Use when a researched prospect row needs its opening message by email, social, phone, or short public post.
The English summary is being prepared. Showing the original description.
Run score Not tested
See how to installReview the instructions the agent will receive before you install.
Use this when a researched row needs its opening message. If the row has not been enriched yet, stop and route it to research before writing a word.
The target-list row with its hook and sources, the user's voice sample, the ask, and the proof they are allowed to cite.
Write from the row only:
Match the user's voice sample; if there is none, keep it plain and under 100 words for email, under 60 words for a social message, under 280 characters for a short public post, and under 30 seconds spoken for phone with a voicemail fallback line.
Email carries a subject in sentence case, four to five words; a short question naming the trigger is fine. Never use Re:/Fwd:, colons, or ALL CAPS in a subject.
Never invent a fact. No assumed funding, no guessed headcount, no quote they never said, no "I noticed you" without the link underneath. Proof points come only from what the user gave you.
Skip the banned openers: no "hope you're well", no "just bumping", no "pick your brain", no flattery without a fact behind it. No emoji and no exclamation points in any draft.
Show the draft in chat with the source links under it and one line on what you left out. Mark the row drafted with today's date in drafted_on, and save. The draft is unsent, so log no outreach touch: that entry goes in only after the user confirms the send, or the row reads as contacted when nobody was.
Output: the unsent first-touch draft with sources, plus the row update.
A thin row with no hook means you say so and offer the two weakest lines to fix by research, or a plain intro draft they approve as-is. A channel you cannot shape for means you ask which of the four to use.
Approval gate: drafts only, nothing sends without your explicit yes.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Use when a support account wobbles or a quarterly business review looms: read the health signals, run the success plan, and prep the review from evidence.
The English summary is being prepared. Showing the original description.
Reconcile accounts by comparing GL balances to subledgers, bank statements, or third-party data. Use when performing bank reconciliations, GL-to-subledger recs, intercompany reconciliations, or identifying and categorizing reconciling items.
The English summary is being prepared. Showing the original description.
Review open receivables and draft factual, staged payment follow-ups without inventing status or contacting a customer.
The English summary is being prepared. Showing the original description.
Write ad variants that each test one idea, within platform limits and supported claims.
The English summary is being prepared. Showing the original description.
Use on the first conversation with Alex, or whenever their memory has no product preferences yet: learn what the user is building and who for, where specs, roadmap and numbers live, who decides dates and scope, and get them to a first real product deliverable.
The English summary is being prepared. Showing the original description.
Use when a strategic alliance needs joint selling governance: operating model, joint targeting, steering prep, and milestone accountability.
The English summary is being prepared. Showing the original description.