Aurais Writing Editor
Critique-only · never rewrites your prose
Paste a draft + your audience and tone. Get structural, sentence-level, and tone critique — the bot flags issues, you do the editing.
What it does — and doesn't
- Structural issues: pacing, ordering, paragraph flow
- Sentence-level: clarity, tightening, repetition
- Tone audit against your declared target
- Every issue cites a verbatim excerpt from your draft
- Never produces a rewritten version — your voice stays yours
Critique, not rewrite
The bot surfaces problems; you solve them. That's a deliberate boundary. An LLM that rewrites your prose launders your voice into its voice. This one tells you what to look at — structure, a sentence that's buried, a tone that drifts — and leaves the actual editing to you. Every suggestion cites a verbatim excerpt from your draft (or says "paraphrased" if it can't). Your authorship stays yours.
- car_id
- car-aurais-writing-editor-3ceeac804688
- agent_id
- aurais-writing-editor@0.1.0
- org_id
- vorion-llc
- deployment_id
- dpl_4TWfrDX9SjZyvKEYtF8BWBnzY2WS
- tier
- T3 · BLACK_BOX
- trust_ceiling
- 600
- max_earnable_tier
- T4
- parent_hash
- (root — AgentAnchor A3I)
- context_hash
- sha256:4b9168689fa063fa8…
- capabilities
- 7 declared
- a3i_cert
- registry/writing-editor →
7 capabilities
- · tool:structural_critique
- · tool:sentence_critique
- · tool:tone_audit
- · data:read:user:draft-transient
- · data:write:none
- · safety:never_rewrites_prose
- · api:post:api.anthropic.com
What “offline-attested” means: The CAR ID and capabilities are derived deterministically from the signed manifest and emitted in every proof chain — identity is verifiable. Live trust-score progression, lifecycle state transitions, and pre-action gating require the Vorion registry backend, which is in roadmap, not shipped. Tier 3 is the published operating envelope; the bot cannot silently exceed it.
Pricing
Free, unlimited at BYOK tier · $9/mo hosted with version compare