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

Does Taleo Remember Between Runs? The Candidate Profile Holds. The Run Reasoning Does Not.

Does Taleo Remember Between Runs? The Candidate Profile Holds. The Run Reasoning Does Not. Short answer: Taleo keeps a long record for every candidate, and that record holds a great deal. A candidate account stores a parsed profile that persists across applications to the same employer. Candidate files hold answers, attachments, and history in one place. Talent pools and folders keep people grouped and searchable for the next requisition. What does not hold in the same way is the work a schedul

Does Taleo Remember Between Runs? The Candidate Profile Holds. The Run Reasoning Does Not.

Short answer: Taleo keeps a long record for every candidate, and that record holds a great deal. A candidate account stores a parsed profile that persists across applications to the same employer. Candidate files hold answers, attachments, and history in one place. Talent pools and folders keep people grouped and searchable for the next requisition. What does not hold in the same way is the work a scheduled run does across many candidates, requisitions, and locations at once. The comparison, the order, and the reasons behind both are not saved as a history the next run can load.

What one profile keeps in Taleo

Taleo, Oracle's standalone talent acquisition suite, was built for large employers, government agencies, and high-volume hiring teams, so its memory is organized around the candidate and the requisition. The center is the candidate file.

An application starts with an account. Unlike a guest apply flow, Taleo requires a candidate account with a username and password for that employer. That account is the reason the profile can persist. A person who applied in one year and returns in a later year to the same employer is working from the same stored base, not from a blank form.

Resume parsing builds the first layer of that base. An uploaded file is turned into structured fields for contact details, employer name, title, start and end dates, education institution, and degree. The system auto-fills application fields from those parsed values, then asks the candidate to confirm or complete them, because parsing runs through a partner service and clean fields matter for search. Multiple resume versions can sit in the profile, with the tailored version selected per requisition.

Around the parsed fields, the file grows. Screening answers sit with the application, including answers to required and asset criteria for a specific job. Attachments stay on the record. Source is kept, so the team can see how the person arrived. General interest profiles are also kept, so a person can be held for a future vacancy even without a single open role attached.

That is durable, profile-level memory. It answers who this person is, what was submitted, and what was answered for each role.

What pools, prescreening, and sourcing keep moving

Around the profile, Taleo keeps sourcing history alive in several ways.

Talent pools, created in Taleo Performance and visible in the Recruiting Center, are lists of people nominated by pool collaborators. Authorized users can view a pool, match employees and candidates to requisitions, file people into folders for more pooling, or contact them directly. Quick filters cover internal, referred, and in-selection candidates, plus employer and program. An advanced filter for employee potential sorts people into low, medium, or high. A pool preserves the group. A folder preserves the shortlist shape.

Sourcing tools feed those pools. Branded career sites, marketing campaigns, automated postings, and referral features attract candidates and grow the pool instead of starting each search from a job board again. Analytics then report on sourcing processes, talent assessments, candidate communication, and onboarding, so a team can see which channels produced people worth keeping.

ACE prescreening adds a ranking layer inside a single requisition. Filtering and ranking run on answers to the job's required and asset criteria. Strong answers flag a candidate as a stronger match for that role. Recruiters search the stored database by keyword, title, and skill, and filter on those same answers.

Each layer works well on its own terms. The pool preserves the people. The folder preserves the grouping. The prescreening preserves a flag against one job. Notice what every layer reads from: the stored profile as it stands today. None of those layers was built to hold conclusions that belong to a run across all of them.

Where a scheduled run starts from zero

Picture a recurring automation that works a Taleo pipeline on a schedule. Each run pulls candidates across several requisitions, compares new applicants against a pool built over months, checks who was already reviewed for a similar role, and decides who should move first and why.

The profile helps with the first step only. It gives the run today's parsed fields, today's answers, and today's attachments. The pool helps with the second step only. It gives the run today's members and today's filters.

What the run worked out last time lives in none of those places. Which candidates were set aside because a hiring manager changed the criteria mid-cycle. Which near-miss from a closed requisition was marked as the first call for the next similar opening, and the exact reason. Which comparison across two locations settled a tie, and what evidence settled it. That reasoning was produced by the run, across records, and Taleo's candidate-centered store has no field for it.

So the next run re-derives it. It re-reads the same profiles, re-applies the same filters, and re-makes the same comparisons, often reaching a slightly different order because the starting context was never saved as a shared history. The records remember the people. The run itself is forgotten.

Give the run a memory of its own

The fix is a memory layer that sits outside any one candidate record and holds the run's own work. Vilix AI is built for that job.

Vilix AI is cloud-hosted, so there is zero infrastructure to set up or manage. An automation connects once over MCP, and the same memory is then available everywhere that connection runs, on every tool and every schedule, not locked inside one platform's database. When a run finishes a comparison, a ranking, or a decision about a pool, it saves that work to Vilix AI. When the next run starts, it loads that history first, before it touches a single profile.

That history is full conversation history, not just facts. A saved fact can say a candidate was shortlisted. Full history keeps the exchange that led there: the criteria used, the candidates compared, the reason one was placed ahead of another, and the note that changes the order next time. A later run, or a different agent working the same pipeline, reads the reasoning, not only the result.

Start with the free plan, which is free forever. A 7-day Pro trial is available with no credit card required for teams that need more. Data stays portable the whole time: export everything or delete it anytime.

Taleo will keep doing what it does well. The candidate profile will hold, the pool will hold, and the prescreening flag will hold. Add a memory that holds the run as well, and a scheduled pipeline stops starting from zero. It starts from last time, with the reasons included.

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