Does JazzHR Remember Between Runs? The Profile Persists. The Job-Specific Work Does Not.
Does JazzHR Remember Between Runs? The Profile Persists. The Job-Specific Work Does Not. Short answer: JazzHR keeps one candidate profile as the central location for candidate data, and that profile holds a lot. Contact details, the resume and application, discussion notes, votes, emails, and documents all survive between runs. What does not survive in the same way is job-specific work. Documents, questionnaires, interviews, evaluations, assessments, and scorecards tied to one job do not transf
Does JazzHR Remember Between Runs? The Profile Persists. The Job-Specific Work Does Not.
Short answer: JazzHR keeps one candidate profile as the central location for candidate data, and that profile holds a lot. Contact details, the resume and application, discussion notes, votes, emails, and documents all survive between runs. What does not survive in the same way is job-specific work. Documents, questionnaires, interviews, evaluations, assessments, and scorecards tied to one job do not transfer when a candidate is added to another job, and the cross-candidate reasoning a scheduled run builds across many profiles is not stored for the next run at all.
That split is easy to miss, because the profile looks complete from the inside. Open a candidate and the history is there. Look for what a run concluded across the whole pipeline, and that layer has no home.
What one candidate profile keeps in JazzHR
The candidate profile is where JazzHR puts core information and key actions in one place. The header shows location, phone number, email address, and source, and that contact layer can be edited at any time. From the same header, a reviewer can request a comment from someone outside JazzHR, send an email, create a task, watch a candidate, or add the candidate to another job.
The tabs separate the record by kind. The Profile tab holds the resume, the job application, and the full profile. The Interviews tab holds interview guides and scheduling. The Scorecard tab holds a scorecard when one is added to the job. The Assessments tab houses evaluations and background checks. The Emails tab sends and stores individual and bulk communications. The Documents tab holds files uploaded through a questionnaire, plus offer letters and eSignature documents.
Three controls sit above the tabs: Reject, Vote, and Advance. A vote is tracked on the Discussion tab and counts as a maybe, a way to register an opinion without rejecting or advancing the candidate yet.
That is durable, person-level memory. It answers who the candidate is, which job they applied to, and what the team recorded about them in that job.
What discussion keeps, and what stays job-specific
The Discussion tab tracks the team conversation about a candidate. Teammates can be mentioned there, status changes appear there, and votes are stored there. Feedback requested from a non-JazzHR reviewer also lands on Discussion, so outside comment joins the same thread as internal notes.
JazzHR draws a clear line when a candidate moves. Add a candidate to another job from the profile header, choose a workflow status for the new placement, and any workflow helper on that status can be triggered during the move. The candidate carries over. Part of the record does not.
Job-specific data does not transfer between jobs. That list is explicit: documents, questionnaires, interviews, interview guides, evaluations, assessments, and scorecards stay with the original job view. Non-job-specific data stays accessible: emails remain, and the Discussion tab remains when it is set to All Jobs. A profile can be toggled between job views to see each job's specific information.
Search adds a third kind of recall. Quick Search finds a candidate by name, email, or phone from any page. The Candidates page offers more than twenty combinable search and filter options, covering job, workflow status, recruiter, category, and rating, plus profile, questionnaire, and custom field filters. Saved search filters can be reused, and results can be sorted. Workflows add automation on top: customizable stages, workflow helpers attached to a stage or disposition, email triggers, and knockout questions that filter candidates early.
All of that helps a person find and revisit a candidate fast. Notice the shape, though. Every layer is organized around one candidate, or around one job's view of that candidate. None of them was built to hold conclusions that belong to a run: that two jobs are drawing from the same small group, that one stage is where strong candidates keep stalling, or that a priority order was set for reasons recorded nowhere.
What a scheduled run loses overnight
Consider a routine that runs each morning across open jobs. It sweeps new applications, checks candidates who sit in more than one pipeline, compares scorecards and evaluations that point in different directions, and prepares a priority order for the day, grouped by job.
During that sweep, the run builds knowledge that exists in no single profile. It decides that a candidate strong in one job view looks weaker once the other job's interview notes are read beside it. It notices that several stalls share one stage. It traces a pattern to one source or one knockout question that is filtering harder than intended.
When the run ends, the profiles are still complete. The discussions still hold every note and vote. The cross-job comparison, the shared stall cause, and the priority order were never written to a shared history the next run can load. The next morning starts from the raw profiles again and rebuilds the same groups before any new work begins.
The cost is not lost data. The data stayed in JazzHR. The cost is repeated reasoning, paid in full on every run, for work that was already done well once.
Give the runs one shared memory
Vilix AI is built for that missing layer: one memory held outside any single candidate profile or job view, which every run can load before it starts and update before it ends.
It is cloud-hosted, so there is zero infrastructure to run or maintain. No separate store has to be provisioned and keyed to candidate IDs by hand just so an automation can keep its own working notes between runs.
Every connected tool reaches the same memory over MCP. A morning screening run beside JazzHR, an assistant drafting outreach, and a reporting step summarizing pipeline movement can all read and write the same Vilix AI memory. The same memory follows the work everywhere, across tools and devices, instead of ending at the edge of one job view.
Vilix AI stores full conversation history, not just facts extracted from it. For hiring work, that difference is practical. A stored fact can say two job views were compared for one candidate. The full history shows what the run compared, which view it trusted, and why a case was left open, so the next run can check the reasoning instead of repeating it.
With that layer in place, the morning changes. The first run saves its comparisons, patterns, and open decisions to Vilix AI. The second run loads that saved work first, then spends its effort only on new applications and cases still waiting. JazzHR keeps the profile and the discussion. Vilix AI keeps what the runs learned across them.
Start free, keep control of the data
Vilix AI has a free plan forever, with no time limit forcing a choice. Paid plans start with a 7-day Pro trial with no credit card required, so a full hiring cycle can be tested before any payment.
Data stays under the team's control. Everything can be exported at any time, and everything can be deleted at any time.