Menu

Approval gates for AI agents: how Sahkarmi decides what a coworker may do
📰

Approval gates for AI agents: how Sahkarmi decides what a coworker may do

DEV Community: security·Dhrubojyoti Gangopadhyay·13 days ago
#fClogdLb
#devtosecurity#devto#dev#agent#policy
Reading 0:00
15s threshold

The permission model behind Sahkarmi: sixteen action categories, six that can never be auto-approved, time-boxed delegated authority, and a browser take-over flow that keeps passwords away from the model.

Most agent demos answer one question well: what did the model say? Operations work asks a harder one: what did the system actually do, and who allowed it? Sahkarmi is a desktop platform where AI coworkers browse, file, draft and report on a user's own Windows machine. This article is about the part of it I spent the most design time on, which is the part that stops the agent.

The failure we are designing against

An agent with a browser and a shell can pay an invoice, message a customer, submit a government form, publish a page or delete a folder. Each of those is a one-way door. A chat assistant that hallucinates wastes a minute; an agent that hallucinates a bank transfer costs real money and trust. So the first design rule in Sahkarmi is blunt:

The model proposes. A human approves.…

Continue reading — create a free account

Join HashtagPLUS to read full articles, follow hashtags, vote, and join the conversation.