Official vendor OpenAPI document · agent-readyHR recruitingRecruiting AtsapiKey1 EndpointsREST
For Agents
Search aggregated tech and remote job listings via a single GET /jobs endpoint authenticated with a Token API key.
Use for: Search for remote Python developer jobs, Find recent tech job listings in Berlin, List all senior backend roles posted this week, Retrieve jobs matching a saved keyword filter
Not supported: Does not handle job posting, application submission, or applicant tracking - use for searching aggregated tech and remote job listings only.
The Findwork API exposes a single endpoint that returns aggregated tech and remote job listings sourced from multiple boards, returned as JSON over Django REST Framework. Authentication is performed by sending an Authorization header with the value Token YOUR_API_KEY. The API is used by job aggregators, agent-driven job search assistants, and dashboards that surface relevant tech roles without scraping individual ATS sites or maintaining their own crawler.
Install Jentic One Beta
Connect the Findwork API to your agent
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Findwork 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.
1
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%2Ffindwork.dev%2Ffindwork" | sh2
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%2Ffindwork.dev%2Ffindwork" | 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.
Capabilities
What an agent can do with Findwork API.
Search aggregated tech job listings filtered by keyword, location, and remote flag
Return company name, role, and application URL for each matching listing
Page through job results to power dashboards and digest emails
Surface listings sourced across multiple boards in a single normalised response
Drive an agent loop that re-queries on a schedule for new matches
Use Cases
Patterns agents use Findwork API for, with concrete tasks.
★ Personal Job Search Assistant
Job seekers can have an agent call GET /jobs with their saved keywords on a schedule and email a daily digest of new matches. Because Findwork normalises listings across multiple boards into a single response, the assistant does not need to integrate with each ATS individually and the seeker sees fewer duplicates.
Call GET /jobs with the saved keyword and remote=true, dedupe against yesterday's results, and email the new listings.
Remote-Only Talent Dashboard
Talent teams hiring remote tech staff can build a dashboard backed by GET /jobs filtered to remote roles in their stack. The agent walks the result pages and renders a leaderboard of competing job posts, helping the team benchmark their own listing against the live market.
Page through GET /jobs with remote=true and a stack filter, rank by company posting frequency, and render the dashboard.
Newsletter Curation
Tech newsletter operators can have an agent pull GET /jobs filtered by their audience's stack and surface a weekly top-ten section. Findwork's aggregation means a single API call replaces five or six per-board scrapers and the curator can spend their time on commentary rather than collection.
Call GET /jobs with the newsletter's keyword set, rank by recency and prestige signals, and select ten for the issue.
AI Agent Findwork Integration via Jentic
An agent connected to Jentic can search by intent (for example find remote python jobs) and Jentic returns the Findwork GET /jobs operation along with its query parameters. The Token API key lives in the vault, so the agent never embeds the credential. Integration drops from a one-day setup to a single search-load-execute call.
Search Jentic for find remote tech jobs, load GET /jobs, and execute with search and remote query parameters while Jentic injects the token.
Key Endpoints
1 endpoints — the findwork api exposes a single endpoint that returns aggregated tech and remote job listings sourced from multiple boards, returned as json over django rest framework.
METHOD
PATH
DESCRIPTION
GET
/jobs
Search aggregated tech and remote job listings
GET
/jobs
Search aggregated tech and remote job listings
Jentic AI Readiness Score
This API is usable in Jentic One now. Its AI-readiness score against Jentic's framework shows where it stands today and where improvements would make it even easier for agents to use.
F
Findwork API
- AI-Aware (B+)70/100
100
Foundational Compliance63
Developer Experience & Jentic Compatibility56
AI-Readiness & Agent Experience94
Agent Usability50
Security100
AI DiscoverabilityPowered by JenticScoring Framework 1.0.0 | Scoring Engine 0.4.0
Show dimension breakdown
100
Foundational Compliance
Base layer of spec validity and structural soundness.
Grade: A+Signals: 4
99%
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).
100%
Structural Integrity
Structural correctness score based on schema issues using logarithmic dampening.
63
Developer Experience & Jentic Compatibility
Clarity, completeness, and ingestion readiness for developers and tooling.
Grade: B-Signals: 4
0%
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.
56
AI-Readiness & Agent Experience
Semantic breadth, depth, and agent comprehension for AI systems.
Grade: CSignals: 4
73%
Description Coverage
Coverage of descriptions across API elements.
0%
Error Standardization
Coverage of RFC 9457 Problem Details for error responses.
100%
OperationId Quality
Coverage, uniqueness, and casing consistency of operationIds for AI inference.
50%
Summary Coverage
Coverage of summaries across operations/tags/info.
94
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.
50
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).
100
AI Discoverability
Findability, semantic richness, and reasoning readiness.
Grade: A+Signals: 1
100%
Descriptive Richness
Clarity and depth of descriptions across API elements.
Score it yourself
Every API in the directory is allowlisted, so you can re-score it with no key required.
npx @jentic/api-scorecard-cli score <openapi-url>Why Jentic?
What agents get from Jentic-routed access to this vendor.
Setup
Wiring the Findwork API by hand means sending the token in the Authorization header, pointing at findwork.dev/api, and constructing the query filters on its single job-search route yourself. Through Jentic you install once, import the Findwork API from the API Directory, store the token once, and your agent calls it.
Permission scoping
Findwork exposes a single read-only job-search operation with its target carried as query filters rather than an owned-resource path id, so scope the agent to that one search operation and nothing else. Because you choose the allowed operation, the agent only reads the listings the search returns.
Credential isolation
Your Findwork token is stored once, encrypted, by your own Jentic One instance and injected at execution time. The raw token never enters the agent's prompt, logs, or context.
Intent-based discovery
Agents search Jentic by intent such as 'find remote python jobs', and Jentic returns the Findwork job-search operation with its query parameter schema, so the agent does not need to read the API docs.
Related APIs
Alternatives and complements available in the Jentic catalogue.
FAQs
Specific to using Findwork API through Jentic.
What authentication does the Findwork API use?
Findwork uses a token API key sent in the Authorization header in the format Token YOUR_API_KEY. Through Jentic the token lives in the encrypted vault and is injected at execution; the agent only ever sees a vault reference.
Can I filter Findwork results to remote roles only?
Yes. GET /jobs accepts a remote query parameter that filters to listings flagged as remote. Combine it with the search parameter to narrow to a specific stack such as Python or React.
What are the rate limits for the Findwork API?
Findwork applies per-API-key throttling and the spec does not publish a fixed RPS. Free keys are limited more aggressively than commercial keys. Agents should respect 429 responses with exponential backoff and cache results when polling on a schedule.
How do I find remote Python jobs through Jentic?
Search Jentic for find remote python jobs, load GET /jobs, and execute with search=python and remote=true. Jentic injects the token from the vault and Findwork returns the matching listings.
Does Findwork provide application URLs for each listing?
Yes. Each result in the GET /jobs response includes the source application URL, so an agent can present the apply link directly without redirecting through the Findwork site.
Is the Findwork API free to use?
Findwork has a free developer tier with a daily request quota and paid tiers for higher volume. Both tiers use the same single GET /jobs endpoint and the same Token authentication scheme.
Can I limit what my agent is allowed to do with the Findwork API?
Yes. Findwork exposes a single read-only job-search operation, GET /jobs, and because Jentic One is self-hosted your own rules decide which operations and credentials the agent may use. You can scope the agent to that one search operation and nothing else, so it can only read the listings a GET /jobs query returns and cannot reach any other route. The target is carried as query filters such as search and remote rather than an owned-resource path, so there is no write or delete surface for the agent to touch.
GET STARTED