Expert human data for university AI research.
Preference data (RLHF), model evaluation, benchmarking, expert demonstrations and red-teaming for university studies, by graduate-level specialists in your field. Academic rates for university-affiliated research groups. One fixed quote before work starts.
Your study design and data stay yours. We never train on or resell what the cohort produces. EU-resident evaluators, GDPR-compliant, paid the full rate.
Some studies need scale. Yours needs judgement.
Preference rankings from people who know the field. Rubric grades from professionals. Demonstrations written by someone who has done the job. When that judgement has to come from an expert, the program gives you a staffed, managed cohort matched to your study.
University research groups
Faculty, postdocs, and PhD students whose AI studies need expert human data. Open to university-affiliated researchers worldwide.
A staffed expert cohort
Graduate-level specialists matched to your domain, trained on your protocol, managed end to end. You keep full design control.
Research rates
Academic rates for university-affiliated research groups. One fixed quote before work starts.
Trained and reviewed with the EuroExec method.
Sovrano Scholars are graduate-level specialists in finance, law, data protection, medicine, employment and tax, recruited from universities across Europe. Every Scholar completes structured training before production work. Every project runs rubric-graded quality review, using the authoring and dual-review method behind the EuroExec benchmark.
- Graduate-level, verified specialists
- Structured training + rubric-graded QA
- Dual independent review on request
- EU-resident · GDPR-compliant · DPA available
- Specialists across European markets and jurisdictions
Six study types, one managed cohort.
Pairwise & ranking judgements
RLHF-style preference comparisons over model outputs, ranked by experts who know the domain.
Rubric grading & benchmarks
Model answers scored against your rubric or benchmark, with per-item grades and agreement statistics.
Gold answers & traces
Expert-written reference answers, worked examples, and reasoning traces for SFT or gold sets.
Adversarial & error analysis
Structured probing by domain experts, with failures labeled against your taxonomy.
Cross-market judgement
Evaluation by specialists in each European market, where the right answer depends on local rules. One coordinated cohort.
Your own protocol
Bring the design your study needs. Your evaluation interface or a shared one we set up.
You send the protocol. We staff it. Data comes back audit-ready.
Send: your tasks, your format
Send tasks in the exact format you would hand an in-house evaluator. We train the cohort on your protocol as written; the design stays under your control.
Staff: we match the cohort
We staff from the Scholar network by domain, language, and availability. You approve the cohort size, timeline, and fixed quote before work begins.
Deliver: data with the paper trail
Completed data with pseudonymous rater IDs, inter-rater agreement statistics, versioned guidelines, and a methods paragraph you can adapt for the paper.
Data you can put in a paper.
Preference judgements were collected from N graduate-level evaluators recruited and managed through the Sovrano Research Program. Each pair was independently rated by two evaluators against a shared rubric (Krippendorff's alpha = 0.78). Evaluators were domain specialists in [field], EU-resident, and compensated at their full hourly rate. Guidelines (v3) and per-item ratings are released with this paper.
{ "item_id": "pref_0421", "task": "pairwise_preference", "domain": "clinical_medicine", "rater_ids": ["ev_17", "ev_42"], "choice": "A", "agreement": true, "confidence": [4, 5], "rationale": "Option A gives the correct first-line therapy; B omits the contraindication.", "guidelines_version": "v3"}
Illustrative only. Your schema, fields, and rubric are whatever the study needs; this is the shape most groups export.
Academic rates. One fixed quote.
Academic rates for university-affiliated research groups · one fixed quote
Your quote is set by four things: domain, review depth, timeline and volume. It covers the experts' time, training on your protocol, quality review and project management. Experts receive their full rate. Billed on delivered, QA-passed hours, as one euro invoice that fits a purchase order.
Your fixed quote is set by domain, review depth, timeline and volume, and agreed before work starts.
A typical study (50 experts, one 4-hour task each) is quoted as one line item that fits inside a grant's data budget. Most of the quote goes to the experts.
What sets your rate
Domain
Review depth
Timeline
Volume
These four drivers set your quote. You see it, fixed, before work starts.
Free
5 tasks, the exact format you'd give an in-house evaluator. Completed data back within two weeks. No commitment.
200 expert hours, the standard unit for a study-sized annotation run.
500+ expert hours: larger protocols, multi-wave designs, longitudinal collection.
Every project gets one fixed quote, locked before work begins and held through delivery. The pack size is the only minimum.
Built to pass your ethics review.
Fair pay you can cite
Evaluators paid their full hourly rate under fair-pay terms. Compensation and consent documentation for your IRB or ethics review, with wording for your statement.
Your data stays yours
You own the data and the study design. NDA on request.
European by default
Every evaluator is EU-resident and covered by European data-protection law. A DPA is available on request, and the setup fits a Horizon Europe or ERC data-management plan.
Anonymity built in
Evaluators are identified by pseudonymous rater IDs, so you can release ratings and agreement statistics, including in double-blind submissions.
Why academic rates?
The Scholars program is how we train and credential our experts, and academic protocols written by working scientists are the best training ground they can get. Research groups get academic rates, the experts are paid in full, and published work shows what they can do. Slots are capped at ten projects per quarter, reviewed in application order and by fit. The free pilot is always open.
“Expert human data for this study was provided by the Sovrano Research Program (sovrano.ai)”
One line in the acknowledgments, plus permission to name your institution among our participating research groups. Nothing else.What research groups ask first.
No. The data and the study design are yours. We never train on, reuse, or resell what the cohort produces for you, and an NDA is available on request.
Yes. Evaluators are EU-resident and paid their full hourly rate under fair-pay terms. We provide the compensation, consent, and data-protection documentation your ethics review needs.
Yes. Send your task spec in the exact format you would give an in-house evaluator, and use your own interface or a shared one we set up. The study design stays under your control.
Every evaluator is trained on your protocol before production work, and items run with rubric-graded QA. On request we run dual independent review and report inter-rater agreement.
The free 5-task pilot has no minimum and no commitment. Paid runs start at the Research Pack of 200 expert hours. Most groups pilot first, then size the full study from the output.
Pilot data comes back within two weeks. Full studies run in standard windows of two to six weeks. Compressed timelines are available and are reflected in the quote.
One fixed quote before work begins, locked through delivery. A single euro invoice on delivered, QA-passed hours, purchase-order friendly. The quote is the full price.
Start a pilot or apply for a slot.
Thirty seconds. We reply within one business day.
The free 5-task pilot
Send 5 tasks our way and get the completed data back within two weeks, no cost, no commitment. Most groups start here and size the full study from the output.
A quarterly project slot
A staffed cohort for your full protocol, at academic rates. A short call confirms scope, then you get one fixed quote and a start date.
You're in the review queue
We reply within one business day. What happens next:
- Pilot: send your 5 tasks in whatever format your evaluators would get; completed data comes back within two weeks.
- Project slot: a short call to confirm scope, then a single fixed quote and a start date for your cohort.
Slots are reviewed in application order, ten per quarter. The pilot has no cap and no commitment.