Sales ops · Production

How Persona Hit 80% AI Agent Adoption with Dust

The problem

As Persona scaled, engineers were overwhelmed by a firehose of technical questions in the #ask-engineers Slack channel, sales and compliance teams wasted hours manually compiling lengthy RFP responses from scattered past materials, and solutions engineers lost significant time writing SRDs from call transcripts.

First attempt

Persona's first Dust deployment was a brittle v0 multi-agent system chained with Zapier that was too complex and still relied on engineers to self-triage questions, providing context but not reducing the interruption load.

Workflow diagram · grounded in source
1
Question submitted in Slack
Trigger
Employees submit questions in the #ask-engineers Slack channel.
▾ source quote
“PersonaEngineer was deployed to answer questions in the #ask-engineers channel”
2
PersonaEngineer routes query
Routing
PersonaEngineer's general reasoning layer routes questions to the right sub-agent and stitches responses together.
▾ source quote
“orchestrated by a general reasoning layer (PersonaEngineer itself), which routed questions to the right place and stitched responses together”
3
Domain sub-agent retrieves answer
Ai action
Specialized sub-agents each focused on a specific domain retrieve answers from their designated knowledge source.
▾ source quote
“DDDEngineer for GitHub codebases InfrastructureEngineer for production changes and incidents DataQueryExpert for data warehouses PersonaHelpCenter for help center and technical documentation PersonaGlossary for internal terminologies PeopleNerd for the employee directory”
4
Answer delivered in Slack
Output
Dust provides context and answers directly in Slack, cutting down on noise and interruptions.
▾ source quote
“Dust now provides context and answers directly in Slack, cutting down on noise and interruptions”
5
RFPNerd generates RFP responses
Ai action
RFPNerd generates accurate RFP answers by drawing on all previous RFPs and latest company information.
▾ source quote
“running them through RFPNerd, a Dust agent connected to all previous RFPs and latest company information”
6
SRDNerd generates SRDs from transcripts
Ai action
SRDNerd automatically generates Solution Requirement Documents from call transcripts.
▾ source quote
“Solutions engineers have SRDNerd, which can automatically generate SRDs from call transcripts”
7
Feedback captured for agent improvement
Feedback loop
Employees flag incorrect answers in Slack, providing a signal to spot gaps and improve agents over time.
▾ source quote
“Dust added feedback capture directly inside Slack, giving employees an easy way to flag when an answer is off. While still early, that signal has become a valuable data point to spot gaps and improve the agent over time.”
Reported outcome

Within six months, AI agent adoption reached more than 80% of Persona's employee base across 11 of 13 departments.
Fraud analysts reduced SQL query work from hours to under 30 minutes, and RFP responses that previously took days are now generated in a fraction of the time.

Reported metrics
AI agent adoption ratemore than 80%
departments with active Dust users11 out of 13
Sales department adoption85%
Post-Sales department adoption85%
Show all 10 reported metrics
AI agent adoption ratemore than 80%
departments with active Dust users11 out of 13
Sales department adoption85%
Post-Sales department adoption85%
Engineering department adoption50%
SQL query completion timeunder 30 minutes
RFP response timefraction of the time
total agents created across companynearly 300
time to reach 80% adoptionsix months
Slack channel initial user growth200 people
Reported stack
DustPersonaEngineerRFPNerdSRDNerdSlackZapierJiraGitHub
◆ Does this fit your context?

Compare to your context

Tell us your scale, team, and constraints. We'll show what changes at your size, what fails at your scale, and whether this case is a fit, needs adaptation, or won't scale to you. Free demo, no signup.

Compare to your context →
~30 seconds · free
Source
https://dust.tt/customers/how-persona-hit-80-ai-agent-adoption-with-dust
Read source ↗

Frequently asked questions

What did this team achieve with this AI workflow?

Within six months, AI agent adoption reached more than 80% of Persona's employee base across 11 of 13 departments.

What tools did this team use?

Dust, PersonaEngineer, RFPNerd, SRDNerd, Slack, Zapier, Jira, GitHub.

What results were reported?

AI agent adoption rate: more than 80%; departments with active Dust users: 11 out of 13; Sales department adoption: 85%; Post-Sales department adoption: 85% (source-reported, not independently verified).

What failed first in this deployment?

Persona's first Dust deployment was a brittle v0 multi-agent system chained with Zapier that was too complex and still relied on engineers to self-triage questions, providing context but not reducing the interruption…

How is this sales ops AI workflow structured?

Question submitted in Slack → PersonaEngineer routes query → Domain sub-agent retrieves answer → Answer delivered in Slack → RFPNerd generates RFP responses → SRDNerd generates SRDs from transcripts → Feedback captured for agent improvement.

Related sales ops cases

WHAT TO DO WITH THIS

Now compare it to your context

This case is one data point. Whether its pattern fits you depends on your volumes, your stack, and your exception load — that comparison is the step no case study can do for you.

Browse the Sales ops cases →