Switch from 30 minutes to a few minutes for a personalized commercial e-mail

What was done

Study Dust, Alexandre Le Goupil, Head of Revenue Systems and AI. " 80% time reduction on email personalization (30+ minutes → minutes per prospect)". Flux: Selecting contacts in CRM → Agent Dust reads history in the Supabase mirror, enriches (LinkedIn, news), route to sub-agents (downloading content vs e-commerce prospecting), generates 3 e-mails, writes JSON/HTML in Supabase, the CRM repeats them in sequence. Anti-hallucination rule: only cite data from the database. 2 500+ production actions via MCP Supabase since summer 2025. Distinct from the other two workflows (social proofs, landing pages).

Before you start

Tool cited by the source: Dust (MCP Supabase). Fill in the bracketed items: [rôle, secteur, historique CRM autorisé], [coller]. Strip confidential data that is not needed and check your tool’s access terms. Features and plans can change.

The method, in three steps.

1. 01

   Gather the context

   Spot the bracketed items in the prompt ([rôle, secteur, historique CRM autorisé], [coller]) and prepare what they ask for.

2. 02

   Adapt the prompt

   Copy the prompt below, replace the bracketed items, then paste it into the AI assistant you use. The cited tool (Dust (MCP Supabase)) is not necessarily available to the public..

3. 03

   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.

Prospect (without personal e-mail): [rôle, secteur, historique CRM autorisé]. Verification: [coller].

3 short emails. Every statement must come from the facts. Otherwise: to be checked.

What deserves your attention

Useful skills

Official skills on the same task, paired by the desk: they are not part of the described case.

• Good practices Postgres (Supabase)Supabase · Collects the best Postgres practices maintained by Supabase, valid for a Postgres hosted anywhere, not just on Supabase.
• Develop with SupabaseSupabase · This skill applies to any Supabase task: base, Auth, Edge Functions, Realtime, Storage, vectors, cron, file, client libraries and SSR integrations (supabase-js, @supabase/ssr) in Next.js, React, SvelteKit, Astro or Remix, troubleshooting (session, JWT, cookies, getSession, getUser, getClaims, RLS), CLI or MCP server, schemas, migrations, audits, Postgres extensions, and debugging ( HTTP or Postgres errors, RLS, schema cache, timesouts, Logs Explorer / ClickHouse logs).
• Optimize Postgres according to Supabase practices, in Build Web AppsOpenAI · Collect, in the OpenAI Build Web Apps plugin, Postgres optimization practices maintained by Supabase.