Investigator-initiated study review, from concept to signed committee decision, with six agents doing the checking
Every investigator's study concept checked against our priorities, ongoing studies and its budget, and decided in half the time.
See one case, screen by screen ↓A concept arrives through the portal: six pages, a budget sheet and a cover email. Before anyone can judge the science, someone has to check it against the published research priorities, search the company’s own studies, the funded investigator studies and the public registry for the same question, work out whether the site can really enrol the patients it promises, and compare every budget line with fair market value.
Done by hand, that checking fills the weeks of screening and scientific review — and it is where duplicates slip through. A concept that repeats a company phase 3b can reach the committee looking original, a plan that needs 3.3 patients a month from a site that enrolled 1.1 a month in its last two studies can go unchallenged, and the committee spends its two hours reading packets instead of deciding.
Median days per step in the working solution’s sample programme: by hand in 2025, and with the agents in the Q4 2026 cycle.
Six specialist agents read, match, compare, cost and screen every concept and draft a cited packet; the scientific reviewer recommends and signs, and the committee decides.
Dr. Elena Varga in Budapest submits VELOCITY-CD: early endoscopic response to Veltrimab after anti-TNF failure in Crohn’s disease. Here is what happens next, screen by screen, in the working solution.
Maya opens the Q4 2026 review cycle: 14 concepts, 13 published priorities, the committee on Wed Oct 21. Every priority shows the company studies, funded investigator studies and this cycle’s concepts against it — IMM-3, Crohn’s disease after prior advanced therapy, is marked Crowded. One concept is waiting for her review.
“Oct 21 docket — 4 of 5 ready · packets one page each · cited.”
VELOCITY-CD came in through the portal as a six-page concept form, a $448,000 budget sheet with 30% overhead and a cover email, and Lena Ortiz, the IIS programme manager, assigned it to Maya. She clicks Run review. The priority matcher finds IMM-3, the overlap finder searches 412 studies and flags high overlap with VELTRIS-CD, and the feasibility and budget checker finds 55 months to full enrolment and 2 budget flags. As each agent works, the source it is reading opens on the right with the passage highlighted.
The last step is never an agent: “Waiting for you — Dr. Maya Chen recommends and signs.”
The concept reader turns the form, budget sheet and email into a structured record of 44 fields, each with a numbered citation to its passage: sponsor Danube University Hospital, single-arm and open-label at one site, 60 patients in 18 months, $448,000 and product for 60 patients. What the concept does not contain is marked missing, not guessed — here, the power calculation and the ethics plan.
“Missing is reported, never guessed.”
VELOCITY-CD fits IMM-3 at 0.88, with the priority text quoted and the runners-up shown (IMM-1 at 0.41, IMM-2 at 0.33). The matcher also notices what a hurried reader would miss: the priority asks for transmural outcomes on MR enterography, and the concept has them only as a secondary endpoint.
Each candidate study is compared element by element — population, treatment, control, outcome, timing, region. VELTRIS-CD, the company phase 3b, scores 0.86: same population, same endpoint, same week 12, reading out in Q2 2027. HISTO-CD (0.54) and a public registry trial (0.38) overlap less. What the concept adds is transmural healing on MR enterography at week 24.
“VELTRIS-CD already answers the primary question in Q2 2027. Danube University Hospital was one of its sites. Ask for transmural healing as the primary endpoint — the gap our priority names.”
60 patients in 18 months needs 3.3 a month. Danube University Hospital enrolled 1.1 a month in VELTRIS-CD and in a national IBD registry sub-study, with 35% screen failure — about 55 months. Maya tries the scenarios: a second site brings it to about 23 months; a second site with a powered sample of 40, about 15.
Two flags: central endoscopy reading at $520 a read against a benchmark of $260–$340, and institutional overhead at 30% against the 25% cap. With both at benchmark the budget falls from $448,000 to $397,750 — inside the fair-market-value range of $360k–$410k. The agent never edits the investigator’s budget; the revision becomes a condition in the letter.
Product: 180 IV vials and 360 prefilled pens for 60 patients over 52 weeks — Sam Patel confirmed clinical stock from Q2 2027.
The reviewer summary runs to one paragraph with seven citations, and recommends a full protocol with conditions: make transmural healing on MR enterography at week 24 the primary endpoint; add a second site, or justify 40 patients with a power calculation; overhead at 25% and central reading at the benchmark rate; a safety data exchange agreement before product is released. Maya can edit, remove or add any of them.
Maya signs her recommendation with her password. The signature records its meaning with her name and the time, and the packet joins the Oct 21 docket.
“Meaning of this signature: I reviewed this proposal and its cited evidence and make this recommendation to the IIS review committee.”
The voting members vote, the quorum is met, and the chair signs the decision: request full protocol with conditions. The letter writer drafts the letter to Dr. Varga with the four numbered conditions and a full-protocol date of January 4, 2027, a policy check removes internal study names, and Lena Ortiz reviews and sends it through the portal — drug supply and transparency records updated.
“Internal study names never appear in letters to investigators.”
The same concept, seen by the five people who carry it — what their cycle looked like, and what it looks like now.
Six specialist agents read, match, compare, cost and screen every concept and draft a cited packet; the scientific reviewer recommends and signs, and the committee decides.
Turns each concept form, budget sheet and cover email from the submission portal into a structured proposal record — every field with the passage it came from.
Matches the proposal to the published research priorities and quotes the priority text it fits, with a fit score and the runner-up priorities.
Searches company studies, funded investigator studies and the public trial registry, and compares each candidate element by element — population, intervention, comparator, outcome, timepoint and region.
Checks requested enrolment against the site’s own history and budget lines against fair-market-value benchmarks and the overhead cap; works out the drug quantity.
Screens the concept and correspondence for red flags — commercial colleagues involved, promotional wording, links to prescribing — and notes transparency and safety-agreement obligations.
Drafts the cited reviewer summary and the one-page committee packet, and after the decision drafts the letter to the investigator with the conditions.
Recommends and e-signs. The agents propose; a named person decides.
Reviewers and the programme team ask in plain words — or tell it what to change. Every answer shows the passage behind it.
Does VELOCITY-CD overlap with our own studies?
Yes — one study asks the same primary question. VELTRIS-CD measures endoscopic response at week 12 in anti-TNF failures and reads out in Q2 2027 (overlap 0.86). HISTO-CD scores 0.54 and a registry trial in Germany 0.38. What VELOCITY-CD adds is transmural healing on MR enterography — exactly what priority IMM-3 asks for.
Can VELOCITY-CD enrol 60 patients in time?
Not at this site alone. 60 patients in 18 months needs 3.3 a month; Danube University Hospital enrolled 1.1 a month in VELTRIS-CD and in its registry study, with 35% screen failure. At this site’s rate: 55 months. Add a second site: 23. 40 patients: 37. Both: 15. The concept has no power calculation yet — that is condition 2.
What is wrong with the VELOCITY-CD budget?
Two lines: central endoscopy reading at $520 a read against a benchmark of $260–$340, and overhead at 30% against our 25% cap. With both at benchmark the budget falls from $448,000 to $397,750, inside the fair-market-value range of $360k–$410k. Everything else is within range.
Flag budgets with overhead above 25%
Done. New rule: flag any budget whose overhead is above 25% of direct costs, before scientific review. VELOCITY-CD’s budget sheet shows 30%. The rule is live in Settings and the proposal list has a Budget flags view.
13 screens from the working solution, on its sample data. Pick one to see it large.
Thresholds, benchmarks, reviewers and the committee are settings the programme team owns.
| Setting | Default | Choose from |
|---|---|---|
| Overlap alert | 0.6 | 0.5 · 0.6 · 0.7 |
| Minimum priority fit | 0.6 | 0.5 · 0.6 · 0.7 |
| Overhead cap | 25% of direct costs | Raise or lower by 1%, from 15% to 35% |
| Enrolment from site history | On | On · Off (taken as requested) |
| Commercial-involvement screen | On | Turning it off needs compliance approval |
| Budget benchmarks | 2026 benchmarks by country · v3 | 2026 v3 · 2025 v2 |
| Scientific reviewer by area | Immunology: Dr. Maya Chen | Any reviewer, per therapeutic area |
| Committee quorum | 4 of 6 | 3 · 4 · 5 of 6 |
Every figure is labelled: a target the solution is built to, an estimate, a typical published result, or a proven one.
“demo” = seen in the working solution, on its sample programme data · “target” = the design goal, measured in the live solution · the days per step are the working solution’s sample medians · sources: published investigator-initiated study programme processes (2025). People, products and studies named on this page are characters and fictional data in the working solution.
Software that takes an investigator’s study concept from the submission portal through screening, scientific review and the committee to a signed decision and a letter. The IIS Proposal Reviewer adds six agents that read the concept, match it to your research priorities, search for overlapping studies, check enrolment and budget, screen for compliance red flags and draft the cited packet.
The overlap finder searches company studies, funded investigator studies and the public trial registry, then compares each candidate on population, intervention, comparator, outcome, timepoint and region, citing both passages. It scores the overlap, names what the concept adds and shows when each study reads out.
Each budget line is compared with the range for that country and cost item in the benchmark set chosen in Settings, and overhead is checked against your cap. Lines above range are flagged with the budget-sheet passage. The agent never edits the investigator’s budget — the reviewer decides, and the letter asks for the change.
The compliance screener flags any sales or marketing colleague in the correspondence, any link to prescribing and any promotional wording, and holds the concept for compliance before scientific review continues. It also lists payments to the investigator in the last 24 months and the transparency reporting that applies.
Yes. Agents prepare the packet and draft letters; a scientific reviewer signs the recommendation and the committee chair signs the decision, each signature recording meaning, name and time. Every step is on the audit trail.
No. Company study records are internal and never shown to investigators, and letters never name internal studies — a policy check removes them before the programme manager sends the letter through the portal.
Yes. The overlap alert, minimum priority fit, overhead cap, benchmark set, whether enrolment is projected from site history, the reviewer for each therapeutic area and the committee quorum are all settings, and every change is versioned in the audit trail.
The Agentic Solution Engine builds and deploys it from your requirements and documents — your research priorities, concept and budget templates, benchmarks and a sample of past concepts — and it goes live once every quality gate has passed. We will walk you through it on your own concepts first.
Every claim checked against its reference page and the label before a reviewer opens it.
1-min filmMedical InformationEvery question from a healthcare professional answered in a signed letter where each sentence links to its source.
1-min filmMedical InsightsEvery field insight becomes a cited theme within days, ready for the quarterly report.
1-min filmWe’ll run the IIS Proposal Reviewer on a sample of your own past concepts and priorities.