Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the CAAC Go Developer 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%2Fcresclab.com%2Fcresclab" | 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%2Fcresclab.com%2Fcresclab" | 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 CAAC Go Developer API.
Send a WhatsApp text message from the workspace number
Generate an AI reply drafted from the business's own content
Verify a workspace API key and read the workspace it belongs to
Patterns agents use CAAC Go Developer API for, with concrete tasks.
★ WhatsApp Customer Messaging
An agent sends a WhatsApp text message to a customer from the workspace number, for an order update, a reminder, or a reply in an ongoing thread. CAAC Go handles delivery through the workspace's connected number, so the agent only supplies the recipient and message content.
GET STARTED
Send a WhatsApp message with POST /api/v1/messages to the customer's number with the order-update text
AI-Assisted Reply Drafting
An agent generates an AI reply grounded in the business's own content before sending it, so the response stays accurate and on-brand. CAAC Go drafts the reply from the supplied business content, and the agent can then send it as a WhatsApp message in the same flow.
Call POST /api/v1/ai/reply with the business content and incoming question, then send the draft with POST /api/v1/messages
AI Agent Integration via Jentic
An AI agent reaches CAAC Go through Jentic without handling the workspace key itself. It searches by intent, receives the matching operation and its input schema, and executes the call with the credential injected at run time. This lets an agent send a WhatsApp message or draft a reply as one step in a support workflow without wiring the key in code.
Search Jentic for 'send a WhatsApp message', load the POST /api/v1/messages schema, and execute it with Jentic-managed credentials
3 endpoints — the caac go developer api sends whatsapp text messages and generates ai replies from a business's own content.
METHOD
PATH
DESCRIPTION
/api/v1/me
Verify the key and get the workspace
/api/v1/messages
Send a WhatsApp text message
/api/v1/ai/reply
Generate an AI reply from business content
/api/v1/me
Verify the key and get the workspace
/api/v1/messages
Send a WhatsApp text message
/api/v1/ai/reply
Generate an AI reply from business content
What agents get from Jentic-routed access to this vendor.
Setup
Wiring CAAC Go by hand means managing its workspace bearer key and threading it through each message-send and AI-reply call. Through Jentic you install once, import CAAC Go from the API Directory, store the key once, and your agent calls it.
Permission scoping
CAAC Go carries the recipient inside the request body, so rules bound which operations your agent may call, not which contact it can reach. You choose the operations it may call, so message sending and AI-reply drafting can be allowed while the key-verification read stays separate.
Credential isolation
Your CAAC Go key 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 'send a WhatsApp message' or 'generate an AI reply', and Jentic returns the matching CAAC Go 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 CAAC Go Developer API through Jentic.
What authentication does the CAAC Go Developer API use?
The CAAC Go Developer API authenticates with a workspace API key (cwa_...) sent as a bearer token in the Authorization header, per its OpenAPI spec. The identity operation confirms which workspace a key belongs to. Through Jentic the key is stored encrypted by your own Jentic One instance and injected at execution time, so it never reaches the agent.
Can I send a WhatsApp message with the CAAC Go Developer API?
Yes. The messages operation sends a WhatsApp text from the workspace's connected number, so an agent supplies the recipient and content and CAAC Go handles delivery. You can pair it with the AI-reply operation to draft the message before sending.
What are the rate limits for the CAAC Go Developer API?
The OpenAPI spec does not publish specific rate-limit numbers; check https://caacgo.cresclab.com for current details. The identity operation confirms the active workspace, which is a cheap preflight before an agent sends a batch of messages.
Is there a CAAC Go MCP server?
You don't need an MCP server to give your agent CAAC Go. Jentic connects it directly from the API Directory: import it, store your credential once, and your agent calls the message and AI-reply operations. Nothing extra is loaded into the agent's context until an operation is actually invoked.
Can I limit what my agent is allowed to do with the CAAC Go Developer API?
Yes. CAAC Go carries the recipient inside the request body, so rules bound which operations your agent may call rather than which contact it can reach. Allow only the message-send and AI-reply operations and the key-verification read stays separate, with every call logged by your own Jentic One instance.
How do I send a WhatsApp message with the CAAC Go Developer API through Jentic?
Search Jentic for 'send a WhatsApp message', and it returns the CAAC Go message operation with its input schema. Load the schema and execute POST /api/v1/messages with the recipient and content, with the credential injected at run time. To run it on your own infrastructure, install Jentic One from its GitHub repo.
For Agents
Send WhatsApp text messages from a workspace number and generate AI replies grounded in business content, plus verify the workspace a key belongs to. Authenticated with a workspace API key as a bearer token.
Use for: Send a WhatsApp message to a customer, Generate an AI reply grounded in our business content, Draft a WhatsApp response for an incoming question, Verify my workspace API key
Not supported: Does not handle voice calls, SMS, or contact-list management. Use for sending WhatsApp messages and generating AI replies only.
The CAAC Go Developer API sends WhatsApp text messages and generates AI replies from a business's own content. One operation delivers a message from the workspace number, another drafts a reply grounded in the business content so responses stay on-brand, and a third verifies the workspace API key and returns the workspace it belongs to. It is a small, focused surface for wiring WhatsApp messaging and AI-assisted responses into an agent.
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.
Base layer of spec validity and structural soundness.
Aggregated quality score from linter diagnostics, weighted by severity.
Percentage of `$ref` references that resolve successfully.
Checks whether the API description parses successfully and conforms to its declared specification (e.g., OpenAPI).
Structural correctness score based on schema issues using logarithmic dampening.
Clarity, completeness, and ingestion readiness for developers and tooling.
How richly the API is illustrated with examples.
Percentage of examples that conform to their schemas.
Percentage of operations with complete response definitions (success, client error, server error).
Health of API ingestion, bundling, and resolution within Jentic pipelines.
Semantic breadth, depth, and agent comprehension for AI systems.
Coverage of descriptions across API elements.
Coverage of RFC 9457 Problem Details for error responses.
Coverage, uniqueness, and casing consistency of operationIds for AI inference.
Coverage of summaries across operations/tags/info.
Functional utility, complexity comfort, and AI orchestration readiness.
Agent comfort level based on API operational and structural complexity.
Trust, risk posture, and security compliance.
Average quality of security schemes based on authentication method strength (weakest link for OAuth2).
Findability, semantic richness, and reasoning readiness.
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>