Install Jentic One Beta

Connect the Float API to your agent

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

Schedule people to projects and project tasks across phases and project stages

Manage roles, departments, and statuses to model team structure inside Float

Configure project expenses, project stages, and phases to mirror agency project plans

Pull pre-built people and projects reports for capacity and utilization analysis

Maintain time-off records with custom time-off types and team and public holiday calendars

GET STARTED

Start building with Float API

Explore with Jentic One

View OpenAPI Document

Use Cases

Patterns agents use Float API for, with concrete tasks.

★ End-to-end agency project setup

Agencies set up a complete project plan in Float by creating the project, its stages, phases, tasks, and project expenses through the corresponding endpoints. /projects, /project-stages, /phases, /project-tasks, and /project-expenses all live in the same surface, so a single workflow can produce a fully populated plan ready for scheduling.

Create project P01 for client Acme with three stages, six phases, twelve tasks, and a single project expense for software licenses

Capacity and utilization reporting

Operations teams pull utilization data from /reports/people and /reports/projects to drive dashboards that compare scheduled hours, logged time, and time off across departments. The reports endpoints aggregate the underlying records, so a BI tool does not need to recompute totals from raw allocations.

Pull the people report for the previous quarter and the projects report for the same window, and write both as CSV

Holiday and time-off calendar management

HR and ops teams keep Float's availability view accurate by maintaining /public-holidays, /team-holidays, and /time-off records with custom /time-off-types. Centralising this in Float means scheduling decisions reflect actual availability without having to cross-check a separate HR calendar.

Add a new public holiday on 2026-12-26 to the UK calendar and create a 'Conference' time-off type

AI agent agency operator

An AI ops agent uses the full Float API through Jentic to handle complex agency requests: scaffolding a new project, reorganising people across departments, merging duplicate tasks, and pulling the report needed for the leadership stand-up. Jentic returns the right Float operation per intent across all 86 endpoints so the agent does not need to map the resource hierarchy by hand.

Reorganise three people from the Design department into a new 'Brand' department and merge tasks T101 and T102 into T101

Key Endpoints

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

METHOD

PATH

DESCRIPTION

GET

/projects

List projects

POST

/projects

Create a new project

GET

/project-tasks

List project tasks

POST

/project-tasks/merge

Merge duplicate project tasks

GET

/people

List people

GET

/reports/people

Get people utilization report

GET

/reports/projects

Get projects report

POST

/public-holidays

Create a public holiday entry

GET

/projects

List projects

POST

/projects

Create a new project

GET

/project-tasks

List project tasks

POST

/project-tasks/merge

Merge duplicate project tasks

GET

/people

List people

GET

/reports/people

Get people utilization report

GET

/reports/projects

Get projects report

POST

/public-holidays

Create a public holiday entry

Why Jentic?

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

Setup

Wiring the Float API by hand means setting its bearer auth, spreading calls across 86 project, task, people, and report endpoints, and handling retries and pagination yourself. Through Jentic you install once, import Float from the API Directory, store the token once, and your agent calls it.

Permission scoping

Float works largely through collection endpoints whose targets travel in the request body rather than an owned resource in the URL path, so limit the agent to the operations it needs, such as listing projects or pulling a people report, and leave project or task creation out of the allowed set unless required. You choose which of the 86 operations it may call.

Credential isolation

Your Float token is stored once, encrypted, by your own Jentic One instance and injected into the Authorization header at execution time. It never enters the agent's prompt, logs, or context.

Intent-based discovery

Agents search Jentic by intent such as 'pull a Float people report' or 'list projects', and Jentic returns the matching operation with its input schema so the agent calls the right one of 86 endpoints without browsing the reference docs.

FAQs

Specific to using Float API through Jentic.

Why is there no official OpenAPI spec for Float API?

Float does not publish a complete OpenAPI specification covering its full resource set. Jentic generates and maintains this spec so that AI agents and developers can call Float API 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 full Float API use?

Float uses HTTP bearer tokens. Through Jentic the bearer token is held in the encrypted vault and injected into the Authorization header at execution time.

What does this spec cover that the curated Float spec does not?

This spec covers project stages, phases, project expenses, roles, statuses, accounts, time-off types, public and team holidays, and the reports endpoints in addition to the people, projects, tasks, time off, and clients found in the curated 18-endpoint subset.

Can I merge duplicate project tasks?

Yes. POST /project-tasks/merge consolidates two project task records into one, which is useful when imports or manual edits create duplicates.

What are the rate limits for the Float API?

Float does not document a fixed global rate limit in the spec. Limits are applied per token. Treat 429 responses as the source of truth and back off using the Retry-After header.

How do I pull a people utilization report through Jentic?

Search Jentic for 'pull a Float people report', load the schema for GET /reports/people, and execute the call with the date range. Install with pip install jentic and run it through Jentic One, the self-hosted execution layer.

How is this spec different from the float-com/float spec?

The float spec is a curated 18-endpoint subset focused on the most common scheduling operations. This float-api spec is the full 86-endpoint surface generated by Jentic so agents can reach every entity Float exposes.

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

Yes. Because you run Jentic One yourself, your own rules decide which of Float's 86 operations the agent may call and which token it uses. Since most Float endpoints are collection calls whose targets travel in the request body rather than in an owned URL path, you can allow read-only operations such as listing projects or pulling the GET /reports/people utilization report while withholding writes like POST /projects or POST /project-tasks/merge. The agent can only reach the operations you include in its allowed set.

Float API

Browse all Float APIs

AI ReadinessNon-Ready (B-)62/100

See full scorecard

Agent-ready OpenAPI document · curated by JenticProductivityTask Managementbearer86 EndpointsREST

Know of an official OpenAPI document? Contribute it →

For Agents

Read and write the full Float resource-planning corpus including projects, project stages, phases, tasks, people, roles, time off, holidays, and report endpoints.

Use for: Create a new project with stages, phases, and tasks, Allocate a designer across two phases of the Acme project next month, Pull the people utilization report for last quarter, Add a new public holiday for the UK office

Not supported: Does not handle invoicing, payroll, or chat collaboration - use for full Float resource scheduling, project planning, time off, holidays, and utilization reports only.

Jentic publishes the only available OpenAPI specification for Float API, keeping it validated and agent-ready. This is the full Float resource-planning API surface, covering people, departments, roles, statuses, projects, project stages, project tasks, phases, project expenses, clients, accounts, public and team holidays, time off, time-off types, and reports for both people and projects. It is the larger sibling to the curated Float spec and gives agents reach into every entity Float exposes for scheduling, allocation, and reporting.

Jentic One on Github View OpenAPI Document

Show dimension breakdown

Foundational Compliance

Base layer of spec validity and structural soundness.

Grade: FSignals: 4

45%

Lint Results

Aggregated quality score from linter diagnostics, weighted by severity.

46%

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).

60%

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: A-Signals: 4

47%

Example Density

How richly the API is illustrated with examples.

99%

Example Validity

Percentage of examples that conform to their schemas.

43%

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: C+Signals: 4

70%

Description Coverage

Coverage of descriptions across API elements.

Error Standardization

Coverage of RFC 9457 Problem Details for error responses.

97%

OperationId Quality

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

69%

Summary Coverage

Coverage of summaries across operations/tags/info.

Agent Usability

Functional utility, complexity comfort, and AI orchestration readiness.

Grade: ASignals: 1

88%

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 Float API to your agent

Capabilities

Start building with Float API

Use Cases

Key Endpoints

Why Jentic?

Related APIs

FAQs

Float API

Jentic AI Readiness Score

Float 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