Install Jentic One Beta

Connect the Ranch.Bot HTTP API to your agent

Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Ranch.Bot HTTP 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%2Franch.bot%2Franch" | 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%2Franch.bot%2Franch" | 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 Ranch.Bot HTTP API.

List a farm's animals by inventory_status such as CURRENT, SOLD, or DECEASED and look one up by exact EID

Find or create an animal from an EID tag scan during a chute session

Schedule farm events, approve or reject pending ones, and manage recurring events

Preview a workflow run from a template_id and inputs, then commit or discard the preview

GET STARTED

Start building with Ranch.Bot HTTP API

Explore with Jentic One

View OpenAPI Document

Use Cases

Patterns agents use Ranch.Bot HTTP API for, with concrete tasks.

★ Ranch assistant agent through Jentic

A ranch assistant agent can answer herd questions and log work without the rancher opening the app. Through Jentic the agent searches for 'look up an animal by EID', receives the Ranch.Bot operation with its input schema, and calls GET /v1/farm/{farm_id}/animals/lookup-by-eid, with the OAuth device token injected at execution time. Ranch.Bot notes that direct API writes skip the app's confirmation screen, so preview-then-commit operations are the safer path for changes.

Look up an animal with GET /v1/farm/{farm_id}/animals/lookup-by-eid using its EID, then list its records with GET /v1/farm/{farm_id}/records

Previewed workflow runs

Farm work such as processing a group through vaccinations is easy to get wrong when written straight to the record. Ranch.Bot's POST /v1/farm/{farm_id}/workflows/preview takes a request_id, template_id, and inputs and returns a preview that can be read, then committed through the commit route or dropped through the discard route.

Create a preview with POST /v1/farm/{farm_id}/workflows/preview using request_id, template_id, and inputs, read it back with GET /v1/farm/{farm_id}/workflows/previews/{preview_id}, then commit it

Event scheduling and approvals

Herd health plans run on schedules, and some events need sign-off before they land. Ranch.Bot lists scheduled events, returns those pending approval through GET /v1/farm/{farm_id}/scheduled-events/pending/approval, and approves or rejects each one, while recurring events and farm follow-up tasks keep routine work on the calendar.

Call GET /v1/farm/{farm_id}/scheduled-events/pending/approval and approve each event with POST /v1/farm/{farm_id}/scheduled-events/{scheduled_event_id}/approve

Chute-side animal logging

When cattle move through a chute, each EID tag scan needs to match an animal record. Ranch.Bot chute sessions are created with a config, and POST /v1/farm/{farm_id}/animals/find-or-create-by-eid takes an eid and returns the matching animal or creates it, with a sync route to push session entries and an undo route for mistaken entries.

Create a chute session with POST /v1/farm/{farm_id}/chute-sessions and a config, then call POST /v1/farm/{farm_id}/animals/find-or-create-by-eid for each scanned eid

Key Endpoints

118 endpoints — the ranch.

METHOD

PATH

DESCRIPTION

GET

/v1/farm/{farm_id}/animals

List animals

GET

/v1/farm/{farm_id}/animals/lookup-by-eid

Look up an animal by EID

POST

/v1/farm/{farm_id}/animals/find-or-create-by-eid

Find or create an animal by EID

GET

/v1/farm/{farm_id}/scheduled-events/pending/approval

List events pending approval

POST

/v1/farm/{farm_id}/workflows/preview

Preview a workflow run

GET

/v1/farm/{farm_id}/farm-tasks

List farm follow-up tasks

GET

/v1/farm/{farm_id}/reports/inventory

Get inventory report

GET

/v1/farm

List farms

GET

/v1/farm/{farm_id}/animals

List animals

GET

/v1/farm/{farm_id}/animals/lookup-by-eid

Look up an animal by EID

POST

/v1/farm/{farm_id}/animals/find-or-create-by-eid

Find or create an animal by EID

GET

/v1/farm/{farm_id}/scheduled-events/pending/approval

List events pending approval

POST

/v1/farm/{farm_id}/workflows/preview

Preview a workflow run

GET

/v1/farm/{farm_id}/farm-tasks

List farm follow-up tasks

GET

/v1/farm/{farm_id}/reports/inventory

Get inventory report

GET

/v1/farm

List farms

Why Jentic?

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

Setup

Wiring Ranch.Bot by hand means completing the OAuth device flow against /oauth/device and /oauth/device/token, keeping the JWT fresh, and matching the required scopes and farm role listed per data operation. Through Jentic you install once, import Ranch.Bot from the API Directory, store the credential once, and your agent calls it.

Permission scoping

Ranch.Bot puts the farm id in the URL path (/v1/farm/{farm_id}/...), so a rule can pin your agent to one farm and the operations you pick. You choose the operations it may call, so destructive ones like DELETE /v1/farm/{farm_id}/animals/{animal_id} or workflow commits are not included unless you add them.

Credential isolation

Your Ranch.Bot 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 'look up an animal by EID' or 'approve pending farm events', and Jentic returns the matching Ranch.Bot operation with its input schema so the agent calls the right endpoint without reading the reference.

FAQs

Specific to using Ranch.Bot HTTP API through Jentic.

What authentication does the Ranch.Bot HTTP API use?

Per its OpenAPI spec, Ranch.Bot accepts an OAuth device access token in JWT format as a bearer token, with a deprecated LegacyKey bearer scheme for rb_sk_ keys. The /oauth routes, including device authorization and token exchange, are open and take a registered client_id. The /v1 data operations list required scopes such as read:animals or write:records and a minimum farm role, and PUT /v1/user/default-farm is declared for LegacyKey. Access is for directed developer use through support@ranch.bot.

What are the rate limits for the Ranch.Bot HTTP API?

The OpenAPI spec states a production limit of 100 requests per 15-minute window per legacy key or device account, 1000 per browser session, and otherwise per client IP. RateLimit headers report the current window, and clients should respect Retry-After on a 429 response.

Can I look up an animal by its EID tag with the Ranch.Bot HTTP API?

Yes. GET /v1/farm/{farm_id}/animals/lookup-by-eid looks up an animal by exact EID without writing anything. POST /v1/farm/{farm_id}/animals/find-or-create-by-eid takes an eid and creates the animal if no match exists.

Is there a Ranch.Bot MCP server?

You don't need an MCP server to give your agent Ranch.Bot. Jentic connects it directly from the API Directory: import it, store your token once, and your agent calls the animal, event, and workflow operations it needs, discovered on demand.

Can I limit what my agent is allowed to do with the Ranch.Bot HTTP API?

Yes. For example, write a rule that allows only the animal list, EID lookup, and records read operations under one farm_id, so the agent can answer herd questions for that ranch and cannot delete animals, commit workflows, or remove exports, and its calls are logged.

How do I approve scheduled farm events through Jentic?

Search Jentic for 'approve pending farm events', load GET /v1/farm/{farm_id}/scheduled-events/pending/approval to list them, then call POST /v1/farm/{farm_id}/scheduled-events/{scheduled_event_id}/approve for each one. To run it on your own infrastructure, install Jentic One from its GitHub repo.

Ranch.Bot HTTP API

AI ReadinessFoundational (C+)59/100

See full scorecard

Official vendor OpenAPI document · agent-readyProductivityTask Managementbearer118 EndpointsREST

For Agents

Read and update Ranch.Bot livestock records, look up animals by EID, schedule and approve farm events, track farm tasks, and run previewed workflows for a farm.

Use for: Look up the cow with EID 982000123456789, List all current animals on my ranch, Approve the vaccination events waiting for approval, Get this week's open farm follow-up tasks

Not supported: Does not handle crop field mapping, livestock sales marketplaces, or veterinary prescriptions. Use for Ranch.Bot livestock records, farm events, tasks, and workflows only.

The Ranch.Bot HTTP API keeps livestock records for farms and ranches: animals and their EID tag identifiers, groups, records, feedings, rations, and calving or birth events. It schedules and approves farm events, tracks follow-up farm tasks and recurring events, and runs chute sessions that log animals as they pass through the chute. Workflow templates let a farm preview a workflow run before committing it, and exports, imports, and inventory or AgriStability reports move data in and out, all scoped by farm_id.

Jentic One on Github View OpenAPI Document

Show dimension breakdown

Foundational Compliance

Base layer of spec validity and structural soundness.

Grade: CSignals: 4

92%

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).

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: A-Signals: 4

17%

Example Density

How richly the API is illustrated with examples.

100%

Example Validity

Percentage of examples that conform to their schemas.

72%

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

20%

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.

60%

Summary Coverage

Coverage of summaries across operations/tags/info.

Agent Usability

Functional utility, complexity comfort, and AI orchestration readiness.

Grade: A-Signals: 1

79%

Complexity Comfort

Agent comfort level based on API operational and structural complexity.

Security

Trust, risk posture, and security compliance.

Grade: B+Signals: 1

68%

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: C-Signals: 1

51%

Descriptive Richness

Clarity and depth of descriptions across API elements.

Connect the Ranch.Bot HTTP API to your agent

Capabilities

Start building with Ranch.Bot HTTP API

Use Cases

Key Endpoints

Why Jentic?

Related APIs

FAQs

Ranch.Bot HTTP API

Jentic AI Readiness Score

Ranch.Bot HTTP 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