Free forever, no credit card.Get Started for Free →
← All posts
November 20, 2026 · 5 min read

Does Bullhorn Remember Between Runs? The Candidate Record Endures. The Run Reasoning Does Not.

Does Bullhorn Remember Between Runs? The Candidate Record Endures. The Run Reasoning Does Not. Short answer: Bullhorn keeps a deep record for every candidate, client, and job, and that record holds a great deal. Contact details, parsed resume data, notes, calls, emails, submissions, and placements all survive between runs in one searchable database. Bullhorn Automation keeps follow-ups and data cleanup moving, and Amplify can search, match, and screen from those records. What does not survive i

Does Bullhorn Remember Between Runs? The Candidate Record Endures. The Run Reasoning Does Not.

Short answer: Bullhorn keeps a deep record for every candidate, client, and job, and that record holds a great deal. Contact details, parsed resume data, notes, calls, emails, submissions, and placements all survive between runs in one searchable database. Bullhorn Automation keeps follow-ups and data cleanup moving, and Amplify can search, match, and screen from those records. What does not survive in the same way is the work a scheduled run does across many candidates, clients, and job orders at once. The comparisons, the shortlist order, and the reasons behind both are not stored as a history the next run can load.

What one record keeps in Bullhorn

Bullhorn was built as an applicant tracking system and CRM for staffing and recruitment agencies, so its memory is organized around relationships. Candidate records, client accounts, job orders, and placements sit in the same system, and a recruiter and an account manager working the same client see the same history without switching tools.

Resume parsing fills much of that record automatically. When a resume is uploaded, Bullhorn extracts contact details, skills, and work history into structured fields, so a candidate becomes searchable data instead of a file in a folder.

Around that parsed base, the team adds the working record. Notes, calls, and emails attach directly to a candidate or client record. Submissions track who was put forward for a job order. Placements track who started, and where. Each record therefore answers a clear set of questions well: who this person is, what the resume says, who spoke to them, and where they stand right now.

That is durable, record-level memory. It is organized around one candidate, one client, or one job order at a time.

What automation and Amplify keep moving

Bullhorn Automation, formerly Herefish, handles the repetitive work around those records. It manages candidate nurture sequences, status update emails, data cleanup, and multi-step follow-ups triggered by changes in Bullhorn data. A status change can send prep material. A record left untouched for a set period can be flagged for re-engagement. The automation reads the current record and acts on it.

Amplify, Bullhorn's AI layer, reads from the same base. Amplify Chat answers questions about candidates, jobs, and clients using the firm's Bullhorn data. Search & Match ranks best-fit candidates from existing records against a new job. Higher tiers add screening, resume summaries, enrichment, and outreach, and the top tier adds digital workers that carry out multi-step work.

Notice what every layer reads from: the stored record as it stands today. Automation acts on a trigger. Chat answers from current data. Match ranks people against one job order. None of those layers was built to hold conclusions that belong to a run across all of them.

What a scheduled run loses overnight

Consider a routine that runs each evening across every open job order. It checks new applications, compares candidates submitted to more than one client, watches for placed contractors whose assignments are ending, and prepares a ranked shortlist for the morning.

During that pass, the run builds knowledge that exists in no single record. It decides that a candidate with a middling match for one order is the strongest option once a second submission and an older placement are read beside it. It notices that several clients are stalling at the same submission stage. It works out which ending assignments to contact first for a role that just opened, and why that order makes sense.

When the run ends, the records are still complete, the placements still show their dates, and the match scores can be regenerated on demand. The cross-client comparison, the shared stall pattern, and the shortlist order with its reasons were never written to a shared history the next run can load. The next evening starts from the raw records again and rebuilds the same judgments before any new work begins.

The cost is not lost candidate data. The data stayed in Bullhorn. 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 record, client account, or job order, 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. An evening screening run beside Bullhorn, an assistant drafting outreach, and a reporting step summarizing placements 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 order view.

Vilix AI stores full conversation history, not just facts extracted from it. For staffing work, that difference is practical. A stored fact can say a shortlist was ranked in a certain order. The full history shows what the run compared, which record it trusted when two submissions disagreed, and why a case was left open, so the next run can check the reasoning instead of repeating it.

With that layer, the evening changes. The first run saves its comparisons and open decisions to Vilix AI. The second run loads that work first, then spends its effort only on new applications and waiting cases. Bullhorn keeps the candidate record, the clients, and the placements. 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 placement 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.

Get Started for Free

Free forever, no credit card.

Get Started for Free

Persistent memory across ChatGPT, Claude, and the AI tools you already use in Vilix AI.

Get Started for Free

Free forever, no credit card.

Keep reading
Does Lemon Squeezy Remember Between Runs? The Customer Record Holds. The Run Reasoning Does Not.

Does Lemon Squeezy Remember Between Runs? The Customer Record Holds. The Run Reasoning Does Not. Ask whether Lemon Squeezy remembers between runs and the answer splits cleanly in two. Lemon Squeezy remembers the commercial state of a customer relationship in detail, because that is its job as a merchant of record for digital products. It does not remember what an automation or an AI agent was thinking while it worked on that customer. Those are different kinds of memory, and mixing them up is w

Does FastSpring Remember Between Runs? The Account Record Holds. The Run Reasoning Does Not.

Does FastSpring Remember Between Runs? The Account Record Holds. The Run Reasoning Does Not. Ask whether FastSpring remembers between runs and the answer splits cleanly in two. FastSpring remembers the commercial state of a customer relationship in detail, because that is its job as a merchant of record. It does not remember what an automation or an AI agent was thinking while it worked on that customer. Those are different kinds of memory, and mixing them up is where scheduled billing workflow

Does Paddle Remember Between Runs? The Customer Record Holds. The Run Reasoning Does Not.

Does Paddle Remember Between Runs? The Customer Record Holds. The Run Reasoning Does Not. Ask whether Paddle remembers between runs and the answer splits cleanly in two. Paddle remembers the commercial state of a customer relationship in detail, because that is its job as a merchant of record. It does not remember what an automation or an AI agent was thinking while it worked on that customer. Those are different kinds of memory, and mixing them up is where scheduled billing workflows quietly s