← all tools
Recruiting CRM / ATS

Atlas

A recruitment CRM built for AI, so the agent writes into it cleanly.

Cost per callBYOK · vendor billed
Your own keyrequired
CategoryRecruiting CRM / ATS

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.

things you can ask for

  • Take this job brief url, build a longlist with Prospeo and AI Ark, and push it into the project
  • Read this candidate profile url, then use Exa and Apollo to find recently funded companies they would fit, and log those as opportunities
  • Move these candidates to the next stage and file the Fathom notes
  • Do we have this company already, or should I enrich it with ZoomInfo?

works well with Atlas

  • Prospeo

    the enrichment that fills an Atlas project

  • Exa

    research a company before it becomes an opportunity

  • Fathom

    interview notes written straight onto the candidate

  • Instantly

    outreach off an Atlas shortlist

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 →

What your agent reads before it touches Atlas

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 →
Show the raw playbookwritten for the agent

HOW in lib/atlas.py.

Auth & config

  • Base URL: https://api.recruitwithatlas.com/api/v1 · Auth: Authorization: Bearer <JWT> (env ATLAS_API_KEY; never hardcode). list_projects() is a safe read-only pilot.
  • Every path is confirmed against the official OpenAPI 3.1 spec.

Terminology (Atlas models people once)

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.

Operations

  • Companies (dedup + enrichment): list / get / find / create / update_company.
  • People: search_people, lookup_people, get / create / update_person, add_person_note.
  • Projects (jobs): list / get / create_project, list_project_stages, list_project_candidates, add_candidate_to_project, add_project_applicant, move_candidate_to_stage.
  • Opportunities (deals): list / get / create_opportunity, list_opportunity_stages.
  • The long tail (campaigns, meetings, interviews, fees, files, placements, users, custom attributes) is reachable through the generic request() passthrough.

Cost

ATS reads and writes are free. Writes are side-effecting and pass through the approval gate.

Handoff

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.