Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Fergus 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%2Ffergus.com%2Ffergus" | shStep 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%2Ffergus.com%2Ffergus" | sh
jentic register # connects your agent to your Jentic One instanceJentic 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.
What an agent can do with Fergus API.
Create and update jobs with phases, statuses, and assigned tradespeople
Generate quotes against jobs and convert them into customer invoices
Track time entries logged by field staff against specific jobs
Schedule calendar events tied to jobs and assigned users
Search customers and sites with substring filters across name and section fields
GET STARTED
Maintain a pricebook with tiered pricing for parts and labour
Patterns agents use Fergus API for, with concrete tasks.
★ Quote-to-Invoice Trade Workflow
Automate the path from job creation through quote acceptance to invoice issue for trades businesses. The Fergus API exposes /jobs, /jobs/{id}/quotes, and /customer-invoices as related endpoints so an agent can move work through pipeline stages without manual data entry. Eliminates the typical 15-20 minute admin overhead per job common in plumbing and electrical contractors.
Create a job, attach a quote with three line items, finalise it via PUT /jobs/{jobId}/finalise, then generate the customer invoice
Field Staff Time Tracking
Pull time entries logged by tradespeople against jobs to compute payroll hours and job profitability. The Fergus API surfaces time entries with job and user filters, so an agent can summarise hours per job, per person, or per period. This replaces spreadsheet-based timesheet collation common in small trades businesses.
GET /time-entries filtered by user_id and date range for the last fortnight, sum hours per jobId, and return the top 5 jobs by labour cost
Customer and Site Lookup
Use Fergus's substring search parameters such as filterSearchText to find customers, sites, or jobs without exact-match requirements. This supports natural-language agent queries like 'find the Smith job on Queen Street' against a corpus of thousands of records. Lookup endpoints include /customers, /sites, and /jobs with consistent filtering semantics.
GET /customers?filterSearchText=Smith and return the top 5 matches with their associated sites
AI Agent Job Status Updates
Through Jentic, an agent can answer end-of-day questions like which jobs were finalised today and which quotes are awaiting customer acceptance. Jentic exposes Fergus's job, quote, and invoice operations as discoverable tools, letting a Claude or GPT agent generate daily summaries from natural-language requests. This removes the need for custom dashboards in small trades businesses.
Search Jentic for 'list jobs', filter by updatedAt for today, and return a markdown summary grouped by status
74 endpoints — the fergus api provides programmatic access to the fergus job management platform used by trades businesses such as plumbers and electricians.
METHOD
PATH
DESCRIPTION
/jobs
List jobs
/jobs
Create a job
/jobs/{jobId}/finalise
Finalise a job
/jobs/{jobId}/phases
List job phases
/favourites
List favourites
/jobs
List jobs
/jobs
Create a job
/jobs/{jobId}/finalise
Finalise a job
/jobs/{jobId}/phases
List job phases
/favourites
List favourites
What agents get from Jentic-routed access to this vendor.
Setup
Wiring the Fergus API by hand means choosing between Personal Access Token and OAuth2 auth, sending the bearer header, and threading job ids through 74 trades endpoints yourself. Through Jentic you install once, import the Fergus API from the API Directory, store the token once, and your agent calls it.
Permission scoping
Fergus puts the job id in the URL path (/jobs/{jobId}/phases, /jobs/{jobId}/finalise), so a rule can pin your agent to the jobs you allow. You choose the operations it may call, so a state change like finalising a job is not included unless you add it.
Credential isolation
Your Fergus Personal Access Token or OAuth2 credentials are stored once, encrypted, by your own Jentic One instance and injected at execution time. The raw bearer token never enters the agent's prompt, logs, or context.
Intent-based discovery
Agents search Jentic by intent such as 'create a job' or 'list job phases', and Jentic returns the matching Fergus operation with its input schema, so the agent calls the right endpoint without reading the developer docs.
Alternatives and complements available in the Jentic catalogue.
Specific to using Fergus API through Jentic.
What authentication does the Fergus API use?
The Fergus API supports two methods: a Personal Access Token sent as a bearer token, and OAuth2 for delegated access. Through Jentic both methods are stored encrypted in your Jentic One instance and never enter agent context.
What are the rate limits for the Fergus API?
Fergus enforces 100 requests per minute per company, shared across all endpoints regardless of which token is used. Responses include x-ratelimit-limit, x-ratelimit-remaining, x-ratelimit-reset, and a retry-after header on 429s.
Can I finalise a job through the Fergus API?
Yes. Fergus exposes a dedicated PUT /jobs/{jobId}/finalise endpoint, separate from the generic update job call, so closing out a job is an explicit action with its own audit trail.
How do I create a quote for a job through Jentic?
Search Jentic for 'create job quote', load the POST /jobs/{jobId}/quotes schema, and execute with the line items. Run pip install jentic and from jentic import Jentic to get started.
Does the Fergus API support free-text search on lists?
Yes. Many list endpoints accept filterSearchText and filterSectionName query parameters with substring matching across searchable fields, so agents can find records without exact-match IDs.
Can the Fergus API track time logged against jobs?
Yes. The /time-entries endpoints let you list, retrieve, and create entries linked to specific jobs and users, supporting payroll and job profitability workflows.
Can I limit what my agent is allowed to do with the Fergus API?
Yes. Because you run your own self-hosted Jentic One instance, your rules decide which Fergus operations and credentials the agent may use. Since Fergus puts the job id in the URL path, such as /jobs/{jobId}/phases and /jobs/{jobId}/finalise, you can pin the agent to the jobs you allow. You also choose the operations it may call, so a state change like finalising a job through PUT /jobs/{jobId}/finalise is excluded unless you add it.
For Agents
Manage trade-services jobs, quotes, invoices, time entries, and calendar events for plumbers and electricians using Fergus, with bearer token or OAuth2 auth.
Use for: Find all jobs assigned to a specific tradesperson, Create a quote for a new plumbing job, List all overdue customer invoices, Retrieve time entries logged against a job last week
Not supported: Does not handle payroll, accounting ledgers, or payment processing - use for trades job management, quotes, invoices, and scheduling only.
The Fergus API provides programmatic access to the Fergus job management platform used by trades businesses such as plumbers and electricians. It exposes 74 endpoints for jobs, quotes, customer invoices, sites, contacts, time entries, calendar events, pricebooks, and notes, with text-search query parameters across many list operations. Authentication supports both Personal Access Tokens and OAuth2, and the API enforces a rate limit of 100 requests per minute per company.