A8gent
ATS Data Readiness · Lesson 1 of 15

Audit Your ATS Before Connecting An Agent

An agent syncing into a messy ATS just spreads the mess faster. Learn to audit fields, stages, tags, and notes in Bullhorn, Recruit CRM, or Greenhouse first.

Your ATS is the source, and the source is usually messy

Recruiting agents read and write to your applicant tracking system. Whether you run Bullhorn, Recruit CRM, or Greenhouse, the agent is only as good as the data already in there. If your candidate records are half-empty, your pipeline stages mean different things to different recruiters, and your notes are a wall of shorthand, the agent will produce confident, wrong output. Fix the source before connecting anything.

What to audit

  • Fields: which candidate fields are reliably filled (current title, location, availability, right to work, salary expectation) and which are blank most of the time. An agent cannot qualify on a field that is empty in 60 percent of records.
  • Stages: whether your pipeline stages are used consistently. If "submitted" sometimes means sent to client and sometimes means shortlisted internally, an agent updating stages will corrupt your reporting.
  • Tags and categories: whether skills, specialisms, and source tags follow a convention or are freeform chaos.
  • Notes: whether recruiter notes are structured enough to summarize, or are private shorthand that only the writer understands.
  • Source quality: where candidates came from, and whether duplicates are merged or scattered across records.

How to run the audit

  1. Pull a sample of 30 to 50 recent candidate records and check each field for how often it is actually populated.
  2. List every pipeline stage and ask two recruiters what each one means. Where they disagree, you have a problem the agent will inherit.
  3. Read 20 real note fields and mark whether an outsider could understand them.
  4. Write a one-page data readiness report: what is reliable, what is not, and what must be cleaned before build.

What good looks like

You can point at the handful of fields an agent can trust today, name the stages that are used consistently, and list the gaps you will fix first. The candidate records the agent reads are structured enough that a summary of one would be accurate.

Common mistakes

  • Treating messy notes as a trusted source of truth and letting the agent make decisions on them.
  • Connecting an agent to a full pipeline before confirming stages mean the same thing to everyone.
  • Assuming the ATS vendor's clean demo data resembles your real, lived-in database.