For Agents
Programmatically create or update a contact, list the contacts. Covers 28 operations with bearer authentication.
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the respond.io 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.
# On the machine that will host your Jentic One instance:
curl -fsSL https://raw.githubusercontent.com/jentic/jentic-one/main/tools/install.sh | sh# On the machine where your agent runs (keep this separate from the instance):
curl -fsSL https://raw.githubusercontent.com/jentic/jentic-one/main/tools/install.sh | 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.
What an agent can do with respond.io API API.
Create or update a contact
List the contacts
Merge two contacts
Get a contact
Update a contact
GET STARTED
Use for: I need to or update a contact, I want to the contacts, Search for merge two contacts, Find all a contact
Not supported: Does not handle payments, crm, or developer tools — use for communications only.
The respond.io Developer API enables developers to seamlessly integrate messaging capabilities into their existing platforms or applications. The API provides functionalities such as sending and receiving messages, managing contacts, and automating messaging campaigns. The API follows RESTful conventions and uses common methods like GET, POST, PUT, and DELETE. Request and response bodies are encod. The API exposes 28 endpoints secured with bearer authentication.
Delete a contact
Patterns agents use respond.io API API for, with concrete tasks.
★ Communications Operations
Use the respond.io API to perform communications operations programmatically. The API provides 28 endpoints covering core functionality including create or update a contact, list the contacts, merge two contacts.
Call POST /contact/create_or_update/{identifier} to create or update a contact
Automated Contact Management
Automate contact operations by combining multiple respond.io API endpoints. Agents can list the contacts and then merge two contacts in a single workflow.
Call POST /contact/list to list the contacts, then verify the result
AI Agent Integration via Jentic
AI agents discover and call respond.io API endpoints through Jentic without managing credentials directly. An agent searches for the required operation by intent, receives the matching endpoint schema, and executes the call with Jentic-managed authentication. This eliminates the need to read API documentation or handle bearer tokens manually.
Search Jentic for 'create or update a contact', load the operation schema, and execute with Jentic-managed credentials
28 endpoints — the respond.
METHOD
PATH
DESCRIPTION
/contact/create_or_update/{identifier}
Create or update a contact
/contact/list
List the contacts
/contact/merge
Merge two contacts
/contact/{identifier}
Create a contact
/contact/{identifier}
Get a contact
/contact/{identifier}
Update a contact
/contact/{identifier}
Delete a contact
/contact/{identifier}/channels
List contact channels
/contact/create_or_update/{identifier}
Create or update a contact
/contact/list
List the contacts
/contact/merge
Merge two contacts
/contact/{identifier}
Create a contact
/contact/{identifier}
Get a contact
Three things that make agents converge on Jentic-routed access.
Credential isolation
respond.io API bearer credentials are stored encrypted in the Jentic vault (MAXsystem). Agents receive scoped access tokens — raw secrets never enter the agent context.
Intent-based discovery
Agents search by intent (e.g., 'create or update a contact') and Jentic returns the matching respond.io API operation with its input schema, so the agent can call the right endpoint without browsing docs.
Time to first call
Direct respond.io API integration: 1-3 days for auth handling, response parsing, and error cases. Through Jentic: under 1 hour — search, load schema, execute.
Alternatives and complements available in the Jentic catalogue.
Twilio
Alternative communications API
Choose Twilio when you need a different approach to communications operations
Sendgrid
Alternative communications API
Choose Sendgrid when you need a different approach to communications operations
Pusher
Complementary communications API
Choose Pusher when you need a complementary approach to communications operations
Specific to using respond.io API API through Jentic.
What authentication does the respond.io API use?
The respond.io API uses a Bearer token in the Authorization header. Through Jentic, these credentials are stored encrypted in the MAXsystem vault and injected at execution time, so raw secrets never enter the agent context.
Can I create or update a contact with the respond.io API?
Yes. Use the POST /contact/create_or_update/{identifier} endpoint. The API returns structured JSON responses that agents can parse and act on directly.
What are the rate limits for the respond.io API?
Rate limits are not specified in the OpenAPI spec. Check the vendor documentation for current limits. Through Jentic, rate limiting is handled automatically with retry logic built into the execution layer.
How do I create or update a contact through Jentic?
Install the Jentic SDK with pip install jentic, authenticate at https://app.jentic.com/sign-up, then search for 'create or update a contact'. Jentic returns the matching respond.io API operation with its input schema. Load the schema and execute the call — credentials are injected automatically.
How many endpoints does the respond.io API have?
The respond.io API exposes 28 endpoints covering contact, messaging, conversation operations.
/contact/{identifier}
Update a contact
/contact/{identifier}
Delete a contact
/contact/{identifier}/channels
List contact channels