Google Contact Center AI Platform API
Browse all Google APIs41
AI ReadinessFoundational (D-)41/100
Official vendor OpenAPI document · agent-readyCommunicationsVoice Telephonyoauth29 EndpointsREST
For Agents
Create, list, and tear down Google Contact Center AI Platform tenants so an agent can stand up a fully managed cloud contact centre and confirm its provisioning state.
Use for: I need to provision a new CCAI Platform tenant for a customer, List all contact centers in our europe-west1 location, Retrieve the admin URL of a provisioned contactCenter, Check whether a contactCenter creation operation finished successfully
Not supported: Does not configure IVR flows, route calls, or analyse conversations - use only to create and manage CCAI Platform tenant resources.
Google Contact Center AI Platform (CCAI Platform) API lets administrators provision and manage tenant-level contact centre instances on Google Cloud. It exposes a small surface for creating contactCenter resources, listing them per project and location, querying validation state, and tracking long-running provisioning operations. CCAI Platform itself bundles cloud telephony, agent desktop, IVR, routing, and reporting; this API handles the platform-level lifecycle. It is currently published as v1alpha1.
Install Jentic One Beta
Connect the Contact Center AI Platform API to your agent
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Contact Center AI Platform API, or any other public or private API you need. You set the rules, the agent never sees your credentials, and every call is logged.
Two steps, two machines. Install the instance in a safe environment, then register your agent from wherever it runs.
1
Step 1: Jentic One Host machine
# On the machine that will host your Jentic One instance:
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fgoogleapis.com%2Fcontactcenteraiplatform" | sh2
Step 2: Agent machine
# On the machine where your agent runs (keep this separate from the instance):
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fgoogleapis.com%2Fcontactcenteraiplatform" | sh
jentic register # connects your agent to your Jentic One instanceJentic One is in public beta. The setup above keeps your agent separate from the instance, which is what you want before using real credentials: an agent running as the same OS user as Jentic One can read its stored keys directly. Just evaluating? A single local install is fine to start. See the secure deployment guide for the tiers.
Capabilities
What an agent can do with Contact Center AI Platform API.
Provision a new CCAI Platform tenant under a project and location
List active contactCenter instances and their lifecycle state
Retrieve the configuration and admin URL of a specific contactCenter
Track long-running provisioning operations and cancel ones that have stalled
Delete a contactCenter and release its associated telephony resources
Query supported regions for contactCenter creation
Use Cases
Patterns agents use Contact Center AI Platform API for, with concrete tasks.
★ Multi-Tenant Contact Center Provisioning
A BPO or SaaS reseller stands up an isolated CCAI Platform tenant per end customer. The Contact Center AI Platform API creates the contactCenter resource, returns the long-running operation, and surfaces the admin URL once provisioning completes. Each tenant gets its own telephony numbers, agent desktop, and reporting separate from siblings.
Create a contactCenter named 'acme-support' in europe-west1, poll the returned operation until done, and return the admin console URL.
Contact Center Decommissioning
When a customer churns, automation deletes the CCAI Platform tenant and confirms that telephony and storage have been released. The API exposes contactCenter delete plus operation polling so a script can guarantee clean teardown before billing stops. This avoids manual console work that often misses orphaned resources.
Delete the contactCenter 'former-customer-x' and confirm the long-running delete operation reaches a done state.
Provisioning Health Monitoring
An ops dashboard polls the CCAI Platform API to display the provisioning state of every tenant, surface failed operations, and alert when a contactCenter has been stuck creating for more than 30 minutes. The contactCenters list and operations endpoints provide everything needed without scraping the Cloud Console.
List all contactCenters in project 'support-cluster', then for each fetch its latest operation and flag any whose state is not DONE after 30 minutes.
Agent-Driven Tenant Onboarding
An onboarding agent receives a new customer signup, asks Jentic for the create-contactcenter operation, supplies the customer's preferred region and admin email, and waits on the operation. The agent then hands the admin URL back to the human onboarder. Jentic isolates the Google service-account credentials so the agent never sees them.
Provision a contactCenter for tenant 'newco-2026' in us-east4, attach the admin user newco-admin@example.com, and return the admin URL once the operation completes.
Key Endpoints
9 endpoints — google contact center ai platform (ccai platform) api lets administrators provision and manage tenant-level contact centre instances on google cloud.
METHOD
PATH
DESCRIPTION
POST
/v1alpha1/{+parent}/contactCenters
Create a new contactCenter tenant
GET
/v1alpha1/{+parent}/contactCenters
List contactCenters in a project and location
GET
/v1alpha1/{+name}
Get a specific contactCenter or location resource
GET
/v1alpha1/{+name}/operations
List long-running operations
POST
/v1alpha1/{+name}:cancel
Cancel a long-running operation
POST
/v1alpha1/{+parent}/contactCenters
Create a new contactCenter tenant
GET
/v1alpha1/{+parent}/contactCenters
List contactCenters in a project and location
GET
/v1alpha1/{+name}
Get a specific contactCenter or location resource
GET
/v1alpha1/{+name}/operations
List long-running operations
POST
/v1alpha1/{+name}:cancel
Cancel a long-running operation
Jentic AI Readiness Score
This API is usable in Jentic One now. Its AI-readiness score against Jentic's framework shows where it stands today and where improvements would make it even easier for agents to use.
C
Contact Center AI Platform API
- Foundational (D-)41/100
70
Foundational Compliance56
Developer Experience & Jentic Compatibility18
AI-Readiness & Agent Experience94
Agent Usability63
Security67
AI DiscoverabilityPowered by JenticScoring Framework 1.0.0 | Scoring Engine 0.4.0
Show dimension breakdown
70
Foundational Compliance
Base layer of spec validity and structural soundness.
Grade: A-Signals: 4
80%
Lint Results
Aggregated quality score from linter diagnostics, weighted by severity.
100%
Resolution Completeness
Percentage of `$ref` references that resolve successfully.
0%
Specification Validity
Checks whether the API description parses successfully and conforms to its declared specification (e.g., OpenAPI).
100%
Structural Integrity
Structural correctness score based on schema issues using logarithmic dampening.
56
Developer Experience & Jentic Compatibility
Clarity, completeness, and ingestion readiness for developers and tooling.
Grade: CSignals: 4
0%
Example Density
How richly the API is illustrated with examples.
100%
Example Validity
Percentage of examples that conform to their schemas.
25%
Response Coverage
Percentage of operations with complete response definitions (success, client error, server error).
100%
Tooling Readiness
Health of API ingestion, bundling, and resolution within Jentic pipelines.
18
AI-Readiness & Agent Experience
Semantic breadth, depth, and agent comprehension for AI systems.
Grade: FSignals: 4
73%
Description Coverage
Coverage of descriptions across API elements.
0%
Error Standardization
Coverage of RFC 9457 Problem Details for error responses.
0%
OperationId Quality
Coverage, uniqueness, and casing consistency of operationIds for AI inference.
0%
Summary Coverage
Coverage of summaries across operations/tags/info.
94
Agent Usability
Functional utility, complexity comfort, and AI orchestration readiness.
Grade: A+Signals: 1
94%
Complexity Comfort
Agent comfort level based on API operational and structural complexity.
63
Security
Trust, risk posture, and security compliance.
Grade: B-Signals: 1
62%
Authentication Strength
Average quality of security schemes based on authentication method strength (weakest link for OAuth2).
67
AI Discoverability
Findability, semantic richness, and reasoning readiness.
Grade: BSignals: 1
67%
Descriptive Richness
Clarity and depth of descriptions across API elements.
Score it yourself
Every API in the directory is allowlisted, so you can re-score it with no key required.
npx @jentic/api-scorecard-cli score <openapi-url>Why Jentic?
What agents get from Jentic-routed access to this vendor.
Setup
Wiring the Contact Center AI Platform API by hand means setting up Google OAuth 2.0, minting short-lived tokens against the cloud-platform scope, and addressing each tenant resource by name against contactcenteraiplatform.googleapis.com yourself. Through Jentic you install once, import the Contact Center AI Platform API from the API Directory, store the OAuth credential once, and your agent calls it.
Permission scoping
Contact Center AI Platform puts the parent and contact center resource names in the URL path (/v1alpha1/{+parent}/contactCenters, /v1alpha1/{+name}), so a rule can pin your agent to one parent: it can create and list contact centers there and nothing else. You choose the operations it may call, so the operation-cancel call is not included unless you add it.
Credential isolation
Your Contact Center AI Platform OAuth credential is stored once, encrypted, by your own Jentic One instance and injected at execution time. It never enters the agent's prompt, logs, or context.
Intent-based discovery
Agents search Jentic by intent such as 'create a Google contact center' or 'list contact center tenants', and Jentic returns the matching Contact Center AI Platform operation with its input schema so the agent calls the right endpoint without browsing the reference docs.
Related APIs
Alternatives and complements available in the Jentic catalogue.
FAQs
Specific to using Contact Center AI Platform API through Jentic.
What authentication does the Contact Center AI Platform API use?
The CCAI Platform API uses Google OAuth 2.0 with the cloud-platform scope. Through Jentic the service account credentials are kept in your Jentic One instance and the agent receives scoped access tokens per call rather than the raw key.
Can I create a contactCenter tenant in any region with the CCAI Platform API?
No. The contactCenters create endpoint accepts only the regions where CCAI Platform is generally available; call the locations list under the parent project first to see which regions are valid before attempting creation.
What are the rate limits for the CCAI Platform API?
The CCAI Platform API inherits standard Google Cloud per-project request quotas, with stricter limits on contactCenter create and delete because each triggers a long-running provisioning workflow. Check the Cloud Console Quotas page for your project's specific limits.
How do I provision a new contactCenter through Jentic?
Run pip install jentic, search Jentic for 'create ccai platform contact center', load the schema for the contactCenters.create operation on contactcenteraiplatform.googleapis.com, and execute it with the parent location and admin user payload.
Does the CCAI Platform API let me edit IVR flows or agent skills?
No. This API only handles tenant lifecycle. IVR flow design, agent skill assignment, and call routing are configured inside the CCAI Platform admin console at the URL returned after provisioning.
Can I limit what my agent is allowed to do with the Contact Center AI Platform API?
Yes. Because the API puts the parent and contact center resource names in the URL path (/v1alpha1/{+parent}/contactCenters and /v1alpha1/{+name}), your self-hosted Jentic One instance lets you write a rule that pins the agent to a single parent project and location, so it can create and list contact centers there and nothing else. You also choose exactly which operations the agent may call, so the operation-cancel and delete calls are excluded unless you explicitly add them. Your own rules and stored OAuth credential decide which operations run, and the agent only ever exercises the surface you have granted.
GET STARTED