Design the Permission Approval UX
Design approval prompts users actually read: diffs, risk framing, scoped grants, and pacing that prevents approval fatigue.
The Route
0/4 verifiedAudit the current approval moments
Count them, read them, feel the fatigue.
Rebuild the prompt content
Decisions need diffs, commands, and consequences - inline.
Make friction proportional to risk
Routine should be quick; dangerous should be impossible to miss.
Add scoped grants and measure the win
Fewer, better questions - proven with numbers.
Context Pack
Paste this first. It briefs the AI on requirements, constraints, and the Definition of Done before your first build prompt.
Paste this into your AI builder first. It teaches the AI what you want before you give it the build prompt.
Related routes
More Harness Engineering flows that share ground with this one.
Hook a Permission Layer onto Dangerous Tools
Intercept dangerous tool calls with a hook layer: pattern rules, approval gates, and blocks that the model cannot talk its way past.
+1 more steps to Done
Best forbuilders who have shipped a basic app before
Verification Loops: Never Trust an Unrun Edit
Wire verification into your agent so every edit is checked by machines - syntax, tests, behavior - before it counts as done.
+1 more steps to Done
Best forbuilders who have shipped a basic app before
Assemble Tool Prompts Dynamically per Environment
Stop shipping one static mega-prompt: generate tool prompts from environment conditions, inject blocks only when features are on, and dedupe config to save tokens.
+1 more steps to Done
Best forproduction-grade builds with strict verification