Private AI for performance review drafting
A self-hosted model can turn a manager's scattered notes into a coherent performance review draft without sending them to an AI vendor. That matters because the notes are a manager's unfiltered opinion of a named employee's work, sometimes with salary context, disciplinary history or a promotion that hasn't been announced.
What's in a review draft
Managers writing performance reviews often paste in more than the final wording needs: peer feedback quotes, PIP status, comp discussion notes, sometimes a coworker's name in a story about a conflict. None of that is meant to leave the manager-HR relationship, and most of it identifies a specific employee. A cloud AI tool used to smooth the language into a final draft sends all of that context along with the request, processed on infrastructure outside the company, under whatever retention policy applies to that specific plan.
This is a narrower problem than most AI-and-HR-data articles suggest. Review text isn't usually regulated the way health or financial data is, but an employee would reasonably expect it to stay with HR and their direct manager. Much of it becomes embarrassing if it surfaces mid-cycle, before a review is delivered, or in a later dispute.
What changes with a dedicated drafting model
With the drafting model on a dedicated DGX Spark, the notes and the draft go to your own model on a machine assigned only to you. No AI vendor sees the text, and there's no plan-tier question about whether inputs get used for training. The workflow looks the same to the manager: paste rough notes, get back a structured first draft to edit. What differs is everything downstream of "send."
A rented Spark is still GPUwerk's hardware, operated under its published DPA. Review notes about named employees are personal data, so list GPUwerk in your records of processing like any other processor.
A practical setup is Open WebUI configured with a review-drafting system prompt, restricted to the managers and HR partners who need it, on a Spark that isn't shared with unrelated workloads. For teams already running retrieval over internal documents, the same instance can pull in a company's rubric or values language so drafts stay consistent without a manager having to paste the whole document each time.
What a model should and shouldn't decide
A drafting model is useful for structure and tone: turning a manager's bullet points into full sentences, checking that a draft covers the required review categories, or flagging when language reads more harshly than the underlying notes support. It should not be the source of the substantive judgment, and it shouldn't see comp bands or headcount plans it doesn't need for the task in front of it. Scoping what a manager pastes in still matters on a private instance. Self-hosting removes the AI vendor; it doesn't substitute for a manager keeping the input tight.
Rating consistency and bias
Some HR teams ask a model to flag inconsistent language across a manager's reviews, for instance the same behavior described as "assertive" for one employee and "difficult" for another. That's a reasonable use of a private model: the comparison reads several employees' review text together, an aggregation you don't want on an AI vendor's servers. It's a check on drafting language, not a substitute for a calibration meeting, and it won't catch bias that isn't visible in word choice.
What this doesn't solve
Self-hosting the drafting model doesn't change your legal obligations around personnel records, doesn't create an audit trail HR didn't already have, and doesn't decide who should see a given draft before it's delivered. Those are policy questions for HR and legal, not infrastructure questions. What a dedicated instance removes is one specific exposure: a third-party AI vendor holding a copy of what a manager wrote about an employee before that employee has read it themselves. See pricing for what a dedicated Spark costs.