Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Cruz Suiza Seguros Producers 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%2Fcruzsuiza.com%2Fcruzsuiza" | 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%2Fcruzsuiza.com%2Fcruzsuiza" | 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 Cruz Suiza Seguros Producers API.
Check service health without authentication
List available occupation classifications
Read the authenticated producer's context
Request a personal-accident insurance quote
Patterns agents use Cruz Suiza Seguros Producers API for, with concrete tasks.
★ Producer quoting portal
Insurance brokers quote personal-accident cover for clients. The Cruz Suiza API lists the supported occupations and accepts a quote request, so a producer portal can price a policy without manual lookups.
List the available occupations, then request a personal-accident quote for a selected occupation
Occupation reference sync
Quoting tools need the current list of occupation classifications that drive pricing. The API returns the available occupations so a tool can keep its dropdowns and rating logic current.
Fetch the available occupation classifications and refresh the quoting tool's reference list
Agent-driven quote assistant
A producer-facing agent can gather a quote on request. Through Jentic, an agent reads the producer context and occupations and then submits a quote request on the producer's behalf.
Read the producer context, pick an occupation, and request a personal-accident quote
4 endpoints — the cruz suiza seguros producers api gives insurance producers programmatic access to the latin american insurer's quoting tools.
METHOD
PATH
DESCRIPTION
/health
Service health check
/ocupaciones
List available occupations
/contexto
Get the authenticated producer context
/cotizaciones
Request a personal-accident quote
/health
Service health check
/ocupaciones
List available occupations
What agents get from Jentic-routed access to this vendor.
Setup
Cruz Suiza issues an Amazon Cognito JWT from a producer client id and secret before quoting. With Jentic One you install once, import the operations from the API Directory, and the token exchange is handled for you.
Permission scoping
The protected operations act on the authenticated producer rather than arbitrary record ids, so scoping is at the operation level: an agent can be limited to reading occupations and requesting quotes.
Credential isolation
Your Cruz Suiza client id and secret are stored encrypted by your own Jentic One instance and used only to mint tokens at execution time, so they never enter the agent's prompt, logs, or context.
Intent-based discovery
Agents find the quoting operation through Jentic's intent search, matching a request like getting a personal-accident insurance quote to the matching Cruz Suiza endpoint.
Alternatives and complements available in the Jentic catalogue.
Specific to using Cruz Suiza Seguros Producers API through Jentic.
How does the Cruz Suiza Producers API authenticate?
Producers exchange a client id and secret for an Amazon Cognito JWT, which is sent as a bearer token on each protected request. The health check needs no token. Jentic One manages the token and injects it at execution time.
Can I limit what my agent can do with the Cruz Suiza API?
Yes. You import only the operations an agent needs, so a quoting agent can request quotes and read occupations while anything outside that stays unavailable.
What is a personal-accident quote?
It is a price for personal-accident insurance cover, calculated from inputs such as the client's occupation. The quote operation returns that pricing for a producer to present.
What language does the API use?
The spec and responses use Spanish for a Latin American audience, and an agent can still call each operation programmatically regardless of language.
Does the health check need authentication?
No. The health endpoint is public and reports service status without a token; the occupation, context, and quote operations require the Cognito bearer token.
GET STARTED
/contexto
Get the authenticated producer context
/cotizaciones
Request a personal-accident quote
Know of an official OpenAPI document? Contribute it →
For Agents
Lets an AI agent list occupations, read producer context, and request personal-accident insurance quotes from Cruz Suiza, authenticated with a Cognito JWT bearer token.
Use for: I need a personal-accident insurance quote, List the occupation codes Cruz Suiza supports, Who is the authenticated producer?, Check whether the Cruz Suiza service is up
Not supported: Does not issue policies, process claims, or take premium payments: use it to list occupations, read producer context, and request quotes only.
The Cruz Suiza Seguros Producers API gives insurance producers programmatic access to the Latin American insurer's quoting tools. After signing in with an Amazon Cognito JWT, a producer can list available occupations, read their authenticated producer context, and request a personal-accident insurance quote. A public health-check endpoint reports service status.
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>