Install Jentic One Beta

Connect the Parallel API to your agent

Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Parallel 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%2Fonparallel.com%2Fparallel" | 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%2Fonparallel.com%2Fparallel" | 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 Parallel API.

Create a petition from an existing template and pre-fill its fields

Add one or more recipients to an existing petition

Read the field definitions of a petition to map them onto an internal schema

List the templates available to the calling account

Download a recipient's reply file when the petition is completed

GET STARTED

Start building with Parallel API

Explore with Jentic One

View OpenAPI Document

Use Cases

Patterns agents use Parallel API for, with concrete tasks.

★ Client onboarding for financial services

Wealth managers, accountants, and lenders use Parallel to collect KYC information, supporting documents, and disclosures from new clients. The API lets the firm's CRM or onboarding tool create a petition from a template, pre-fill known fields, and send the link to the client. Replies come back as structured data plus attached files, ready to be loaded into the back office without re-keying.

POST /petitions with a template id and the client's prefill data, then POST /petitions/{petitionId}/recipients with the client's name and email.

Legal intake and document collection

Law firms run client intake through structured forms that branch based on matter type. Parallel's petition model handles the conditional logic, so the firm only sees the questions relevant to a given engagement. The API surfaces the resulting field map and reply files for ingestion into the matter management system, replacing PDF email loops.

GET /templates to find the intake template, POST /petitions to instantiate it, then GET /petitions/{petitionId}/fields to confirm the field mapping before sending.

AI agent structured collection through Jentic

An AI agent that handles back-office onboarding can use Parallel through Jentic to send a structured form rather than asking the client to write a long email. The agent searches Jentic for the petition operation, loads the schema, and posts the petition with the recipient. Once the recipient replies, a follow-up agent can pull the reply file and parse it into the system of record.

Search Jentic for 'send a parallel petition', load the POST /petitions operation, and execute it for a known template_id with a single recipient.

Key Endpoints

5 endpoints — jentic publishes the only available openapi specification for parallel api, keeping it validated and agent-ready.

METHOD

PATH

DESCRIPTION

POST

/petitions

Create a new petition from a template

GET

/petitions/{petitionId}/fields

Read the field schema of a petition

POST

/petitions/{petitionId}/recipients

Add recipients to a petition

GET

/petitions/{petitionId}/replies/{replyId}/download

Download a recipient's reply file

GET

/templates

List available petition templates

POST

/petitions

Create a new petition from a template

GET

/petitions/{petitionId}/fields

Read the field schema of a petition

POST

/petitions/{petitionId}/recipients

Add recipients to a petition

GET

/petitions/{petitionId}/replies/{replyId}/download

Download a recipient's reply file

GET

/templates

List available petition templates

Why Jentic?

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

Setup

Wiring the Parallel API by hand means managing a long-lived workspace bearer token that can both create petitions and download replies containing client PII, and building each call against www.onparallel.com/api/v1 yourself. Through Jentic you install once, import the Parallel API from the API Directory, store the token once, and your agent calls it.

Permission scoping

Parallel puts the petition id in the URL path (/petitions/{petitionId}/fields, /petitions/{petitionId}/recipients), so a rule can pin your agent to one petition: it can read fields and add recipients for that petition and nothing else. You choose the operations it may call, so downloading recipient replies is not included unless you add it.

Credential isolation

Your Parallel 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 'send a structured client form' or 'download a petition reply', and Jentic returns the matching Parallel operation with its input schema so the agent calls the right endpoint without browsing the reference docs.

FAQs

Specific to using Parallel API through Jentic.

Why is there no official OpenAPI spec for Parallel API?

Parallel publishes its API as developer-facing HTML at onparallel.com/developers/api but does not ship a maintained OpenAPI specification. Jentic generates and maintains this spec so that AI agents and developers can call Parallel via structured tooling. It is validated against the live API and kept up to date. Get started with Jentic One, the self-hosted execution layer.

What authentication does the Parallel API use?

Parallel uses HTTP bearer authentication. Pass your API key as 'Authorization: Bearer <key>' on every request. Through Jentic, the bearer token is held in the vault and injected at execution time, which keeps client-data tokens out of agent prompts and logs.

Can I send a petition to multiple recipients?

Yes. Create the petition with POST /petitions, then call POST /petitions/{petitionId}/recipients once per recipient or in a single batch payload. Each recipient receives their own link so replies can be tracked individually against the same petition.

What are the rate limits for the Parallel API?

Parallel does not publish a global rate limit in its OpenAPI spec. In practice, the platform handles bursts from typical onboarding workflows comfortably, and integrations should back off on 429 responses if they appear during bulk sends. Surface area is small (5 endpoints), so rate limit pressure is unusual outside of bulk-import jobs.

How do I download a recipient's reply through Jentic?

Install the SDK with 'pip install jentic', search for the operation with the query 'download parallel reply', then load the GET /petitions/{petitionId}/replies/{replyId}/download operation, and execute it with the petitionId and replyId. Jentic streams the reply file back to the agent.

How do I find the right template to send?

Call GET /templates to list the templates configured in the account, then use the matching template_id when calling POST /petitions. The template id is also what governs the field schema that GET /petitions/{petitionId}/fields will return.

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

Yes. Because you run Jentic One yourself, your own rules decide which Parallel operations and credentials the agent may use, and you pick the specific endpoints it can call. Parallel puts the petition id in the URL path, such as GET /petitions/{petitionId}/fields and POST /petitions/{petitionId}/recipients, so a rule can pin the agent to a single petition, letting it read that petition's field schema and add recipients while touching nothing else. Since you choose the allowed operations, downloading a recipient's reply file through GET /petitions/{petitionId}/replies/{replyId}/download stays off unless you explicitly grant it.

Onparallel Parallel API

Name: Parallel API
Brand: Parallel API
Availability: InStock

AI ReadinessAI-Aware (B+)68/100

See full scorecard

Agent-ready OpenAPI document · curated by JenticProductivityForms Surveysbearer5 EndpointsREST

Know of an official OpenAPI document? Contribute it →

For Agents

Send a structured data-collection petition to a recipient and download replies and attachments using bearer-token authentication.

Use for: I need to send a client onboarding form with branching questions, Find all templates available in my Parallel account, Add a new recipient to an existing petition, Get the field schema for a petition I am about to send

Not supported: Does not handle e-signature, contract negotiation, or scheduling - use for sending structured data-collection petitions and reading replies only.

Jentic publishes the only available OpenAPI specification for Parallel API, keeping it validated and agent-ready. Parallel is a structured-data collection platform that uses petitions, which are smart forms with branching logic and document attachments, to gather information from clients, partners, or employees. The API lets developers create petitions from templates, send them to recipients, and download replies for downstream processing. It is built for back-office workflows in financial services, legal, and operations where unstructured email and PDFs make data entry slow and error-prone.

Jentic One on Github View OpenAPI Document

Show dimension breakdown

Foundational Compliance

Base layer of spec validity and structural soundness.

Grade: A+Signals: 4

99%

Lint Results

Aggregated quality score from linter diagnostics, weighted by severity.

100%

Resolution Completeness

Percentage of `$ref` references that resolve successfully.

100%

Specification Validity

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

75%

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.

50%

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: D+Signals: 4

40%

Description Coverage

Coverage of descriptions across API elements.

Error Standardization

Coverage of RFC 9457 Problem Details for error responses.

100%

OperationId Quality

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

50%

Summary Coverage

Coverage of summaries across operations/tags/info.

Agent Usability

Functional utility, complexity comfort, and AI orchestration readiness.

Grade: A+Signals: 1

94%

Complexity Comfort

Agent comfort level based on API operational and structural complexity.

Security

Trust, risk posture, and security compliance.

Grade: B-Signals: 1

60%

Authentication Strength

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

100

AI Discoverability

Findability, semantic richness, and reasoning readiness.

Grade: A+Signals: 1

100%

Descriptive Richness

Clarity and depth of descriptions across API elements.

Connect the Parallel API to your agent

Capabilities

Start building with Parallel API

Use Cases

Key Endpoints

Why Jentic?

Related APIs

FAQs

Onparallel Parallel API

Jentic AI Readiness Score

Parallel 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