The result to aim for
Aimance Carpano-Caux describes theAccount Summary Agent Dust: he synthesizes the Salesforce account, the web and history, proposes hooks—example: a prospect had just published a book, used as an opening call. Manual prospect research would fall by around 95%.
What was done
Case study Dust. Distinct from Knowledge Agent and Call Summary (MEDDICC). The 95% and "a few seconds" are editor statements. The book of prospect is an example told by the responsible, non-generalizable.
Before you start
Tool cited by the source: Dust (Account Summary Agent); other tools cited: Dust. Fill in the bracketed items: [coller], [NON VÉRIFIÉ]. Strip confidential data that is not needed and check your tool’s access terms. Features and plans can change.
The method, in three steps.
Gather the context
Spot the bracketed items in the prompt (
[coller],[NON VÉRIFIÉ]) and prepare what they ask for.Adapt the prompt
Copy the prompt below, replace the bracketed items, then paste it into Dust.
Reread before using
Reread the result, correct it if needed and keep the final decision. Caveats are detailed below.
Your starting point.
Replace the bracketed items, then adapt the proposal to your situation. This prompt is written by the iadujour desk It is not a quotation from the source.
CRM card (made, without identity): [coller]. Web extract already opened: [coller]. Plug of 10 lines + 3 hooks only if sourced. If a fact is not stuck, [NON VÉRIFIÉ]. Invent no books, recruitment or turnover.
What deserves your attention
Proof level: Statement by the tool’s publisher. Source checked on 11 November 2026. Use described by the source, not tested by the desk. Original summary written by iadujour.fr: figures and claims are the source’s; the prompt is a desk proposal, not a quotation.
Comments.
A field note, a question, a precision on this use case? Comments are reviewed before publication.
Published comments
Loading comments…
Leave a comment
Moderation charter. Every comment is reviewed before publication. We refuse hate speech, insulting or discriminatory language, advertising, spam and promotional links, off-topic posts and other people’s personal data.