For Agents
List configured Bitskout AI document workflows and trigger a run programmatically. Useful for agents that need to extract structured data from invoices, receipts, or forms via a pre-built Bitskout pipeline.
Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Bitskout Zapier 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://raw.githubusercontent.com/jentic/jentic-one/main/tools/install.sh | shStep 2: Agent machine
# On the machine where your agent runs (keep this separate from the instance):
curl -fsSL https://raw.githubusercontent.com/jentic/jentic-one/main/tools/install.sh | 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 Bitskout Zapier API.
Verify that a Bitskout service token is valid before running an automation
Enumerate the AI document workflows configured under a Bitskout account
Trigger an existing Bitskout workflow against a supplied document or payload
GET STARTED
Use for: I want to list the AI workflows available in my Bitskout account, Run a Bitskout workflow against a new invoice, Check whether my Bitskout service token is still valid, Trigger a document extraction workflow from an automation
Not supported: Does not handle workflow creation, document storage, or AI model training — use for executing pre-configured Bitskout document workflows only.
Jentic publishes the only available OpenAPI specification for Bitskout Zapier API, keeping it validated and agent-ready. The Bitskout Zapier API exposes Bitskout's AI-powered document processing workflows for automation platforms. It lets external tools verify a service token, enumerate the workflows configured in a Bitskout account, and trigger a workflow run on a supplied document or payload. The integration is intentionally narrow so Zapier-style automations and AI agents can list and execute Bitskout workflows without juggling the full Bitskout web UI.
Route document processing requests through a managed Bitskout AI pipeline
Bridge Zapier-style triggers to Bitskout workflow execution from agent code
Patterns agents use Bitskout Zapier API for, with concrete tasks.
★ Invoice Data Extraction Automation
Forward incoming supplier invoices to a Bitskout workflow that extracts header fields, line items, and totals using AI document parsing. The integration calls /run_workflow with the document payload and Bitskout returns the structured output once the pipeline completes. This avoids hand-rolling OCR and field mapping for finance and accounts payable automations.
Call POST /run_workflow with the workflow id for invoice extraction and the invoice document, then return the extracted vendor, total, and line items.
Workflow Discovery Before Execution
Before automating a Bitskout pipeline, list the workflows available in the connected account so the integration picks the right one by name. The API exposes /workflows for enumeration, which agents call once at setup or whenever the workflow catalogue changes. This pattern keeps automations resilient when workflow ids rotate or new pipelines are added.
Call GET /workflows, filter the response for the workflow whose name matches 'Invoice Extraction', and store its id for subsequent run_workflow calls.
Service Token Health Check
Run a lightweight token validation before kicking off long document processing jobs. The /ping endpoint confirms the supplied API key is accepted by Bitskout, which lets automations fail fast with a clear auth error instead of mid-pipeline. This is especially useful for scheduled jobs that may run hours after credentials were configured.
Call GET /ping with the configured Authorization header and abort the run if the response is not 200.
Agent-Driven Document Workflow via Jentic
An AI agent processing inbound emails uses Jentic to find and call the Bitskout workflow that matches the document type. Jentic resolves the workflow execution operation from a natural language intent, supplies the schema for /run_workflow, and isolates the Bitskout API key so the agent never sees the raw secret. The result is a single-step path from 'extract this PDF' to a structured response.
Use Jentic search for 'run a Bitskout document workflow', load the schema, then execute /run_workflow with workflow_id and document fields supplied by the agent.
3 endpoints — jentic publishes the only available openapi specification for bitskout zapier api, keeping it validated and agent-ready.
METHOD
PATH
DESCRIPTION
/ping
Verify the service token is valid
/workflows
List configured workflows
/run_workflow
Run a workflow against a payload
/ping
Verify the service token is valid
/workflows
List configured workflows
/run_workflow
Run a workflow against a payload
Three things that make agents converge on Jentic-routed access.
Credential isolation
The Bitskout API key (Authorization header) is stored in the Jentic vault. Agents receive a scoped Jentic token and never see the raw key, which is critical because Bitskout has no granular OAuth scopes — the API key authorises all workflows.
Intent-based discovery
Agents search Jentic with intents like 'run a Bitskout document workflow' or 'list Bitskout workflows' and Jentic returns the matching operation with its input schema so the agent can call /run_workflow or /workflows directly.
Time to first call
Direct integration with Bitskout's Zapier API: roughly half a day to wire auth, schema, and error handling. Through Jentic: under 30 minutes to search, load, and execute against the same endpoints.
Alternatives and complements available in the Jentic catalogue.
Specific to using Bitskout Zapier API through Jentic.
Why is there no official OpenAPI spec for Bitskout Zapier API?
Bitskout does not publish an OpenAPI specification. Jentic generates and maintains this spec so that AI agents and developers can call Bitskout Zapier API via structured tooling. It is validated against the live API and kept up to date. Get started at https://app.jentic.com/sign-up.
What authentication does the Bitskout Zapier API use?
The API uses an API key passed in the Authorization header (security scheme name ApiKeyAuth). Through Jentic the key is stored in the encrypted vault, and the agent receives a scoped token instead of the raw value, so the secret never enters the agent's prompt context.
Can I trigger a Bitskout workflow with the Bitskout Zapier API?
Yes. Send a POST to /run_workflow with the workflow identifier and the payload to process. The endpoint is the entry point for executing any AI document workflow configured in your Bitskout account.
How do I find the workflow id I need to call run_workflow?
Call GET /workflows once to enumerate the workflows configured in your account, then pick the id whose name matches the pipeline you want to execute. Cache the id and refresh the list when your workflow catalogue changes.
What are the rate limits for the Bitskout Zapier API?
The OpenAPI spec does not declare explicit rate limits. In practice the endpoint is built for Zapier-style automations, so design retries and backoff around your Bitskout plan limits and watch for HTTP 429 responses.
How do I run a Bitskout document workflow with this API through Jentic?
Install with pip install jentic, then use Jentic search with the query 'run a Bitskout document workflow'. Load the returned operation schema and execute with your workflow_id and document payload. Jentic resolves the call to POST /run_workflow without exposing your API key.