Free forever, no credit card.Get Started for Free →
← All posts
November 20, 2026 · 6 min read

Does SmartRecruiters Remember Between Runs? The Candidate Record Scores. The Run Reasoning Does Not.

Does SmartRecruiters Remember Between Runs? The Candidate Record Scores. The Run Reasoning Does Not. Short answer: SmartRecruiters keeps a rich record for every candidate, and that record holds a great deal. Contact details, the parsed resume, tags, the current stage in a hiring workflow, reviews and ratings from the hiring team, shared notes, and message history all survive between runs. The platform also scores candidates against a job and searches talent pools and past applicants for new mat

Does SmartRecruiters Remember Between Runs? The Candidate Record Scores. The Run Reasoning Does Not.

Short answer: SmartRecruiters keeps a rich record for every candidate, and that record holds a great deal. Contact details, the parsed resume, tags, the current stage in a hiring workflow, reviews and ratings from the hiring team, shared notes, and message history all survive between runs. The platform also scores candidates against a job and searches talent pools and past applicants for new matches. What does not survive in the same way is the work a scheduled run does across many candidates and many jobs 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 candidate record keeps in SmartRecruiters

Every candidate in SmartRecruiters sits in a central candidate database, with a profile built around that person. Resume parsing reads the resume and stores the data in a structured format, so experience and skills become searchable fields instead of text buried in a file.

Around that parsed record, the team adds its own layer. Recruiters and hiring managers share notes on the profile and rate candidates, so an opinion recorded by one person is visible to the rest of the team later. Tags mark candidates for later searches. Messages sent to the candidate, including SMS and WhatsApp as well as online chat, stay attached to the record, and interview scheduling moves the candidate through the workflow for the job.

Each job tracks its applicants across its own workflow stages, and the dashboard shows progress and status changes as candidates move. Bulk actions can message, reject, tag, or change the status of many candidates in a pipeline at once.

That is durable, person-level memory: who the candidate is, what the resume says, where the candidate stands in a workflow, and what the team recorded. It is organized around one person in one job at a time.

What pools and the matching engine keep

SmartRecruiters also remembers beyond a single application. Its CRM side holds candidates in talent pools so they can be sourced and nurtured for future roles instead of disappearing when one job closes. A person who was a near miss last quarter stays findable next quarter.

SmartAssistant, the matching tool SmartRecruiters released in 2018, works on top of that stored base. When a job is posted or edited, SmartAssistant looks into the company's existing talent pools and past applicants to identify who might be a qualified candidate for the role, and it generates a match score for candidates. The AI-powered candidate summary shows the candidate's star rating and the share of high-priority and other skills found in the resume.

Winston, the AI recruiting companion launched in 2025, adds a conversational layer. Winston Companion answers questions from recruiters and hiring managers about jobs, pipelines, and processes, and Winston Match breaks its scores into sub-scores for education, skills, and experience so ranking decisions stay consistent.

Notice what all of these layers read from: the stored candidate record. Pools hold people. Scores rate a person against a job. The companion answers from the current state of the database. None of them 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. It checks new applications, reads fresh match recommendations, compares candidates who applied to more than one job, watches the talent pools for people who fit a role that just reopened, and prepares a ranked shortlist for the morning.

During that pass, the run builds knowledge that exists in no single profile. It decides that a candidate with a middling score for one job is the strongest option once a second application and an older pool record are read beside it. It notices that several shortlisted candidates are stalling at the same workflow stage. It works out which pool members to contact first for the reopened role, and why that order makes sense.

When the run ends, the profiles are still complete, the pools still hold the same people, and the scores can be regenerated on demand. The cross-job 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 SmartRecruiters. 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, pool, or job, 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 SmartRecruiters, 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's pipeline 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 a shortlist was ranked in a certain order. The full history shows what the run compared, which record it trusted when two applications 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. SmartRecruiters keeps the candidate record, the pools, and the scores. 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.

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