Free forever, no credit card.Get Started for Free →
← All posts
November 19, 2026 · 5 min read

Does Workable Remember Between Runs? The Timeline Persists. The Screening Work Does Not.

Does Workable Remember Between Runs? The Timeline Persists. The Screening Work Does Not. Short answer: Workable keeps the candidate record and a full timeline of what happened to that candidate. It does not keep what a scheduled run concluded while working across many candidates at once. The profile and the timeline survive the night. The sorting, grouping, and judgment built on top of them do not, unless that work is saved somewhere the next run can load. That distinction matters because Work

Does Workable Remember Between Runs? The Timeline Persists. The Screening Work Does Not.

Short answer: Workable keeps the candidate record and a full timeline of what happened to that candidate. It does not keep what a scheduled run concluded while working across many candidates at once. The profile and the timeline survive the night. The sorting, grouping, and judgment built on top of them do not, unless that work is saved somewhere the next run can load.

That distinction matters because Workable looks well remembered from the inside. Open any candidate and there is history. Run an automation over fifty candidates, close the run, and the history that automation created in its own head is gone.

What a candidate profile keeps in Workable

Workable gives every candidacy its own profile. When the same person is considered for more than one job, there is a unique profile for each job, and the Candidates page shows the most recent one by default, with the others nested under an "Also in" note for the remaining jobs. Each profile holds the application details for that job: what the candidate submitted, a resume when one was uploaded, answers to application questions, custom fields, and referral information when a referral brought the person in.

Around that profile sits a searchable candidate database. Recruiters can search and filter across everyone who applied, was sourced to a job, or was added to the Talent Pool, using keywords, tags, location, custom fields, and evaluations. A candidate found months later is not a blank card. The record carries the latest experience and education, the source, the current stage, and the most recent evaluation score.

That is durable memory for a person in a role. It answers where someone stands and what they sent. It does not answer what a run learned by comparing that person with everyone else in the same batch.

What the timeline keeps, and what it cannot hold

The second layer is the Timeline. For each candidate, the Timeline gives a chronological view of activities and interactions: emails sent, interviews scheduled, notes left, and other significant events. Email threads are logged there automatically, evaluations sit alongside the record, and comments stay attached to the candidate.

The Talent Pool extends that persistence beyond a single opening. The pool stores candidates who do not fit an active job but should be considered for future roles, in stages for all, sourced, and applied candidates. When a pool candidate is moved to a job, the content of the timeline, including emails and comments, moves along with the person. Workable can also resurface candidates already in the database, including the Talent Pool, when a new job opens, drawing in part on sentiment in earlier internal feedback.

All of that is real retention, and it helps a human reviewer enormously. A reviewer can reconstruct what happened to one candidate without digging through inboxes.

Notice the shape, though. The Timeline remembers events tied to one candidate, in order. It was not built to hold conclusions that belong to no single candidate: that three separate profiles point to the same person, that one source keeps producing the strongest applicants for one team, or that a small set of candidates is blocked by the same missing feedback. Those conclusions live across records, not inside one timeline.

What a scheduled run loses overnight

Consider a routine that runs before the working day starts. It sweeps new applications across several jobs, checks for likely duplicates across jobs, groups people who applied twice under different details, notes where evaluations point in opposite directions, and prepares a short priority list for recruiters.

During the sweep, the run builds knowledge that exists nowhere in a profile. It decides that two per-job profiles are one person who should be reviewed once. It notices a pattern in which sources are working for one role and failing for another. It groups four apparently separate stalls and traces them to one shared cause.

When the run ends, the profiles are still complete. The timelines still show every email, interview, and note. The duplicate call, the source pattern, and the shared cause behind the stalls are not stored as a shared history the next run can load. Without a hand-built store, keyed and shaped the same way every time, the next morning starts from the raw profiles again and rebuilds the same groups, the same pattern, and the same priority list before it can do anything new.

The cost is not lost data. The data stayed. The cost is repeated reasoning, paid again 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 profile or timeline, 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 database has to be provisioned, keyed to candidate IDs by hand, and kept in sync just so an automation can keep its own screening notes between runs.

Every connected tool reaches the same memory over MCP. A screening run beside Workable, 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 candidate profile.

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 candidate was grouped with another profile. The full history shows what the run compared, what it set aside, and why it left a case open for a human, 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 groups, patterns, and open decisions to Vilix AI. The second run loads that saved work first, then spends its effort only on new applications and on cases that are still waiting. Workable keeps the record and the timeline. Vilix AI keeps what the runs learned from working that record.

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

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