Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Talent API · API Reference, 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%2Ftalentapi.com%2Ftalentapi" | 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%2Ftalentapi.com%2Ftalentapi" | 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 Talent API · API Reference API.
Authenticate with the Talent API.
Recommend profiles for a given job.
Integrate Talent API · API Reference into automated workflows
Query and filter Talent API · API Reference records by parameters
Monitor Talent API · API Reference operational status and events
GET STARTED
Patterns agents use Talent API · API Reference API for, with concrete tasks.
★ HR and Recruiting Operations
Use the Talent API · API Reference to perform hr recruiting operations programmatically. The API provides 25 endpoints covering core functionality including authenticate with the talent API., recommend profiles for a given job., recommend jobs for a given profile..
Call POST /auth to authenticate with the talent API.
Automated Recommend Management
Automate recommend operations by combining multiple Talent API · API Reference endpoints. Agents can recommend profiles for a given job. and then recommend jobs for a given profile. in a single workflow.
Call POST /recommend/job/{job_id}/profiles to recommend profiles for a given job., then verify the result
AI Agent Integration via Jentic
AI agents discover and call Talent API · API Reference 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 'authenticate with the talent API.', load the operation schema, and execute with Jentic-managed credentials
25 endpoints — <p>api support: <a href="support@radix.
METHOD
PATH
DESCRIPTION
/auth
Authenticate with the Talent API.
/recommend/job/{job_id}/profiles
Recommend profiles for a given job.
/recommend/profile/{profile_id}/jobs
Recommend jobs for a given profile.
/recommend-master/profile/{profile_id}/jobs
Recommend jobs for a given profile (master).
/recommend-master/job/{job_id}/profiles
Recommend profiles for a given job (master).
/recommend-master/job/{job_id}/jobs
Recommend jobs for a given job (master).
/recommend-master/profile/{profile_id}/profiles
Recommend profiles for a given profile (master).
/recommend/job/{job_id}/jobs
Recommend job for a given job.
/auth
Authenticate with the Talent API.
/recommend/job/{job_id}/profiles
Recommend profiles for a given job.
/recommend/profile/{profile_id}/jobs
Recommend jobs for a given profile.
/recommend-master/profile/{profile_id}/jobs
Recommend jobs for a given profile (master).
/recommend-master/job/{job_id}/profiles
Recommend profiles for a given job (master).
/recommend-master/job/{job_id}/jobs
Recommend jobs for a given job (master).
/recommend-master/profile/{profile_id}/profiles
Recommend profiles for a given profile (master).
What agents get from Jentic-routed access to this vendor.
Setup
Wiring the Talent API by hand means calling its auth endpoint for a JWT bearer token, sending it on every request, and threading job and profile ids through nested recommendation routes yourself. Through Jentic you install once, import the Talent API from the API Directory, store the token once, and your agent calls it.
Permission scoping
The Talent API puts the job id and profile id in the URL path (/recommend/job/{job_id}/profiles), so a rule can pin your agent to one job or profile: it can fetch recommendations for that record and nothing else. You choose the operations it may call, so the broader recommend-master routes are not included unless you add them.
Credential isolation
Your Talent 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 'recommend profiles for a job' or 'recommend jobs for a profile', and Jentic returns the matching Talent 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 Talent API · API Reference API through Jentic.
What authentication does the Talent API · API Reference use?
The Talent API · API Reference 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 authenticate with the talent API. with the Talent API · API Reference?
Yes. Use the POST /auth endpoint. The API returns structured JSON responses that agents can parse and act on directly.
What are the rate limits for the Talent API · API Reference?
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 authenticate with the talent API. through Jentic?
Install the Jentic SDK with pip install jentic, authenticate through Jentic One, the self-hosted execution layer, then search for 'authenticate with the talent API.'. Jentic returns the matching Talent API · API Reference operation with its input schema. Load the schema and execute the call - credentials are injected automatically.
How many endpoints does the Talent API · API Reference have?
The Talent API · API Reference exposes 25 endpoints covering recommend, search, add or update operations.
Can I limit what my agent is allowed to do with the Talent API?
Yes. Because you run Jentic One yourself, your own rules decide which Talent API operations and credentials the agent may use. Since the Talent API carries the job id and profile id in the URL path, such as /recommend/job/{job_id}/profiles, you can pin the agent to a single job or profile so it fetches recommendations for that record and nothing else. You also choose the exact operations it can call, so the broader recommend-master routes stay off limits unless you explicitly add them.
Know of an official OpenAPI document? Contribute it →
For Agents
Programmatically authenticate with the talent API., recommend profiles for a given job.. Covers 25 operations with bearer authentication.
Use for: I need to authenticate with the talent API., I want to recommend profiles for a given job., Search for recommend jobs for a given profile., Find all recommend jobs for a given profile (master).
Not supported: Does not handle payments, communications, or crm - use for hr and recruiting only.
<p>API Support: <a href="support@radix.ai">support@radix.ai</a> | Website: <a href="https://www.radix.ai">https://www.radix.ai</a></p> <p>Job and profile matching using Artificial Intelligence.</p> <h1>What is it?</h1> <p>Talent API is a system that allows retrieving jobs recommendations for a profile or profiles recommendations for a job.<br> There are three types of entities involved:</p> <ul> <. The API exposes 25 endpoints secured with bearer authentication.
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.
/recommend/job/{job_id}/jobs
Recommend job for a given job.
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>