Install Jentic One Beta

Connect the Halict API to your agent

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

Build and list forms, and read a single form's definition

Read form responses and move them through stages

Add notes to a response for team follow-up

Generate a new form from a one-sentence description

Subscribe to webhooks so an agent hears about a new response as it arrives

GET STARTED

Start building with Halict API

Explore with Jentic One

View OpenAPI Document

Use Cases

Patterns agents use Halict API for, with concrete tasks.

★ Intake to Case Pipeline

An agent turns incoming form responses into actionable cases. It lists responses for a form, reads each one, moves it to the right stage, and adds a note for the person who will follow up. Because responses and their stages and notes are first-class resources, the agent can run an intake queue end to end without a human copying data between tools.

List responses for a form, move the newest response to the next stage, and add a note describing the follow-up

AI Form Builder

An agent creates a ready-to-use form from a plain-language brief. It calls the generate operation with a sentence describing the questions, then reads the created form back to confirm its fields. This lets a team spin up a new intake or survey form from a description instead of building it field by field.

Call the form-generate operation with a sentence describing an intake form and return the id of the created form

Real-Time Response Handling

An agent reacts to new submissions the moment they land. It subscribes to the response event, then reads the new response and routes it, instead of polling the form on a timer. Subscriptions are created and removed through the API, so the agent manages which events it listens for.

Subscribe to the new-response event for a form and confirm the subscription was created

Key Endpoints

16 endpoints — the halict api builds forms, reads their responses, and turns each response into a case a team can stage, tag, and follow up.

METHOD

PATH

DESCRIPTION

GET

/forms

List forms

POST

/forms

Create a form

GET

/forms/{id}

Get a form

GET

/forms/{formId}/responses

List responses for a form

POST

/responses/{id}/notes

Add a note to a response

POST

/v1/forms/generate

Build a form from a sentence

GET

/forms

List forms

POST

/forms

Create a form

GET

/forms/{id}

Get a form

GET

/forms/{formId}/responses

List responses for a form

POST

/responses/{id}/notes

Add a note to a response

POST

/v1/forms/generate

Build a form from a sentence

Why Jentic?

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

Setup

Wiring Halict by hand means handling its bearer token, learning how responses move through stages, and polling or subscribing for new submissions. Through Jentic you install once, import Halict from the API Directory, store the token once, and your agent calls it.

Permission scoping

Halict puts form and response ids in the URL path, so a rule can pin your agent to the response operations for one form. You choose the operations it may call, so destructive ones like form or response deletion are not included unless you add them.

Credential isolation

Your Halict 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 'build a form' or 'list form responses', and Jentic returns the matching Halict operation with its input schema so the agent calls the right endpoint without reading the reference docs.

FAQs

Specific to using Halict API through Jentic.

What authentication does the Halict API use?

Per its OpenAPI spec, the Halict API authenticates with a bearer token sent in the Authorization header. Through Jentic the token is stored by your own self-hosted instance and injected when the agent calls an operation, so it never appears in the agent's prompt or logs.

Can I generate a form from text with the Halict API?

Yes. Halict exposes a generate operation that builds a form from a single-sentence description, so an agent can create an intake or survey form from a brief instead of defining each field. The agent can then read the form back to confirm its questions before sharing it.

What are the rate limits for the Halict API?

The OpenAPI spec does not state a numeric rate limit. Add retry and backoff around 429 responses, and check the Halict documentation at https://halict.com for any published limits before running high-volume jobs.

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

Yes. Write a rule that allows the response read and note operations for one form id, so the agent can triage and annotate submissions while the form-delete and member operations stay out of reach, and every call it makes is logged. Halict carries form and response ids in the URL path, which is what makes that per-form boundary possible.

Is there a Halict MCP server?

You do not need an MCP server to give your agent the Halict API. Jentic connects it directly from the Jentic API Directory: import Halict, store your token once, and your agent calls the form, response, and generate operations on demand without loading another server's tool definitions into its context.

How do I handle form responses with the Halict API through Jentic?

Search Jentic by intent such as 'list form responses', and Jentic returns the Halict operation with its input schema so the agent reads and stages submissions. To run it on your own infrastructure, install Jentic One from its GitHub repo with `curl -fsSL https://raw.githubusercontent.com/jentic/jentic-one/main/tools/install.sh | sh`, then add Halict from the directory.

Halict API

AI ReadinessAI-Aware (B)64/100

See full scorecard

Official vendor OpenAPI document · agent-readyProductivityForms Surveysbearer16 EndpointsREST

For Agents

Build forms, read and update their responses, move responses through stages, add notes, generate a form from a sentence, and subscribe to webhooks for new responses.

Use for: Create a new intake form for my team, List all responses submitted to a given form, Build a form from a sentence describing what I want to ask, Add a note to a response before I follow up

Not supported: Does not handle payment collection, e-signatures, or survey analytics dashboards. Use for building forms and managing their responses and cases only.

The Halict API builds forms, reads their responses, and turns each response into a case a team can stage, tag, and follow up. It lets a backend list and create forms, read and update responses, move them through stages, add notes, and manage team members and webhook subscriptions. A separate generate operation builds a form from a single sentence, and webhook subscriptions let a system hear about a new response the moment it arrives.

Jentic One on Github View OpenAPI Document

Show dimension breakdown

Foundational Compliance

Base layer of spec validity and structural soundness.

Grade: ASignals: 4

98%

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).

30%

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: BSignals: 4

Example Density

How richly the API is illustrated with examples.

100%

Example Validity

Percentage of examples that conform to their schemas.

52%

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: DSignals: 4

37%

Description Coverage

Coverage of descriptions across API elements.

Error Standardization

Coverage of RFC 9457 Problem Details for error responses.

88%

OperationId Quality

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

57%

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).

AI Discoverability

Findability, semantic richness, and reasoning readiness.

Grade: B+Signals: 1

70%

Descriptive Richness

Clarity and depth of descriptions across API elements.

Connect the Halict API to your agent

Capabilities

Start building with Halict API

Use Cases

Key Endpoints

Why Jentic?

Related APIs

FAQs

Halict API

Jentic AI Readiness Score

Halict 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