Skip to main content

How AI One-to-One Email works

AI One-to-One Email lets the agent generate personalized one-to-one email content at runtime. You configure core delivery controls — sender identity and failure behavior — in the builder, while the agent tailors the subject, preview text, and body to the current situation. This tool combines the personal feel of one-to-one messaging with the flexibility of AI-generated content. It is ideal for high-touch outreach scenarios where the message should reference specific user context — like recent activity, account health, or lifecycle stage — while still appearing as a direct email from a real team member. The agent adapts every send to the recipient, so no two emails need to read the same way.

Configuration

Inputs

Prompt
string
required
Instructions that tell the agent when this tool should be used and what quality bar the generated copy should meet.
Send to
string
required
Target user to email.
Send from
string
required
Team member identity used as sender.
Subject
string
required
AI-generated subject line.
Preview (optional)
string
Optional AI-generated preview text.
cc
string[]
Optional CC recipients; can be set by builder defaults or agent at runtime.
bcc
string[]
Optional BCC recipients; can be set by builder defaults or agent at runtime.
Complete on send failure
boolean
default:"true"
Controls whether the run should continue when send fails.

Outputs

status
enum
required
The status of the email send operation. Can be success, failure, or skipped.
to_id
string
required
The ID of the user that the email was sent to.
from_id
string
required
The team member ID used as the sender for this email.
email_id
string
The ID of the email that was sent (available on success).
create_email_options
object
The options used when creating the email, including the AI-generated subject, preview text, and body content (available on success).
create_email_response
object
The response from the email creation service (available on success).
code
enum
The code indicating why the email send operation failed or was skipped. Can be resend_error, duplicate_email, or user_marketing_email_opt_out.
error_message
string
The message of the error that occurred (available on failure).

Use cases

Trial-to-Paid Conversion Follow-Up
Condition: User upgrades from trial to paid plan
Action: Agent generates personalized congratulatory email from assigned CSM
Outcome: New customer receives a warm, contextual welcome that references their trial activity
High-Risk Account Outreach
Condition: Churn risk score crosses a critical threshold
Action: Agent generates a contextual check-in with next-step recommendations from the account owner
Outcome: At-risk user receives a personal, relevant message addressing their specific situation
Onboarding Guidance
Condition: User completes initial setup but has not activated a key feature after 5 days
Action: Agent generates a helpful nudge from the success manager referencing the user's current progress
Outcome: Stalled user receives targeted guidance that feels like a personal check-in, not a generic drip
Quarterly Business Review Prep
Condition: QBR date is within 14 days and usage data is available
Action: Agent generates a pre-QBR outreach email summarizing recent activity and proposed agenda items
Outcome: Customer receives a thoughtful, data-informed touchpoint that sets up a productive review

Best practices

Prompt Quality and Tone Control
  • Give concrete voice, policy, and CTA constraints in the tool prompt to keep generated outreach consistent and safe.
  • Include examples of ideal tone and length so the agent has a clear quality bar for every send.
  • Reference specific user properties the agent should weave into the message (e.g., company name, recent milestones, plan tier).
Sender Identity and Personalization
  • Configure sender selection rules to ensure the agent uses the correct team member identity for each recipient.
  • Avoid generic sender assignments — the from_id should map to the person who actually owns the customer relationship.
  • Audit from_id and create_email_options outputs periodically to verify the agent is sending from the right person with appropriate content.
Testing and Guardrails
  • Start with a small cohort to evaluate generated copy quality before rolling out to a broader audience.
  • Set complete_on_send_failure appropriately — enable it when the agent run has other critical steps that should proceed regardless.
  • Monitor code output for patterns like duplicate_email to detect and prevent repeat outreach to the same user.