The product is provided by TextForAgents LLC to operators under the operator's own account; the operator is responsible for the sites it asks the range to mirror, the permitted-effect set it declares per workflow, and the live actions its agents take on the basis of a promotion receipt.
The rehearsal service is as proven in the lab: a stateful mirror of a target site (cooperating manifest+state clone, or non-cooperating observable-surface capture), a rehearsal run scored on the sandbox state diff against the permitted-effect set (not on task completion alone), and an HMAC-signed promotion receipt (agent, site, task class, mirror version, drift bound, score) whose validity is fidelity-bound on STRUCTURAL drift. For non-cooperating mirrors the score degrades honestly to the submission surface, and the receipt states that weaker shape — it never presents a submission-surface score as a deep state-diff score.
A promotion receipt is a clearance credential within its scope (agent × site × task class), not a guarantee of live outcomes: it expires, it invalidates when structural drift exceeds its bound, and reuse inside scope is by design (clearance, not a single-use token).
The product does not claim JS-rendered-site fidelity at launch on this record: the lab proof is HTML-surface capture; JS-rendered capture cost and fidelity are packet items, and no JS-heavy-site claim is made until they are measured. A mirror flagged js_heavy is not charged the per-rehearsal tier.
Mirroring is for rehearsal of workflows the operator is authorized to run on the target site; the operator warrants that authorization. The range does not rehearse against, or help evade controls on, sites the operator has no right to automate.
Pricing: Per-rehearsal API $1.50/rehearsal · Operator $29/mo per operator · Fleet $99/mo per operator. One rehearsal free, one time per operator; there is no perpetual free tier. Liability and warranty terms are under the company's standard terms; nothing here expands TextForAgents LLC's liability beyond those standard terms. Support: support@textforagents.com.