Write in my voice
well_write_in_my_voiceWrite an email in the person's voice from a brief. Call this before drafting any email wording in the person's voice. It returns only the subject, body and writing metadata (guidelines_used, style_training). style_training says what happened to learning the person's style. On "started", add one short line after the email: Well is learning their style from their sent emails, and later drafts will sound more like them. On "needs_gmail", you may add one short line asking them to connect Gmail so Well can learn how they write. On "running", "recently_trained" or null, say nothing about it. When the token authorizes one workspace, call this directly — no workspace call is needed first. When it authorizes several, this read will not guess which one you mean: pass workspace_id on the call.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| brief | Yes | The email's purpose and key points, in up to 2,000 characters. | |
| language | No | The email language, French or English, when known. | |
| recipients | Yes | Email recipients; pass an empty array when there are none, with no more than 50 recipients. | |
| workspace_id | No | Target workspace. Omit when the token authorizes one workspace. Required when it authorizes several: this read reports one workspace's own figures and will not choose which. | |
| conversation_id | No | The conversation id returned by the previous Well result, in its meta under well/conversation_id, in its structuredContent, or in its JSON text block. Pass it back on every call in the same conversation, including a call a card makes, so the chosen workspace and the earlier answers still apply. It decides the conversation on its own: nothing the host states about the session replaces it. Omit it only on the first call of a conversation. | |
| workspace_scope | No | Restrict this call to the family: the token's primary workspace plus the company workspaces under it that you are a member of. Unrelated authorized workspaces drop out of the read; row reads merge across the family, while a per-workspace figure still reports exactly one workspace. |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| body | Yes | The email body, empty when writing failed. | |
| error | Yes | The refusal or writing error, or null on success. | |
| subject | Yes | The email subject, empty when writing failed. | |
| success | Yes | Whether the email was written. | |
| language | Yes | The language of the email. | |
| cohort_id | Yes | The opaque style cohort id used, or null. | |
| style_training | Yes | Whether Well started learning the person's style for later drafts, or null when there is nothing to say. | |
| conversation_id | No | The conversation this result belongs to. Pass it back as the conversation_id argument on every later Well call in the same conversation. | |
| guidelines_used | Yes | Whether the person's style guidelines informed the email. | |
| newly_connected | No | Tools that connected to this workspace since the last result and that no session was told about yet, oldest first. Present only when at least one tool is new. The connected-line rule says when to tell an entry; when it does, one line per entry, in the person's language: "<name> is connected.". Never fold several entries into one sentence. Each entry comes back once, on one result only: never repeat its line later. | |
| resolved_workspace | No | The workspace that answered, when the caller named none and the token authorizes several. | |
| conversation_id_note | No | Present only when the server opened a fresh lane, stating that no choice recorded earlier was read. | |
| conversation_id_source | No | Where the conversation id came from: the host's own request meta, the caller's argument, or a fresh lane the server opened. |