The Decision Quality Layer

An independent second opinion on your agent's plan — before you commit.

Identity, authorization and security ask if an action is allowed, safe, and from a real user. None of them asks the last question: is the plan your agent came up with actually a good one? That's the layer we're building.

Open app — pricing Trial & packs

Live API at dql.thoughtproof.ai. Card packs on app, or pay-per-call with USDC (x402) on Base — same endpoint, no prepaid key required for agents.

Five checks · every action · any agent

01
Intent match
Does the plan actually solve the request, or is it a plausible-sounding detour?
02
Consequence awareness
Does the plan recognize every irreversible side effect before it happens?
03
Constraint compliance
Does it stay within your stated bounds — budget, time, allow/deny lists?
04
Plausibility
Are the numbers, prices, times and facts within a reasonable range?
05
Alternative existence
Is there an obviously better option the agent missed?

Who it's for

You use an agent browser — Perplexity Comet, Genspark, or Chrome/Edge with agent mode. The extension pauses the action and shows you the verdict before you commit.
You use a desktop / CLI MCP host — Cursor, Claude Desktop, or another host with stdio MCP support (Node.js 18+). Add thoughtproof-mcp, set DQL_API_KEY, and call verify_decision before the action. execute is true only on ALLOW. Auto-route can hit Sentinel; mode=sentinel needs SENTINEL_API_KEY.
You're a developer — the Sentinel API is already live at sentinel.thoughtproof.ai. Integrate directly.