Sharing a "RAM" with my agent: a stack-based memory keeps revisions on goal

alfcnz · x · 2026-11-18

alfcnz shares his personal workflow of sharing a "RAM" between himself and his AI agent. They use a stack structure: the ultimate goal sits at the bottom of the stack, so revision detours (formula tweaks, figure redraws) still converge on the original target. The screenshot shows the live stack: PyTorch chapter revision items, pending decisions like whether to use torch.setgradenabled(False), and parked items. He notes the more he builds his own zero-friction tooling around this, the better it works.

Related event: Dev Shares Stack-Based Shared RAM Workflow for Human-Agent Collaboration(2 posts)→

Original post →

More from coding & agent

coding & agent channel →