Collect Testimonials From Your Happiest Customers

AI identifies satisfied customers from usage data and drafts personalized testimonial requests. Your marketing team reviews the timing and approach.


Why this matters

Marketing teams struggle to collect testimonials because they don't know which customers are happiest or when to ask. Generic requests get ignored, while personalized outreach at the right moment gets results — but identifying those moments and crafting individual asks doesn't scale.


How MultiMail solves this

MultiMail's AI agent identifies optimal testimonial candidates based on usage metrics, NPS scores, and support interactions. It drafts personalized requests citing the customer's specific success metrics. With gated_send oversight, marketing reviews the timing and messaging before delivery.

1

Identify Happy Customers

The AI analyzes usage metrics, NPS scores, and support interaction sentiment to identify customers most likely to provide positive testimonials.

2

Draft Personalized Ask

The agent composes a testimonial request that references the customer's specific success — their delivery rate, email volume growth, or time saved. This personal touch dramatically improves response rates.

3

Marketing Reviews Timing

With gated_send, marketing verifies the request is well-timed — not during a support escalation or right after a billing change. They also ensure the ask aligns with current campaign needs.

4

Send and Follow Up

Approved requests are sent. The agent monitors for positive replies and routes them to the marketing team for case study development.


Implementation

Identify and Request Testimonials
python
import requests

API = "https://api.multimail.dev/v1"
HEADERS = {"Authorization": "Bearer mm_live_xxx"}

def request_testimonial(customer: dict, metrics: dict):
    body = (
        f"Hi {customer[&"cm">#039;name']},\n\n"
        f"Your team has processed over {metrics[&"cm">#039;total_emails']:,} "
        f"emails with a {metrics[&"cm">#039;delivery_rate']}% delivery rate "
        f"since joining MultiMail. That&"cm">#039;s impressive!\n\n"
        f"Would you be open to sharing a brief testimonial about "
        f"your experience? It can be as simple as 2-3 sentences "
        f"about what&"cm">#039;s working well for your team.\n\n"
        f"If you&"cm">#039;re interested in a full case study, we'd love to "
        f"highlight your success story on our website."
    )

    return requests.post(
        f"{API}/send",
        headers=HEADERS,
        json={
            "from": "[email protected]",
            "to": customer["email"],
            "subject": "Would you share your experience with MultiMail?",
            "text_body": body
        }
    ).json()

# Find high-satisfaction customers
happy_customers = get_happy_customers(min_nps=9, min_emails=10000)
for customer in happy_customers:
    metrics = get_customer_metrics(customer["id"])
    request_testimonial(customer, metrics)

Find happy customers based on usage metrics and send personalized testimonial requests.

Track Testimonial Responses
python
import requests

API = "https://api.multimail.dev/v1"
HEADERS = {"Authorization": "Bearer mm_live_xxx"}

"cm"># Check for replies to testimonial requests
inbox = requests.get(
    f"{API}/mailboxes/marketing-mailbox-id/inbox",
    headers=HEADERS,
    params={"status": "unread"}
).json()

for message in inbox["emails"]:
    email = requests.get(
        f"{API}/emails/{message[&"cm">#039;id']}",
        headers=HEADERS
    ).json()

    sentiment = analyze_sentiment(email["text_body"])
    if sentiment == "positive":
        requests.post(
            f"{API}/emails/{email[&"cm">#039;id']}/tags",
            headers=HEADERS,
            json={"tags": ["testimonial-accepted", "follow-up-needed"]}
        )
        print(f"Testimonial accepted by {email[&"cm">#039;from']}")

Monitor replies to testimonial requests and route positive responses to the marketing team.

MCP Tool Integration
typescript
"cm">// Testimonial request workflow via MCP

"cm">// 1. Search for high-usage customers
const happyCustomers = await mcp.search_contacts({
  tags: ["high-nps", "active"]
});

"cm">// 2. Send personalized requests
for (const customer of happyCustomers.contacts) {
  await mcp.send_email({
    from: "[email protected]",
    to: customer.email,
    subject: "Would you share your experience with MultiMail?",
    text_body: `Hi ${customer.name}, your team has been crushing it with MultiMail. Would you share a brief testimonial?`
  });
}

"cm">// 3. Check for responses
const replies = await mcp.check_inbox({
  mailbox_id: "marketing-mailbox-id",
  status: "unread"
});

Use MultiMail MCP tools for testimonial request workflows.


What you get

Right Customer, Right Time

AI identifies customers with the highest satisfaction signals — high NPS, strong usage metrics, positive support interactions — and requests testimonials when sentiment is highest.

Personalized Asks Convert Better

Referencing specific success metrics in the request makes customers feel recognized and increases willingness to share their experience.

Marketing Controls the Pipeline

Gated send lets marketing verify timing and coordinate testimonial requests with ongoing campaigns, launches, and content calendars.

Automated Follow-Up Tracking

Tag and track every testimonial request, acceptance, and delivered testimonial to maintain a healthy pipeline of customer stories.


Recommended oversight mode

Recommended
gated_send
Testimonial requests are relationship-sensitive. Marketing needs to verify the timing is right — asking during a support escalation or billing dispute would backfire. Gated send lets AI identify and draft while marketing applies judgment.

Common questions

How does the AI identify good testimonial candidates?
The AI looks at a combination of signals: NPS scores above 8-9, high feature usage, strong delivery metrics, positive support interactions, and account tenure. Customers who are getting real value from the product are most likely to share positive feedback.
What's the difference between a testimonial request and a case study request?
A testimonial is a brief 2-3 sentence endorsement. A case study is a detailed story with metrics, process, and outcomes. The AI starts with a low-commitment testimonial ask and offers the case study option for customers who seem enthusiastic.
How do I comply with FTC endorsement guidelines?
The FTC requires that endorsements reflect honest opinions and material connections are disclosed. MultiMail provides the audit trail of the request and response. Ensure your published testimonials include appropriate disclosures if incentives were offered.
What if a customer declines?
Tag declined customers so they're excluded from future requests for a reasonable period. The AI can try again in 6 months if their engagement remains strong. Never pressure customers — a declined request shouldn't affect the relationship.

Explore more use cases

The only agent email with a verifiable sender

Email infrastructure built for AI agents. Verifiable identity, graduated oversight, and a 38-tool MCP server. Formally verified in Lean 4.