Sales outreach · Production

Brevo automated go-to-market workflows with Dust & Supabase: 80% faster email personalization, zero engineering tickets

The problem

Brevo's sales reps spent 30+ minutes per prospect manually researching across fragmented systems, while 30%+ of RevOps requests required manual human responses despite being answerable from existing documentation. AI agents had no access to CRM data, and finding relevant customer references for sales calls relied entirely on tribal knowledge.

First attempt

Existing AI agents had no access to the CRM, and alternative data platforms like BigQuery and Snowflake were designed for analytics rather than real-time agent read/write operations.

Workflow diagram · grounded in source
1
BDR selects contacts in CRM
trigger
“BDRs select contacts to prospect in their CRM. This triggers a Dust conversation”
2
Read CRM history from Supabase
integration
“Pulls the prospect's full history from Supabase (prior contact, pipeline stage, products discussed)”
3
Enrich with web and LinkedIn data
ai_action
“Enriches with web context (LinkedIn profiles, company news, firmographic data)”
4
Route to specialized sub-agent
routing
“Routes to specialized sub-agents based on prospect type (gated content downloads get one agent, cold e-commerce leads get another)”
5
Prompt-level hallucination guardrail
validation
“The team built strict rules into their prompts: only reference data that exists in the database. Grounding every agent in structured Supabase data eliminated the risk of fabricated customer names or made-up statistics that would destroy …”
6
Generate 3 personalized emails
ai_action
“Generates 3 personalized emails tailored to the person's role, seniority, and context”
7
Write email sequences to Supabase
output
“- Writes: Generated email sequences (as structured JSON and HTML) back to Supabase - Production use: Brevo's CRM pulls these emails into multi-channel sales sequences (email, phone, LinkedIn)”
Reported outcome

Brevo achieved an 80% time reduction on email personalization, automated 30%+ of internal support requests through self-serve AI agents, and executed 2,500+ production actions through Supabase-connected agents without writing engineering tickets.

Reported metrics
Email personalization time reduction80%
Internal support requests automated30%+
Production actions executed2,500+
Concept to production workflow timeDays, not months
Show all 6 reported metrics
email personalization time reduction80%
internal support requests automated30%+
production actions executed2,500+
concept to production workflow timeDays, not months
email research and writing time reduction80-90%
customer referral search time10-15 minutes → seconds
Reported stack
DustSupabaseMCPLinkedIn
Source
https://dust.tt/customers/brevo-gtm-team-workflows-faster-email-personalization
Read source ↗

Frequently asked questions

What did this team achieve with this AI workflow?

Brevo achieved an 80% time reduction on email personalization, automated 30%+ of internal support requests through self-serve AI agents, and executed 2,500+ production actions through Supabase-connected agents without…

What tools did this team use?

Dust, Supabase, MCP, LinkedIn.

What results were reported?

Email personalization time reduction: 80%; Internal support requests automated: 30%+; Production actions executed: 2,500+; Concept to production workflow time: Days, not months (source-reported, not independently verified).

What failed first in this deployment?

Existing AI agents had no access to the CRM, and alternative data platforms like BigQuery and Snowflake were designed for analytics rather than real-time agent read/write operations.

How is this sales outreach AI workflow structured?

BDR selects contacts in CRM → Read CRM history from Supabase → Enrich with web and LinkedIn data → Route to specialized sub-agent → Prompt-level hallucination guardrail → Generate 3 personalized emails → Write email sequences to Supabase.