For Agents
Programmatically create or update a contact, list the contacts. Covers 28 operations with bearer authentication.
Install Jentic One Beta
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.
Two steps, two machines. Install the instance in a safe environment, then register your agent from wherever it runs.
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%2Frespond.io%2Frespond" | shStep 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%2Frespond.io%2Frespond" | 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.
Create or update a contact
List the contacts
Merge two contacts
Get 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.
Update a contact
Delete a contact
Patterns agents use respond.io 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
What agents get from Jentic-routed access to this vendor.
Setup
Wiring respond.io API by hand means learning its bearer token auth, pointing at the api.respond.io/v2 host, and handling contact and message flows yourself. Through Jentic you install once, import respond.io API from the API Directory, store the token once, and your agent calls it.
Permission scoping
respond.io API puts the contact identifier in the URL path (/contact/{identifier}/...), so a rule can pin your agent to one contact: it can read and update that contact and nothing else. You choose the operations it may call, so destructive ones like contact deletion or contact merge are not included unless you add them.
Credential isolation
Your respond.io API token 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 or update a contact' or 'read a contact's channels', and Jentic returns the matching respond.io API operation with its input schema so the agent calls the right endpoint without browsing the reference docs.
Alternatives and complements available in the Jentic catalogue.
Specific to using respond.io 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 your Jentic One instance 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 through Jentic One, the self-hosted execution layer, 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