An Agentic Doc Repo Makes Documentation Retrievable
Instead of living like normal docs in Notion or Confluence, the repo is designed so agents can actually retrieve what they need.
The Problem
Traditional documentation systems store information, but they do not naturally make it easy for agents to find and use the right piece at the right time.
What Was Built
An experimental documentation concept where backend content is vectorized and stored in a way that makes it much easier for an agent to retrieve relevant information than with a standard docs setup.
Where AI Sits in the Workflow
AI is the reason the repository is structured this way in the first place: the docs are being shaped for retrieval, not just human browsing. A person still decides what belongs in the docs and updates the repo when the operating model changes.
Tools Used
The Result
Less time is spent hunting for the right document because the repository is built for agent retrieval from the start.
Key Insight
The future of documentation is not just better writing. It is better retrieval.
Want this built for your business?
Want a workflow like this in your business? Talk to Dovid.
Start the conversationMore Examples
One Shared Skills Folder Made Every Agent Portable
Instead of letting every agent create its own skills directory, one shared folder and a symlink setup made skills portable across apps.
A Vectorized Memory Layer Gives Agents Shared Context
Important work context can be written once, stored in memory, and read back by agents through an MCP server later.
A Daily Agent Turns Conversations Into Memory
Every day, a scheduled agent reviews Codex conversations, identifies what work is happening, and turns that into usable memory automatically.