01 / What makes it useful
See why a role might fit
The analysis connects job requirements with evidence from the person’s own documents. Supporting quotes must match the source text, helping keep the recommendation grounded.
Job search · Personal workspace · Local by design
employed
Less time sifting.
More focus on the right roles.
employed helps a job seeker turn a flood of remote vacancies into a manageable shortlist. It checks location and experience requirements, explains a possible fit and keeps applications organised in one workspace.
- For
- People seeking remote work
- Role
- Design and full build
- Availability
- Local personal workspace
What it makes possible.
02 / What makes it useful
Check eligibility before investing time
A remote label does not always mean a job is open to everyone. Location and experience checks help surface restrictions before the applicant commits time to a detailed application.
03 / What makes it useful
Keep searching when AI is unavailable
Job collection, basic filtering and ranking still work without an AI connection. The workspace makes it clear which deeper analyses are unavailable.
The everyday essentials.
A more deliberate job search, from finding an opening to following up on an application.
Look beyond a single job board
Gather openings from public job sites, company careers pages and a personal company watchlist.
Clear out obvious mismatches
Location, seniority and unwanted terms help filter out roles that do not meet the search criteria.
Understand a promising role
Ask for an analysis of a specific vacancy to see eligibility requirements and how your experience relates to them.
Put existing experience to work
Use CVs, portfolio documents and notes to build a profile of capabilities with supporting evidence.
Keep track of what happens next
Move roles through a clear application board, from discovery and analysis to application, interview and outcome.
Choose the AI service
Connect a supported AI provider or a local model, depending on how you want to run your search.
For the curiousBehind the buildExplore the architecture and tools.
Architecture
From thousands of postings to evidence you can trust.
Hover or tap a component to trace its connections.
Job sources
Seven aggregators plus resolved company boards
- JSON
- RSS
- ATS APIs
- Harvester · postings
Harvester
Fetches and normalises postings politely
- httpx
- selectolax
- Filter cascade · normalised
Filter cascade
Geo, seniority, anti-terms and title signal, then ranking
- Deterministic
- Analysis agent · shortlist
Evidence check
Rejects any quote that is not verbatim in its source
- Pydantic
- Local store · verified only
ATS resolver
Detects each careers page's job board and verifies it live
- Greenhouse
- Lever
- Ashby
- Job sources · verified boards
Profile documents
CVs and notes read into evidenced capabilities
- pypdf
- python-docx
- Analysis agent · evidence spans
Analysis agent
Eligibility, requirement matrix and approach notes
- Any provider
- Degraded mode
- Evidence check · verdicts + quotes
Local store
Postings, profile, runs and decisions in ~/.employed
- SQLite
- Dashboard · review and decide
Command line
Harvest, resolve, match and analyse on a schedule
- Typer
- Rich
- Local store · runs
Dashboard
Board, job workspace, profile, sources and agent pages
- FastAPI
- Jinja
- HTMX
All connections
- ATS resolver to Job sources: verified boards
- Job sources to Harvester: postings
- Harvester to Filter cascade: normalised
- Filter cascade to Analysis agent: shortlist
- Profile documents to Analysis agent: evidence spans
- Analysis agent to Evidence check: verdicts + quotes
- Evidence check to Local store: verified only
- Command line to Local store: runs
- Local store to Dashboard: review and decide
Technology stack
What it is built with.
Application
- Python
- FastAPI
- Uvicorn
- Pydantic
Interface
- Jinja
- HTMX
- No build step
Harvesting
- httpx (HTTP/2)
- selectolax
- Playwright (optional)
Data and documents
- SQLite
- pypdf
- python-docx
- PyYAML
Tooling
- Typer
- Rich
- pytest
Next project