Outbound Compliance Dialer
TCPA-safe outbound dialing for collections, surveys, and follow-ups. Built-in disclosures, opt-out handling, and full call-detail logging for compliance review.
Why this matters
Voice agents for outsourcing operations. Inbound queues, outbound dialers, multi-tenant agent provisioning. Replace seats, keep quality, full QA + audit trails. This example shows you how to automate outbound compliance dialer calls end-to-end with Guava's SDK — no telephony plumbing, no prompt engineering, just Python.
Installation
Install from Guava's private PyPI index. A public package is coming soon — the install command will simplify to pip install guava.
# Step 1: Install Guava
pip install gridspace-guava --extra-index-url https://guava-pypi.gridspace.com
# Public PyPI package coming soon — the install command will simplify to:
# pip install guava
# Step 2: Set your credentials
export GUAVA_API_KEY="..."
export GUAVA_AGENT_NUMBER="..."How it's built
Every Guava agent is a Python class. Walk through the key sections below, then grab the complete file at the end.
Imports
Import the Guava SDK and any helpers you need. guava.CallController is the base class for every voice agent.
# Install: pip install gridspace-guava --extra-index-url https://guava-pypi.gridspace.com
import guava
import osAgent setup
set_persona() defines how the agent presents itself. set_task() gives it its mission in plain English. The checklist drives the conversation — Guava works through it top-to-bottom, collecting Field values and speaking Say items as it goes.
class ComplianceDialerBot(guava.CallController):
def __init__(self, contact_name: str, account_id: str, campaign: str):
super().__init__()
self.contact_name = contact_name
self.account_id = account_id
self.set_persona(
organization_name="Acme Recovery Services",
agent_name="Morgan",
)
self.set_task(
objective=f"Make a TCPA-compliant outbound call to {contact_name} for {campaign}",
checklist=[
guava.Field(
key="right_party_contact",
field_type="bool",
description=f"Have you confirmed you're speaking with {contact_name}?",
),
guava.Say(
"This call may be recorded for quality and compliance. This is an attempt to "
"collect a debt and any information obtained will be used for that purpose."
),
guava.Field(
key="opt_out_requested",
field_type="bool",
description="Has the consumer requested no further calls?",
),
guava.Field(
key="callback_requested",
field_type="text",
description="If a callback is requested, when?",
required=False,
),
],
on_complete=self.handle_disposition,
)
def handle_disposition(self, fields):
if fields.get("opt_out_requested"):
print(f"OPT-OUT: {self.contact_name} ({self.account_id}) — suppress all future contact")
elif fields.get("callback_requested"):
print(f"CALLBACK: {self.contact_name} requested {fields['callback_requested']}")
else:
print(f"CONTACTED: {self.account_id} — log disposition for QA review")
guava.dial(
controller=ComplianceDialerBot,
controller_args={"contact_name": "Pat Lee", "account_id": "AC-4729", "campaign": "30-day past due"},
to=os.environ["CONTACT_PHONE"],
agent_number=os.environ["GUAVA_AGENT_NUMBER"],
api_key=os.environ["GUAVA_API_KEY"],
)Platform performance
<1s
Response time
99.99%
Uptime SLA
13+
Industries served
Full example
The complete file — copy it, save it as example.py, and run it.
# Install: pip install gridspace-guava --extra-index-url https://guava-pypi.gridspace.com
import guava
import os
class ComplianceDialerBot(guava.CallController):
def __init__(self, contact_name: str, account_id: str, campaign: str):
super().__init__()
self.contact_name = contact_name
self.account_id = account_id
self.set_persona(
organization_name="Acme Recovery Services",
agent_name="Morgan",
)
self.set_task(
objective=f"Make a TCPA-compliant outbound call to {contact_name} for {campaign}",
checklist=[
guava.Field(
key="right_party_contact",
field_type="bool",
description=f"Have you confirmed you're speaking with {contact_name}?",
),
guava.Say(
"This call may be recorded for quality and compliance. This is an attempt to "
"collect a debt and any information obtained will be used for that purpose."
),
guava.Field(
key="opt_out_requested",
field_type="bool",
description="Has the consumer requested no further calls?",
),
guava.Field(
key="callback_requested",
field_type="text",
description="If a callback is requested, when?",
required=False,
),
],
on_complete=self.handle_disposition,
)
def handle_disposition(self, fields):
if fields.get("opt_out_requested"):
print(f"OPT-OUT: {self.contact_name} ({self.account_id}) — suppress all future contact")
elif fields.get("callback_requested"):
print(f"CALLBACK: {self.contact_name} requested {fields['callback_requested']}")
else:
print(f"CONTACTED: {self.account_id} — log disposition for QA review")
guava.dial(
controller=ComplianceDialerBot,
controller_args={"contact_name": "Pat Lee", "account_id": "AC-4729", "campaign": "30-day past due"},
to=os.environ["CONTACT_PHONE"],
agent_number=os.environ["GUAVA_AGENT_NUMBER"],
api_key=os.environ["GUAVA_API_KEY"],
)Run it
Start the agent. It will connect to Guava's infrastructure and begin accepting calls on your assigned number.
python example.py