How to design safe tool permissions for AI agents in production apps

UpdatedAugust 31, 2026

The model is not the authority

An AI agent can choose a tool, fill in arguments, and explain what it intends to do. None of those things make it authorized to perform the action.

That distinction matters as soon as an agent can access customer records, create invoices, update a project, send a message, or call an external service. A helpful demo often gives the model a broad function such as runAction and trusts the model to decide when it is appropriate. A production application cannot make that the security boundary.

Treat the model as an untrusted decision-maker inside a user session. The application must authenticate the user, check authorization, validate the tool arguments, enforce limits, and record the outcome independently of the model’s reasoning.

This is an excerpt. Read the full post at otf-kit.dev/blog/safe-ai-agent-tool-permissions — full-stack kits your AI coding agent can actually ship to production. Browse the kits →

#ai-tools #agents #architecture

Comments

Join the discussion

No comments yet. Be the first to comment.

More from this blog

LLM observability for production apps: what to trace, measure, and fix

LLM observability starts with the whole request LLM observability is the practice of connecting a user request to the model calls, retrieval steps, tool calls, latency, cost, and final outcome that fo

Aug 31, 20261 min read

LLM observability for production apps: what to trace, measure, and fix

A practical LLM evaluation loop for AI features that need to ship

Prompt testing is not an evaluation strategy An AI feature can look excellent in a demo and still fail the first week of real use. A user asks a question in a different way, a retrieved document is in

Aug 30, 20261 min read

A practical LLM evaluation loop for AI features that need to ship

An AI app security checklist for builders moving from demo to production

A production AI app needs more than a safe-looking system prompt. Before you ship, you need a boundary around every input, model call, tool invocation, database write, and user-visible output. This AI

Aug 30, 20261 min read

An AI app security checklist for builders moving from demo to production

Cursor prompts that keep agent sessions focused from first edit to final check

Cursor can make a small feature feel like a conversation: describe the change, watch files move, answer a question, and review the result. That workflow is useful until the task becomes larger than on

Aug 30, 20261 min read

Cursor prompts that keep agent sessions focused from first edit to final check

OTF — kits your AI coding agent can ship to production

493 posts

Engineering notes on shipping production apps with AI coding tools — Claude Code, Cursor, Codex, Lovable, Bolt — and the stack underneath: React Native, Expo, Next.js, Supabase. Honest takes on what works, what breaks, and the full-stack kits that get you to production faster. By OTF.

Command Palette

The model is not the authority

Comments

More from this blog