Install Jentic One Beta

Connect the Intervals API to your agent

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

Log billable or non-billable time against a task or project with worktypeid, personid, date, and hours

Open, assign, and update tasks with status, priority, milestone, due date, and owner

Start and stop timers for a person and convert the tracked time into time entries

Build invoices from line items with tax settings and terms, then record payments against them

GET STARTED

Start building with Intervals API

Explore with Jentic One

View OpenAPI Document

Use Cases

Patterns agents use Intervals API for, with concrete tasks.

★ Agent time logging through Jentic

A developer's agent, connected to Intervals through Jentic, turns a daily summary of work into time entries. It looks up the right task with the task search, reads the valid worktypeid values for the project, and posts each entry with personid, date, time, and billable set. Hours land on the right task and project without anyone opening the timesheet screen.

Call GET /task with projectid=1234 and title='Homepage redesign' to find the task, GET /projectworktype with projectid=1234 to get a worktypeid, then POST /time with worktypeid, personid, taskid, date='2026-11-09', time=3, and billable=true

Client billing run

At month end, an agent pulls approved billable time for a project with datebegin, dateend, and billable filters, creates an invoice with projectid, date, termid, and title, and adds invoice items with name and amount. When the client pays, it records the payment with projectid, amount, date, typeid, and the invoiceid so the invoice status stays accurate.

Call POST /invoice with projectid=1234, date='2026-11-30', termid from GET /invoiceterm, and title='November services', then POST /invoiceitem with the new invoiceid, name='Development', and amount=4200

Task triage and follow-up

A project lead asks an agent which tasks are due this week. The agent filters the task list by projectid, assigneeid, and a due-date window, reads task status and priority values from the taskstatus and taskpriority lists, and updates tasks or adds task notes where follow-up is needed.

Call GET /task with projectid=1234, dateduebegin='2026-11-09', and datedueend='2026-11-15', then POST /tasknote with taskid, note='Blocked on client feedback', and public=false for each blocked task

Project expense tracking

Teams that bill expenses alongside hours need them recorded against the right project. An agent posts each expense with projectid, date, expense, and fee, and lists expenses by project or person with date filters when preparing a client report or invoice.

Call POST /expense with projectid=1234, date='2026-11-09', expense='Stock photography license', and fee=79, then GET /expense with projectid=1234 and datebegin='2026-11-01' to confirm it is listed

Key Endpoints

125 endpoints — the intervals api reads and writes the data in an intervals account: projects, tasks, time entries, timers, expenses, invoices, payments, clients, and people.

METHOD

PATH

DESCRIPTION

POST

/time

Log a time entry

GET

/time

List time entries with filters

POST

/task

Add a task

GET

/task

List tasks with filters

POST

/timer

Add a timer

POST

/invoice

Add an invoice

POST

/payment

Record a payment

GET

/quota

Get API quota usage

POST

/time

Log a time entry

GET

/time

List time entries with filters

POST

/task

Add a task

GET

/task

List tasks with filters

POST

/timer

Add a timer

POST

/invoice

Add an invoice

POST

/payment

Record a payment

GET

/quota

Get API quota usage

Why Jentic?

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

Setup

Wiring Intervals by hand means passing the API token as a Basic auth username with a dummy password, setting the Accept header to get JSON instead of XML, and formatting UTC date-times with a space rather than a T. Through Jentic you install once, import Intervals from the API Directory, store the token once, and your agent calls it.

Permission scoping

Intervals record ids sit in the URL path, as in /task/{id}/ and /invoice/{id}/, so a rule can limit your agent to the operations it needs and to specific records. You choose the operations it may call, so destructive ones like deleting a time entry or an invoice are not included unless you add them.

Credential isolation

Your Intervals API 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 'log billable hours' or 'create an invoice', and Jentic returns the matching Intervals operation with its input schema so the agent calls the right endpoint without browsing the reference docs.

FAQs

Specific to using Intervals API through Jentic.

What authentication does the Intervals API use?

The Intervals API uses HTTP Basic authentication per its OpenAPI spec: your Intervals API token goes in as the username and any non-empty string as the password. The token is under My Profile in the Intervals web app, and calls run with that user's role. Through Jentic, the token is stored once by your own Jentic One instance and injected at call time.

Can I log time to a specific task with the Intervals API?

Yes. POST /time requires worktypeid, personid, date, time, and billable, and accepts taskid, projectid, moduleid, and description. Look up valid work types for the project with GET /projectworktype first, since the worktypeid must be one the project allows.

What are the rate limits for the Intervals API?

The spec says each account has a daily request quota rather than a per-second limit, and does not state the number. Call GET /quota to see current usage and the next reset time in GMT; that call does not count against the quota. See https://www.myintervals.com/api/ for details.

How do dates work in Intervals API requests?

Calendar dates use YYYY-MM-DD in the account's local calendar. Date-times use YYYY-MM-DD HH:MM:SS in UTC with a space between date and time, not a T or a Z suffix, and the space is encoded as %20 in query strings. Set the Accept header to application/json, since responses default to XML without it.

How do I log hours to Intervals through Jentic?

Install Jentic One with `curl -fsSL https://raw.githubusercontent.com/jentic/jentic-one/main/tools/install.sh | sh`, import the Intervals API from the API Directory, and store your API token once. Your agent searches for 'log time to an Intervals task', gets the time-entry operation with its input schema, and calls POST /time. 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 Intervals API?

Yes. For a timesheet assistant, write a rule that allows GET /task, GET /projectworktype, and POST /time, so the agent can find tasks and log hours but cannot touch invoices, payments, or people records, and cannot delete anything. Add GET /time if you also want it to read back what it logged.

Myintervals Intervals API

AI ReadinessNon-Ready (F)36/100

See full scorecard

Official vendor OpenAPI document · agent-readyProductivityTask Managementbasic125 EndpointsREST

For Agents

Log time against Intervals tasks, run timers, track expenses, open and update tasks, and build invoices with line items and payments, filtered by project, client, or person.

Use for: Log three billable hours to the website redesign task for today, List all time entries for a client between two dates, I need to open a new task in a project and assign it to a teammate, Find all overdue tasks assigned to me

Not supported: Does not run payroll, process card payments, or sync calendars. Use for Intervals time tracking, tasks, and invoicing only.

The Intervals API reads and writes the data in an Intervals account: projects, tasks, time entries, timers, expenses, invoices, payments, clients, and people. It covers the full loop from logging billable hours against a task to building an invoice from line items and recording the payment against it. Collection endpoints filter by fields such as projectid, personid, clientid, and date ranges, page with limit and offset, and report the total match count in listcount. Responses come back as JSON or XML depending on the Accept header, and access follows the signed-in user's role.

Jentic One on Github View OpenAPI Document

Show dimension breakdown

Foundational Compliance

Base layer of spec validity and structural soundness.

Grade: A-Signals: 4

81%

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).

100%

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: FSignals: 4

80%

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.

66%

Summary Coverage

Coverage of summaries across operations/tags/info.

Agent Usability

Functional utility, complexity comfort, and AI orchestration readiness.

Grade: A-Signals: 1

77%

Complexity Comfort

Agent comfort level based on API operational and structural complexity.

Security

Trust, risk posture, and security compliance.

Grade: FSignals: 1

10%

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

61%

Descriptive Richness

Clarity and depth of descriptions across API elements.

Connect the Intervals API to your agent

Capabilities

Start building with Intervals API

Use Cases

Key Endpoints

Why Jentic?

Related APIs

FAQs

Myintervals Intervals API

Jentic AI Readiness Score

Intervals 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