A recruitment CRM built for AI, so the agent writes into it cleanly.
Atlas is newer than the rest and designed around structured data, which means fewer surprises when an agent pushes into it. Candidates, companies, projects and deals are all readable and writable, so sourcing and business development share one record.
Atlas is a destination, and its projects can start a sourcing run of their own.
Ask for the outcome and your agent composes the run itself. Or start from a skill, a whole pipeline it already knows end to end.
browse all skills →Every tool ships with a written playbook, and the agent loads it before the first call. Auth, rate limits, what each call costs, which actions need your approval, and the mistakes worth avoiding. It is the difference between an agent that knows the tool and one that guesses at it.
Read the Atlas docs →HOW in lib/atlas.py.
https://api.recruitwithatlas.com/api/v1 · Auth: Authorization: Bearer <JWT> (env
ATLAS_API_KEY; never hardcode). list_projects() is a safe read-only pilot.person = one record with many roles (candidate / contact / lead) · company · contact = a company-contact junction, at most one live per person · project = a job · candidate = a person's candidacy within a project pipeline · opportunity = a deal · placement.
list / get / find / create / update_company.search_people, lookup_people, get / create / update_person, add_person_note.list / get / create_project, list_project_stages,
list_project_candidates, add_candidate_to_project, add_project_applicant,
move_candidate_to_stage.list / get / create_opportunity, list_opportunity_stages.request() passthrough.ATS reads and writes are free. Writes are side-effecting and pass through the approval gate.
Read list_projects to learn what the agency is hiring for, source and enrich against it, then write the
candidate back into the matching project pipeline.