Stedi Core
Browse all Stedi APIsCommunity OpenAPI document · agent-readyDeveloper ToolsSource ControlapiKey30 EndpointsREST
Know of an official OpenAPI document? Contribute it →
For Agents
Programmatically retryevent, listexecutions. Covers 30 operations with apiKey authentication.
Use for: I need to retryevent, I want to listexecutions, Search for retryexecutions, Find all getexecution
Not supported: Does not handle payments, communications, or crm - use for developer tools only.
stedi.com/stedi-core-api version 2023-08-01. The API exposes 30 endpoints secured with apiKey authentication.
Install Jentic One Beta
Connect the Core to your agent
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Core, 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.
1
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%2Fstedi.com%2Fcore" | sh2
Step 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%2Fstedi.com%2Fcore" | 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.
Capabilities
What an agent can do with Core API.
RetryEvent
ListExecutions
RetryExecutions
GetExecution
ListExecutionFaults
Use Cases
Patterns agents use Core API for, with concrete tasks.
★ Developer Tools Operations
Use the Core to perform developer tools operations programmatically. The API provides 30 endpoints covering core functionality including retryevent, listexecutions, retryexecutions.
Call POST /events/{eventId}/retry to retryevent
Automated Events Management
Automate events operations by combining multiple Core endpoints. Agents can listexecutions and then retryexecutions in a single workflow.
Call GET /executions to listexecutions, then verify the result
AI Agent Integration via Jentic
AI agents discover and call Core 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 apiKey tokens manually.
Search Jentic for 'retryevent', load the operation schema, and execute with Jentic-managed credentials
Key Endpoints
30 endpoints — stedi.
METHOD
PATH
DESCRIPTION
POST
/events/{eventId}/retry
RetryEvent
GET
/executions
ListExecutions
POST
/executions/retry
RetryExecutions
GET
/executions/{executionId}
GetExecution
GET
/executions/{executionId}/faults
ListExecutionFaults
GET
/executions/{executionId}/input
GetExecutionInputDocument
GET
/executions/{executionId}/input-url
GetExecutionInputDocumentUrl
GET
/executions/{executionId}/metadata
GetExecutionMetadataDocument
POST
/events/{eventId}/retry
RetryEvent
GET
/executions
ListExecutions
POST
/executions/retry
RetryExecutions
GET
/executions/{executionId}
GetExecution
GET
/executions/{executionId}/faults
ListExecutionFaults
GET
/executions/{executionId}/input
GetExecutionInputDocument
GET
/executions/{executionId}/input-url
GetExecutionInputDocumentUrl
GET
/executions/{executionId}/metadata
GetExecutionMetadataDocument
Why Jentic?
What agents get from Jentic-routed access to this vendor.
Setup
Wiring the Stedi Core API by hand means setting up its Authorization header key, targeting the US region host with its dated path, and threading execution and event ids through retry, faults and metadata calls yourself. Through Jentic you install once, import the Core API from the API Directory, store the API key once, and your agent calls it.
Permission scoping
The Core API puts the execution id in the URL path (/executions/{executionId}/faults, /executions/{executionId}/input), so a rule can pin your agent to one execution: it can read that execution's faults, input and metadata and nothing else. You choose the operations it may call, so retrying an execution is not included unless you add it.
Credential isolation
Your Stedi API 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 'retry an event' or 'read an execution's faults', and Jentic returns the matching Core operation with its input schema so the agent calls the right endpoint without browsing the reference docs.
Related APIs
Alternatives and complements available in the Jentic catalogue.
Alternative
Github
Alternative developer tools API
Choose Github when you need a different approach to developer tools operations
FAQs
Specific to using Core API through Jentic.
What authentication does the Core use?
The Core uses an API key passed 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 retryevent with the Core?
Yes. Use the POST /events/{eventId}/retry endpoint. The API returns structured JSON responses that agents can parse and act on directly.
What are the rate limits for the Core?
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 retryevent through Jentic?
Install the Jentic SDK with pip install jentic, authenticate through Jentic One, the self-hosted execution layer, then search for 'retryevent'. Jentic returns the matching Core operation with its input schema. Load the schema and execute the call - credentials are injected automatically.
How many endpoints does the Core have?
The Core exposes 30 endpoints covering events, executions, fragments operations.
Can I limit what my agent is allowed to do with the Stedi Core API?
Yes. Because you run Jentic One yourself, self-hosted, your own rules decide which Core API operations and credentials the agent may use. Since the execution id sits in the URL path, such as GET /executions/{executionId}/faults, /input, and /metadata, you can pin the agent to a single execution so it only reads that execution's faults, input, and metadata. You also pick the operations it may call, so retrying an event or execution is not available to the agent unless you explicitly add it.
GET STARTED