Agentic chat
Agentic chat is an AI workspace that combines document search, memory, tools, and research flows so it can answer with better context and lower repeat cost.
Agentic chat was built as an AI workspace that can choose the right path for each request instead of treating every prompt the same way. It supports web search, reading URLs, working with documents, Google Workspace actions, and deeper research flows.
Agentic chat was built as an AI workspace that can choose the right path for each request instead of treating every prompt the same way. It supports web search, reading URLs, working with documents, Google Workspace actions, and deeper research flows.
The system combines document search, reranking, memory, caching, streaming chat, file uploads, and conversation branching. In practice, that helps it answer with better context and lowers repeat model costs.
How It Was Built
The main technical choices behind the product, from system design to the parts that make it work day to day.
- Built a routing layer that decides whether a request should use memory, documents, images, tools, or a mix of them.
- Added document search with ingestion, chunking, embeddings, semantic search, reranking, and caching so similar requests do not always start from zero.
- Built a routing layer that decides whether a request should use memory, documents, images, tools, or a mix of them.
- Added document search with ingestion, chunking, embeddings, semantic search, reranking, and caching so similar requests do not always start from zero.
- Used LangGraph for deeper research flows with planning, task splitting, result gathering, and final answer building.
- Added URL reading, web search, Google Workspace actions, sharing, exports, and conversation branching so the product works more like a workspace than a simple chatbot.