Install Jentic One Beta

Connect the Constech API to your agent

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

List and create projects

Create and update tasks within a project

Run a task and record the entries it produces

Attach media and templates to a task

Browse portal entities filtered by brand or account

GET STARTED

Start building with Constech API

Explore with Jentic One

View OpenAPI Document

Use Cases

Patterns agents use Constech API for, with concrete tasks.

★ Agent-Run Task Automation

An AI agent connected through Jentic can drive Constech work end to end: it creates a task inside a project, runs the task, and reads the entries the run produces. Because tasks are addressed by project and task id, the agent operates against a specific project's workflow.

Create a task in a project, run it, and read the entries it produces

Project and Task Tracking

Keeping work visible means querying the current state. Constech lists projects filtered by status, tag, or account and lists the tasks inside a project, so an agent can report which projects are active and what work sits under each one without opening the app.

List the projects with a given status and the tasks inside a selected project

Portal Entity Lookup

Constech's portal holds entities tied to a brand or account. The portal operations list entities filtered by brand name or account name and open a single entity by id, so an agent can look up the right entity before attaching work to it.

Find portal entities for a brand and open one entity by id

Task Setup with Templates

Repeatable work benefits from a starting point. Constech attaches a template and media to a task, so an agent can create a task and pre-load it with the template and assets it needs before the task is run.

Create a task and attach a template and media to it

Key Endpoints

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

METHOD

PATH

DESCRIPTION

GET

/projects

List projects

POST

/projects

Create a project

GET

/projects/{projectId}/tasks

List the tasks in a project

POST

/projects/{projectId}/tasks

Create a task in a project

POST

/projects/{projectId}/tasks/{taskId}/run

Run a task

POST

/projects/{projectId}/tasks/{taskId}/entries

Create an entry under a task

GET

/portal/folders

List portal folders

GET

/projects

List projects

POST

/projects

Create a project

GET

/projects/{projectId}/tasks

List the tasks in a project

POST

/projects/{projectId}/tasks

Create a task in a project

POST

/projects/{projectId}/tasks/{taskId}/run

Run a task

POST

/projects/{projectId}/tasks/{taskId}/entries

Create an entry under a task

GET

/portal/folders

List portal folders

Why Jentic?

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

Setup

Wiring the Constech API by hand means handling its x-api-key header, resolving the base path on its dev host, and nesting task calls under project and task ids. Through Jentic you install once, import Constech from the API Directory, store the key once, and your agent calls it.

Permission scoping

Constech puts the project id in the URL path (/projects/{projectId}/...), so a rule can pin your agent to one project: it can read and run tasks in that project and nothing else. You choose the operations it may call, so deleting a project or a task is not included unless you add them.

Credential isolation

Your Constech 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 'run a task in a project' or 'list projects by status', and Jentic returns the matching Constech operation with its input schema so the agent calls the right endpoint without browsing the reference docs.

FAQs

Specific to using Constech API through Jentic.

Why is there no official OpenAPI spec for the Constech API?

Constech does not publish an OpenAPI specification. Jentic generates and maintains this spec so that AI agents and developers can call the Constech API via structured tooling. It is validated against the live API and kept up to date. To run it on your own infrastructure, install Jentic One from its GitHub repo.

What authentication does the Constech API use?

The Constech API authenticates with an API key sent in the x-api-key request header per its OpenAPI spec. When you call it through Jentic, that key is stored once by your own Jentic One instance and injected at execution time, so it never reaches the agent's prompt or logs.

Can I run a task with the Constech API?

Yes. A task is addressed by its project id and task id, and the run operation executes it, after which the entries operations return the entries the run produced. This lets an agent trigger a task and read its output rather than only reading existing data.

What are the rate limits for the Constech API?

The OpenAPI spec does not define numeric rate limits for the Constech API. Check the Constech documentation at https://constech.io for the current request limits that apply to your key.

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

Yes. Constech puts the project id in the URL path, so write a rule that allows only the task list and run operations within one project: the agent can then run that project's tasks and read their entries but cannot delete a task or a project, and every call it makes is logged.

How do I run a task with the Constech API through Jentic?

Search Jentic with an intent like 'run a task in a project', and Jentic returns the run operation at /projects/{projectId}/tasks/{taskId}/run with its input schema so your agent passes the project and task ids and then reads the entries the run produced.

Is there a Constech MCP server?

You don't need an MCP server to give your agent the Constech API. Jentic connects it directly from the API Directory: import the API, store your x-api-key once, and your agent calls the project, task, and portal operations on demand.

Constech API

AI ReadinessNon-Ready (F)7/100

See full scorecard

Agent-ready OpenAPI document · curated by JenticProductivityTask ManagementapiKey29 EndpointsREST

Know of an official OpenAPI document? Contribute it →

For Agents

Manage Constech projects and their tasks, run tasks and record their entries, and browse a portal of brand and account entities organized in folders.

Use for: List the projects in my account, Create a task in a project, Run a task and read its entries, Find portal entities for a specific brand

Not supported: Does not handle payments, messaging, or user authentication beyond its API key. Use for managing Constech projects, tasks, entries, and portal entities only.

Jentic publishes the only available OpenAPI specification for the Constech API, keeping it validated and agent-ready. The Constech API manages projects and the tasks inside them, runs a task, and records the entries a task produces. It browses a portal of entities organized into folders and filtered by brand or account, lists task types, and tracks asset jobs. Authentication uses an API key sent in the x-api-key header.

Jentic One on Github View OpenAPI Document

Show dimension breakdown

Foundational Compliance

Base layer of spec validity and structural soundness.

Grade: A-Signals: 4

96%

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).

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.

75%

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

39%

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.

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: 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: FSignals: 1

Descriptive Richness

Clarity and depth of descriptions across API elements.

Connect the Constech API to your agent

Capabilities

Start building with Constech API

Use Cases

Key Endpoints

Why Jentic?

Related APIs

FAQs

Constech API

Jentic AI Readiness Score

dev-rest-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