Install Jentic One Beta

Connect the End Close API to your agent

Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the End Close 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%2Fendclose.com%2Fendclose" | sh

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%2Fendclose.com%2Fendclose" | sh
jentic register       # connects your agent to your Jentic One instance

Jentic 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 End Close API.

Ingest transaction records into configurable data streams via /data_streams and /records, including bulk loads through /records/bulk

Match records automatically by defining reconciliation rules under /reconciliation_rules and running reconciliations

Surface and clear unmatched items as reconciliation exceptions, writing findings and reading the review via /reconciliation_exceptions/{id}/findings and /review

Track bank account balances by creating or updating them under /bank_account_balances, including bulk balance updates

GET STARTED

Start building with End Close API

Explore with Jentic One

View OpenAPI Document

Use Cases

Patterns agents use End Close API for, with concrete tasks.

★ AI agent month-end reconciliation

An AI finance assistant uses Jentic to discover the End Close operations it needs without browsing docs, then drives a close: it loads the month's transaction records, runs the reconciliation that matches them against bank balances, and hands back the exceptions a human still needs to decide. The agent never holds the raw API key, because Jentic injects it at call time.

Search Jentic for 'reconcile records against bank balances', create a data stream with POST /data_streams, bulk load records via POST /records/bulk, run a reconciliation with POST /reconciliations, then list open items from GET /reconciliation_exceptions

Automated bank reconciliation

Finance teams match a ledger of transaction records against the balances reported by their bank accounts and want the matching to run without manual tie-outs. End Close ingests the records, applies reconciliation rules that pair them to balances, and leaves only the unmatched items for review. Progress can be polled so a workflow knows when matching has settled.

Create a reconciliation with POST /reconciliations, add matching logic with POST /reconciliation_rules, then read GET /reconciliations/{id}/agent_status to confirm the matching run is complete

Exception resolution workflow

Every reconciliation leaves a residue of items that did not match, and these exceptions are where accountants spend their time. End Close lists each exception, lets a reviewer write findings against its lines, and exposes the resulting review so the decision is recorded and auditable. This turns a spreadsheet chase into a structured queue an agent or analyst can work down.

List exceptions with GET /reconciliation_exceptions, open one with GET /reconciliation_exceptions/{id}, write findings with PUT /reconciliation_exceptions/{id}/findings, then read GET /reconciliation_exceptions/{id}/review

Continuous transaction ingestion

Before any reconciliation can run, transaction data has to land reliably. End Close models each feed as a data stream with its own property definitions, accepts records one at a time or in bulk, and reports an ingestion health signal so a pipeline can tell a healthy feed from a stalled one. File imports are tracked per stream with their own retry and cancel controls.

Create a data stream with POST /data_streams, confirm it is healthy with GET /data_streams/{key}/health, then bulk create records with POST /records/bulk

Key Endpoints

79 endpoints — the end close api reconciles financial records against bank account balances and surfaces the unmatched items a team must clear to close the books.

METHOD

PATH

DESCRIPTION

POST

/data_streams

Create a data stream

POST

/records/bulk

Bulk create records

POST

/reconciliations

Create a reconciliation

POST

/reconciliation_rules

Create a reconciliation rule

GET

/reconciliation_exceptions

List reconciliation exceptions

PUT

/reconciliation_exceptions/{id}/findings

Write findings for an exception's lines

POST

/bank_account_balances

Create or update a bank account balance

POST

/agents/{id}/runs

Run an agent

POST

/data_streams

Create a data stream

POST

/records/bulk

Bulk create records

POST

/reconciliations

Create a reconciliation

POST

/reconciliation_rules

Create a reconciliation rule

GET

/reconciliation_exceptions

List reconciliation exceptions

PUT

/reconciliation_exceptions/{id}/findings

Write findings for an exception's lines

POST

/bank_account_balances

Create or update a bank account balance

POST

/agents/{id}/runs

Run an agent

Why Jentic?

What agents get from Jentic-routed access to this vendor.

Setup

Wiring the End Close API by hand means managing its X-API-KEY header, modeling data streams for your records, and building the reconciliation and exception polling loop yourself. Through Jentic you install once, import End Close from the API Directory, store the key once, and your agent calls it.

Permission scoping

End Close puts each resource id in the URL path, such as /reconciliations/{id}, /data_streams/{key}, and /bank_accounts/{id}, so a rule can pin your agent to the reconciliation and ingestion operations it needs. You choose the operations it may call, so destructive ones like deleting a reconciliation rule or a bank account are not included unless you add them.

Credential isolation

Your End Close 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 'reconcile records against bank balances' or 'resolve a reconciliation exception', and Jentic returns the matching End Close operation with its input schema so the agent calls the right endpoint without browsing the reference docs.

FAQs

Specific to using End Close API through Jentic.

What authentication does the End Close API use?

The End Close API authenticates with an API key sent in the X-API-KEY request header, per its OpenAPI spec. When you call it through Jentic, the key is stored encrypted by your own Jentic One instance and injected at execution time, so it never enters the agent's prompt, logs, or context.

Can I resolve reconciliation exceptions with the End Close API?

Yes. List the open items with GET /reconciliation_exceptions, open one with GET /reconciliation_exceptions/{id}, write findings for its lines with PUT /reconciliation_exceptions/{id}/findings, and read the resulting review with GET /reconciliation_exceptions/{id}/review. That gives an agent a structured queue to work down rather than a free-form spreadsheet.

Can the End Close API match records automatically?

Yes. Define the matching logic as reconciliation rules with POST /reconciliation_rules, then run a reconciliation with POST /reconciliations so the rules pair records to bank balances and leave only the unmatched items as exceptions. You can poll progress with GET /reconciliations/{id}/agent_status.

What are the rate limits for the End Close API?

The OpenAPI spec does not specify rate limits for the End Close API. Check the End Close documentation at https://www.endclose.com/docs for current limits, and have your agent retry with backoff when the API signals that it is being throttled.

How do I run a month-end reconciliation with the End Close API through Jentic?

Search Jentic for 'reconcile records against bank balances' to load the End Close operation with its input schema, create a data stream, bulk load the period's records with POST /records/bulk, then run a reconciliation and read its agent status. To run it on your own infrastructure, install Jentic One from its GitHub repo.

Can I limit what my agent is allowed to do with the End Close API?

Yes. Because you run Jentic One yourself, you decide which End Close operations the agent may call. Write a rule that permits listing and reading reconciliations and writing exception findings, and leave out destructive operations such as deleting a data stream or a bank account, so the agent can close the books without being able to erase them, and every call it makes is logged.

End Close API

AI ReadinessFoundational (D+)47/100

See full scorecard

Official vendor OpenAPI document · agent-readyFinanceAccountingapiKey79 EndpointsREST

For Agents

Reconcile transaction records against bank balances in End Close: ingest records through data streams, run reconciliation rules to match them, and work the resulting exceptions, matches, and agent runs.

Use for: Create a data stream to ingest bank transaction records, Run a reconciliation and review the exceptions it produces, Match records automatically with a reconciliation rule, List all open reconciliation exceptions that need findings

Not supported: Does not handle payment processing, invoicing, or tax filing. Use for reconciling records against bank balances and closing the books only.

The End Close API reconciles financial records against bank account balances and surfaces the unmatched items a team must clear to close the books. It ingests transaction records through configurable data streams, applies reconciliation rules that match records automatically, and tracks each leftover item as a reconciliation exception with findings and a review trail. Bank accounts and their balances are managed directly, and reconciliation agents can be configured and run to work through matches and exceptions. Authentication uses an API key sent in the X-API-KEY header, and the surface spans data streams, records, reconciliations, rules, matches, exceptions, bank accounts, and agents.

Jentic One on Github View OpenAPI Document

Show dimension breakdown

Foundational Compliance

Base layer of spec validity and structural soundness.

Grade: DSignals: 4

69%

Lint Results

Aggregated quality score from linter diagnostics, weighted by severity.

100%

Resolution Completeness

Percentage of `$ref` references that resolve successfully.

Specification Validity

Checks whether the API description parses successfully and conforms to its declared specification (e.g., OpenAPI).

Structural Integrity

Structural correctness score based on schema issues using logarithmic dampening.

Developer Experience & Jentic Compatibility

Clarity, completeness, and ingestion readiness for developers and tooling.

Grade: B-Signals: 4

Example Density

How richly the API is illustrated with examples.

100%

Example Validity

Percentage of examples that conform to their schemas.

47%

Response Coverage

Percentage of operations with complete response definitions (success, client error, server error).

100%

Tooling Readiness

Health of API ingestion, bundling, and resolution within Jentic pipelines.

AI-Readiness & Agent Experience

Semantic breadth, depth, and agent comprehension for AI systems.

Grade: FSignals: 4

51%

Description Coverage

Coverage of descriptions across API elements.

Error Standardization

Coverage of RFC 9457 Problem Details for error responses.

OperationId Quality

Coverage, uniqueness, and casing consistency of operationIds for AI inference.

60%

Summary Coverage

Coverage of summaries across operations/tags/info.

Agent Usability

Functional utility, complexity comfort, and AI orchestration readiness.

Grade: ASignals: 1

89%

Complexity Comfort

Agent comfort level based on API operational and structural complexity.

Security

Trust, risk posture, and security compliance.

Grade: C-Signals: 1

50%

Authentication Strength

Average quality of security schemes based on authentication method strength (weakest link for OAuth2).

AI Discoverability

Findability, semantic richness, and reasoning readiness.

Grade: A-Signals: 1

77%

Descriptive Richness

Clarity and depth of descriptions across API elements.

Connect the End Close API to your agent

Capabilities

Start building with End Close API

Use Cases

Key Endpoints

Why Jentic?

Related APIs

FAQs

End Close API

Jentic AI Readiness Score

End Close API

Foundational Compliance

Lint Results

Resolution Completeness

Specification Validity

Structural Integrity

Developer Experience & Jentic Compatibility

Example Density

Example Validity

Response Coverage

Tooling Readiness

AI-Readiness & Agent Experience

Description Coverage

Error Standardization

OperationId Quality

Summary Coverage

Agent Usability

Complexity Comfort

Security

Authentication Strength

AI Discoverability

Descriptive Richness