How to Help Your Agent Build Situational Awareness by Building a Single "Active Projects Tracker"

Stop re-explaining projects

Workflow

Give each ongoing project a short status file and a single index your agent checks first, so a new conversation opens knowing which project, which people, and which stage.

A Cookbook recipe run as a workflow. It replaces the re-briefing at the top of every conversation with one small tracker the agent reads before it answers.

  • Begins by asking the agent what you actually use it for, by category, so the projects that need files are the ones that keep recurring.
  • Writes one status file per project holding only what is established — current stage, the usual ask, who is involved — instead of a full project archive.
  • Builds the index last, linking out to each file rather than repeating their contents, so there is one place the agent checks first.
  • Moves the tracker out of the agent's private memory and into your Fulcra account, with the memory copy kept as a pointer, so every agent sees the same source of truth.

Connect your agent first at fulcradynamics.com/connect/claude or fulcradynamics.com/connect/chatgpt, or point any MCP-capable agent at https://mcp.fulcradynamics.com/mcp. Then open the write-up for the full walkthrough.

Paste this to your agent

Help me stop re-explaining my ongoing projects at the start of every conversation. Start now, with no setup: ask me what I actually bring to you most often, by category, then draft one short status file per project and an index that points at them. For the version other agents can read too, read https://docs.fulcradynamics.com/agent-get-started.txt and connect to Fulcra, so the tracker lives in my account rather than only in your memory.

View the sourceAll skills and workflows