Concept
Permission Fatigue
Because at volume, approving stops being a decision. Anthropic measured that Claude Code users approve 93% of permission prompts and shipped classifiers to cut permission fatigue (Anthropic Engineering, 25 March 2026); a separate 40,000-run study by Scale X found people missed 1 in 3 genuine threats while clicking through. That leaves two bad defaults — approve everything by hand and get nothing done, or skip permissions entirely and hope. Policy-based gating is the third: a deterministic control plane answers on the common path, and a named person is pulled in only when the rules require one, so the approvals someone does see are rare enough to deserve attention.
Why doesn't approving every AI agent action work?
Because at volume, approving stops being a decision. Anthropic measured that Claude Code users approve 93% of permission prompts and shipped classifiers to cut permission fatigue (Anthropic Engineering, 25 March 2026); a separate 40,000-run study by Scale X found people missed 1 in 3 genuine threats while clicking through. That leaves two bad defaults — approve everything by hand and get nothing done, or skip permissions entirely and hope. Policy-based gating is the third: a deterministic control plane answers on the common path, and a named person is pulled in only when the rules require one, so the approvals someone does see are rare enough to deserve attention.
3 patterns answer this
Control MCP egress
An agent calls a tool that reaches a network destination, uploads a file, or posts data to a third party.
Its gate and signals
Gate agent memory and retrieval
An agent retrieves documents into context, or writes what it learned into durable memory.
Its gate and signals
Prevent destructive production changes
A command, script, or agent drops a table, deletes a bucket, or tears down infrastructure.
1 policy pack
From this term to a governed action
- Control MCP egressThe recurring action behind this term.
- Browse the policy packsThe bundles the evaluator ships, rule by rule.
- Try to break it in the sandboxA real signed verdict, no account.
- Deploy on your surfaceAvailable on 6 platforms today.
- Verify the proof yourselfCheck the signature without trusting us.
- Start NowMeasure on your traffic before enforcing.
Where this fits
Decionis is the deterministic decision layer between intent and execution. This concept is one way in; the architecture behind it is the same in every case.