ones Couldn’t
InHeurisLabsbyPranav Dhoolia·Feb 7, 2025Building a Universal Assistant to connect with any APIIn our previous blog, we built a universal assistant that could use Claude’s Model Context Protocol (MCP) to interface with different…A response icon4A response icon4
Pranav Dhoolia·Jan 28, 2025Creating an embeddable chatbotIn these demos, I create and deploy a RAG (Retrieval Augmented Generation) based chatbot for Question Answering over website content using…
InHeurisLabsbyPranav Dhoolia·Jan 20, 2025Building our own Universal Assistant with LangGraph and MCPModel Context Protocol (MCP) is an open protocol that enables seamless integration between LLM applications and external data sources and…A response icon1A response icon1
InHeurisLabsbyPranav Dhoolia·Jan 17, 2025Building & Deploying an Agent with LangGraphThis blog is part of a mini-series where I create and deploy a RAG (Retrieval Augmented Generation) based chatbot for Question Answering…
InHeurisLabsbyPranav Dhoolia·Jun 24, 2024Making a ChatGPT-like UI for your application in 15 minutesLet us create a Generic Chat UI that we can use with ANY LLM solution we create in future!A response icon1A response icon1
InHeurisLabsbyPranav Dhoolia·Jun 24, 2024Adding ChatGPT-Like functionality to MacOS Spotlight SearchAdding ChatGPT like search system to the MacOS filesystem with Spotlight, Ollama, and LangChain
InHeurisLabsbyPranav Dhoolia·Jan 28, 2024Build and Deploy GenAI Solutions LocallyBust the myth that AI is only for tech giants. The process of setting up and running sophisticated AI models at home is surprisingly…
