Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Application user 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%2Fspikeapi.com%2Fspikeapi" | 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%2Fspikeapi.com%2Fspikeapi" | 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 Application user API.
Application Information
Authenticate via V1 Client Token
Upload Lab Report
List Lab Reports
Process Lab Report
GET STARTED
Patterns agents use Application user API for, with concrete tasks.
★ Developer Tools Operations
Use the Application user API to perform developer tools operations programmatically. The API provides 62 endpoints covering core functionality including application information, authenticate via v1 client token, authenticate via hmac.
Call GET /applicationinfo to application information
Automated Applicationinfo Management
Automate applicationinfo operations by combining multiple Application user API endpoints. Agents can authenticate via v1 client token and then authenticate via hmac in a single workflow.
Call POST /auth/client_token to authenticate via v1 client token, then verify the result
AI Agent Integration via Jentic
AI agents discover and call Application user 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 'application information', load the operation schema, and execute with Jentic-managed credentials
62 endpoints — spikeapi.
METHOD
PATH
DESCRIPTION
/applicationinfo
Application Information
/auth/client_token
Authenticate via V1 Client Token
/auth/hmac
Authenticate via HMAC
/auth/pkcs1
Authenticate via PKCS1
/lab_reports
Upload Lab Report
/lab_reports
List Lab Reports
/lab_reports/process
Process Lab Report
/lab_reports/{lab_report_id}
Get Lab Report
/applicationinfo
Application Information
/auth/client_token
Authenticate via V1 Client Token
/auth/hmac
Authenticate via HMAC
/auth/pkcs1
Authenticate via PKCS1
/lab_reports
Upload Lab Report
/lab_reports
List Lab Reports
/lab_reports/process
Process Lab Report
/lab_reports/{lab_report_id}
Get Lab Report
What agents get from Jentic-routed access to this vendor.
Setup
Wiring the Spike Application user API by hand means implementing its bearer auth, working through its client-token and HMAC or PKCS1 signing endpoints, and pointing every call at the app-api.spikeapi.com/v3 host yourself. Through Jentic you install once, import the Application user API from the API Directory, store the bearer token once, and your agent calls it.
Permission scoping
The API puts the lab report id in the URL path (/lab_reports/{lab_report_id}), so a rule can pin your agent to one lab report and the read operations around it. You choose the operations it may call, so a write like posting or processing new lab reports is not included unless you add it.
Credential isolation
Your Spike bearer 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 'get application information' or 'fetch a lab report', and Jentic returns the matching Application user 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 Application user API through Jentic.
What authentication does the Application user API use?
The Application user 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 application information with the Application user API?
Yes. Use the GET /applicationinfo endpoint. The API returns structured JSON responses that agents can parse and act on directly.
What are the rate limits for the Application user 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 application information through Jentic?
Install the Jentic SDK with pip install jentic, authenticate through Jentic One, the self-hosted execution layer, then search for 'application information'. Jentic returns the matching Application user API operation with its input schema. Load the schema and execute the call - credentials are injected automatically.
How many endpoints does the Application user API have?
The Application user API exposes 62 endpoints covering applicationinfo, auth, lab_reports operations.
Can I limit what my agent is allowed to do with the Spike Health Data API?
Yes. Jentic One runs self-hosted, so your own rules decide which Spike operations and credentials the agent may use. Because the API puts the lab report id in the URL path (GET /lab_reports/{lab_report_id}), you can pin the agent to a single lab report and the read calls around it, such as GET /lab_reports and GET /applicationinfo. Write operations like POST /lab_reports or POST /lab_reports/process stay out of reach unless you explicitly grant them.
For Agents
Programmatically application information, authenticate via v1 client token. Covers 62 operations with bearer authentication.
Use for: I need to application information, I want to authenticate via v1 client token, Search for authenticate via hmac, Find all authenticate via pkcs1
Not supported: Does not handle payments, communications, or crm - use for developer tools only.
spikeapi.com/spike-health-data version 3.0.2. The API exposes 62 endpoints secured with bearer authentication.