Intent Cloak: query-intent privacy for agents

Intent Cloak: query-intent privacy for agents — by TextForAgents LLC. Every query your agent sends is a disclosure: what its principal is buying, building, or investigating, handed to a counterparty who can price against it, log it for a competitor, or answer differently because of who is asking. The cloak treats intent as a protected asset at query time. A sensitive task's information need is decomposed into constructed subneed queries placed across independent providers under a hard threshold — no provider's share of the task's sensitive entities exceeds 0.5, and no provider ever receives both the goal and the target — with answers reassembled client-side by per-field quality selection; if no legal placement exists, the cloak refuses to send rather than leaking. A synthetic-task probe (never your real query — probing with it would itself be the leak) measures whether a provider prices differently for revealed intent and raises the decoy ratio automatically when it does. Every task returns a signed exposure receipt: a record of what was NOT disclosed, per provider, with the real-vs-decoy spend split stated honestly.

Stated plainly: whether real providers exploit intent today is unmeasured — the $9 exposure audit is the canary that answers it on your own providers. The threshold is a bound on content reconstructability per provider; it is not a guarantee against account-level linkability (a shared authenticated account links queries regardless of content). Deterministic normalization is proven on templated/graded query shapes. Total task spend is higher cloaked — decoys and fragmentation multiply your own underlying provider queries (lab: $17.79 vs $3.90 in double units), disclosed per task on the receipt. The input is a task decomposed into constructed subneed queries — this is not a tool that divides a keyword search query; the default provider posture prefers tool/data API providers over search-engine providers.

Cloak API $0.02/cloaked query (x402) · Operator $19/mo per operator (to 2,000 cloaked queries/mo, deterministic normalization) · Exposure audit $9/task-set. First 100 cloaked queries free, one time per operator.

Start (self-serve, no operator credentials)

POST /register with {"name": ..., "payer_wallet": ...} — you get a one-time claim token. Machine-readable documentation: the docs page (/docs), the OpenAPI spec (/openapi.json) or /llms.txt.
POST /trial/claim with {"claim_token": ...} — you get your API token (Bearer) and the one-time trial grant: the first 100 cloaked queries free, once per operator.
POST /cloak with {"task_id": "T01"} or a full task object — answers reassembled by per-field quality selection plus the signed exposure receipt. POST /cloak/query cloaks one constructed subneed query. POST /audit runs the $9 exposure audit over a task-set.
POST /verify checks any signed receipt's HMAC signature; GET /verify-key lists the accepted receipt-key fingerprints.
POST /subscribe takes an Operator pass ($19/mo, 2,000 cloaked queries/mo included).

Also available as an MCP tool surface at POST /mcp (tools: cloak_run, exposure_receipt, verify_receipt) with the same billing. Terms: /terms · Privacy: /privacy · Support: support@textforagents.com