Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Bookkeeping Core 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%2Fpleo.io%2Fpleo" | 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%2Fpleo.io%2Fpleo" | 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 Bookkeeping Core API.
Create a new account.
Retrieves an account in Pleo by its ID.
Update an account
Delete an account
Fetch a list of accounts
GET STARTED
Patterns agents use Bookkeeping Core API for, with concrete tasks.
★ Developer Tools Operations
Use the Bookkeeping Core API to perform developer tools operations programmatically. The API provides 5 endpoints covering core functionality including create a new account., retrieves an account in pleo by its id., update an account.
Call POST /v1-beta/accounts to create a new account.
Automated BookkeepingCore Management
Automate bookkeepingcore operations by combining multiple Bookkeeping Core API endpoints. Agents can retrieves an account in pleo by its id. and then update an account in a single workflow.
Call GET /v1-beta/accounts/{accountId} to retrieves an account in pleo by its id., then verify the result
AI Agent Integration via Jentic
AI agents discover and call Bookkeeping Core 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 'create a new account.', load the operation schema, and execute with Jentic-managed credentials
5 endpoints — bookkeeping core openapi definitions.
METHOD
PATH
DESCRIPTION
/v1-beta/accounts
Create a new account.
/v1-beta/accounts/{accountId}
Retrieves an account in Pleo by its ID.
/v1-beta/accounts/{accountId}
Update an account
/v1-beta/accounts/{accountId}
Delete an account
/v1-beta/accounts:search
Fetch a list of accounts
/v1-beta/accounts
Create a new account.
/v1-beta/accounts/{accountId}
Retrieves an account in Pleo by its ID.
/v1-beta/accounts/{accountId}
Update an account
/v1-beta/accounts/{accountId}
Delete an account
/v1-beta/accounts:search
Fetch a list of accounts
What agents get from Jentic-routed access to this vendor.
Setup
Wiring the Pleo Bookkeeping Core API by hand means learning its bearer auth, choosing between the production and staging hosts, and hand-building requests across its account endpoints yourself. Through Jentic you install once, import Pleo from the API Directory, store the token once, and your agent calls it.
Permission scoping
Pleo puts the account id in the URL path (/v1-beta/accounts/{accountId}), so a rule can pin your agent to one account: it reads and updates that account and nothing else. You choose the operations it may call, so destructive ones like deleting an account are not included unless you add them.
Credential isolation
Your Pleo 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 'create a new account' or 'search accounts', and Jentic returns the matching Pleo 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 Bookkeeping Core API through Jentic.
What authentication does the Bookkeeping Core API use?
The Bookkeeping Core 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 create a new account. with the Bookkeeping Core API?
Yes. Use the POST /v1-beta/accounts endpoint. The API returns structured JSON responses that agents can parse and act on directly.
What are the rate limits for the Bookkeeping Core 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 create a new account. through Jentic?
Install the Jentic SDK with pip install jentic, authenticate through Jentic One, the self-hosted execution layer, then search for 'create a new account.'. Jentic returns the matching Bookkeeping Core API operation with its input schema. Load the schema and execute the call - credentials are injected automatically.
How many endpoints does the Bookkeeping Core API have?
The Bookkeeping Core API exposes 5 endpoints covering bookkeepingcore, accounts, aggregated bookkeeping category groups operations.
Can I limit what my agent is allowed to do with the Pleo Bookkeeping Core API?
Yes. Because Jentic One is self-hosted, your own rules decide which operations and credentials the agent may use, and you pick exactly which Bookkeeping Core operations it can call. Since Pleo puts the account ID in the URL path (/v1-beta/accounts/{accountId}), a rule can pin the agent to a single account so it only reads and updates that account and nothing else. Destructive calls like DELETE /v1-beta/accounts/{accountId} stay off limits unless you explicitly grant them.
For Agents
Programmatically create a new account., retrieves an account in pleo by its id.. Covers 5 operations with bearer authentication.
Use for: I need to a new account., I want to retrieves an account in pleo by its id., Search for an account, Find all an account
Not supported: Does not handle payments, communications, or crm - use for developer tools only.
Bookkeeping Core OpenAPI definitions. The API exposes 5 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.
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>