RuleGuard

Make your phone's AI agents ask first and follow your rules

Problem

Personal agent apps on phones (Muse, Grok Bot, Dots, Instinct) assume intent and act the moment they get tools, connectors, and data access, without asking the user or respecting stated rules, values, and goals. Users explicitly want agents to align with their own constraints, but no product exposes that boundary today.

Solution

A local rule layer between the agent and its tools: users write in natural language plus structured conditions when it must ask, what is always forbidden, and daily budgets. The layer intercepts tool calls, surfaces a confirmation card on a match, and lets the user allow once or whitelist permanently.

Users

Power users running multiple phone AI agents who care about privacy and automation boundaries

MVP

A rule editor on iOS/Android; 3–5 built-in templates (spend cap, contact whitelist, time-of-day bans); interception via Shortcuts or agent webhooks; local log of every block and allow; export rules as JSON

Revenue

Freemium: three free rules, unlimited rules and multi-agent support at $4–6/month; one-time enterprise template packs

Why now

Phone AI agents exploded this year but none ship a consent or alignment layer, and a cross-agent rule middleware is small enough for one developer to own before platforms fill the gap