Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the CRM Golden Gate 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%2Fbetool.fr%2Fbetool" | 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%2Fbetool.fr%2Fbetool" | 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 CRM Golden Gate API.
List the companies in an organization's Betool CRM
Create a company record in the CRM
Partially update selected fields on a company by id
Read a process datatable's rows together with its column structure
Retrieve a single process record by its register token
GET STARTED
Poll the progress of an asynchronous create or update operation
Patterns agents use CRM Golden Gate API for, with concrete tasks.
★ Agent-maintained company records
An AI agent keeps CRM company records current. Through Jentic the agent lists companies, reads one by id, and submits a partial update; because writes are asynchronous, the update returns an operation id that the agent polls through the operations endpoint until the change settles. This lets an assistant correct a company's details without a human opening the CRM.
List companies, find the one named 'Acme', and submit a partial update setting its website, then poll the returned operation id until it completes
Process datatable reporting
A team runs reporting off a Betool process datatable. The API returns both the datatable's rows and its column structure, and a schema-only call describes the columns without fetching rows, so an agent can map fields before pulling data. This supports building a report or sync without hard-coding the datatable layout.
Fetch a process datatable's schema to learn its columns, then retrieve its rows for the current reporting period
Record lookup by register token
A support assistant resolves a single process record on demand. Given a register token, the API returns that one process record, so an agent handling an inbound request can pull the exact record it refers to without scanning the whole datatable. The lookup is read-only and scoped to one record.
Retrieve the process record for a given register token and return its fields to the support assistant
8 endpoints — the crm golden gate api is the rest entrypoint of the betool crm, where an agent lists and reads the companies in an organization, creates a company, and partially updates one by id.
METHOD
PATH
DESCRIPTION
/companies
List the companies of the organization
/companies
Create a company
/companies/{id}
Retrieve one company
/companies/{id}
Partially update a company
/process/{id}/datatable
Retrieve datatable data and structure for a process
/process/{id}/records/{registerToken}
Retrieve a single process record
/operations/{operationId}
Read the progress of an async create/update operation
/companies
List the companies of the organization
/companies
Create a company
/companies/{id}
Retrieve one company
/companies/{id}
Partially update a company
/process/{id}/datatable
Retrieve datatable data and structure for a process
/process/{id}/records/{registerToken}
Retrieve a single process record
/operations/{operationId}
Read the progress of an async create/update operation
What agents get from Jentic-routed access to this vendor.
Setup
Wiring the CRM Golden Gate API by hand means handling its bearer-token auth, learning the async write pattern where create and update return an operation id you poll, and parsing process datatable structures yourself. Through Jentic you install once, import it from the API Directory, store the token once, and your agent calls it.
Permission scoping
The CRM Golden Gate API puts the company id in the URL path (/companies/{id}), so a rule can pin your agent to the company operations it needs: it can list and read companies and update one by id without reaching the process datatable endpoints. You choose the operations it may call, so create and update are not included unless you add them.
Credential isolation
Your Betool organization token is held 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 'list CRM companies' or 'update a company record', and Jentic returns the matching CRM Golden Gate 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 CRM Golden Gate API through Jentic.
What authentication does the CRM Golden Gate API use?
The CRM Golden Gate API authenticates with a bearer token per its OpenAPI spec: an organization API token passed in the Authorization header as a bearer credential. Through Jentic the token is injected at call time by your own Jentic One instance, so it never enters the agent's prompt or logs.
Can I update a company record with the CRM Golden Gate API?
Yes. The company update operation partially updates a company by its id, so you send only the fields that change. Because writes run asynchronously, the call returns an operation id whose progress you read back through the operations endpoint until the update settles.
What are the rate limits for the CRM Golden Gate API?
The OpenAPI spec does not specify rate limits. Check the provider's documentation at https://betool.fr for current limits before running high-volume syncs.
Is there a CRM Golden Gate MCP server?
You don't need an MCP server to give your agent the CRM Golden Gate API. Jentic connects it directly from the API Directory: import it, store your organization token once, and your agent calls it, so you skip installing and syncing a separate server.
Can I limit what my agent is allowed to do with the CRM Golden Gate API?
Yes. Write a rule that allows only the company list and read operations, so the agent can look up companies but cannot create or update one, and add the update operation only when you want it to write. Every call the agent makes is logged.
How do I update a company with the CRM Golden Gate API through Jentic?
Search Jentic for 'update a CRM company' and it returns the company update operation with its input schema; because writes are asynchronous, the call hands back an operation id you read through the operations endpoint. To run it on your own infrastructure, install Jentic One from its GitHub repo.
For Agents
Work with Betool CRM data: list, read, create, and update company records, and read process datatables and records. Writes are asynchronous and return a pollable operation id.
Use for: List all companies in my CRM organization, Create a new company record in Betool, Update the website field on a company by id, Get one company's details from the CRM
Not supported: Does not handle marketing campaigns, deal pipelines, or support ticketing. Use for CRM company and process-record management only.
The CRM Golden Gate API is the REST entrypoint of the Betool CRM, where an agent lists and reads the companies in an organization, creates a company, and partially updates one by id. It also reads process datatables, returning both their rows and their column structure, and retrieves a single process record by its register token. Create and update calls run asynchronously and return an operation id whose progress the agent polls until the write settles.
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>