Stage-gate dossiers for portfolio committees, built from live programme evidence and scored the same way every time
Every gate dossier built from live programme evidence in days, scored on the same criteria every time.
See one case, screen by screen ↓Ten days before a Portfolio Review Committee, the programme leader has to turn a year of work into one decision paper. The values the gate criteria ask for sit in ten or more documents: the pharmacology and in vivo reports, the DMPK summary, a CRO draft tox report, the process chemistry route and solid-form report, Legal’s IP memo, Competitive Intelligence’s slides and Finance’s cost and timeline model — each with its own version and its own owner.
Most of the days go on chasing the latest final report, copying numbers into the template and checking them against thresholds that differ by gate. The committee then gets dossiers built slightly differently each time, can read a hERG value that a newer final report has already replaced, and may keep an amber programme going for one more committee because nobody had the scores side by side.
Estimated split for one lead-to-candidate dossier, by hand and with the solution.
Six specialist agents read the science, CMC, IP, market and cost, score the criteria and write the dossier; the portfolio committee decides.
NWB-4417, an oral NLRP3 inhibitor for hidradenitis suppurativa, comes to the lead-to-candidate gate at the Oct 14 Portfolio Review Committee. Here is what happens, screen by screen, in the working solution.
Omar opens the solution: 12 programmes at four research gates, the next committee in 7 days, 4 decisions on the agenda and 4 waiting for his vote and signature. The gate map places every programme at its gate, coloured by score and sized by the cost to the next gate — $73.5M asked across the four Oct 14 items.
“NWB-4417 · Oral NLRP3 inhibitor · Go with conditions · Exposure margin at NOAEL: 7.8× (ALT up at 300 mg/kg)”
The dossier list shows each programme’s gate, committee date, score, criteria count and the agents’ recommendation. NWB-4417 scores 86 — 11 met, 3 partly, 0 not — recommended Go with conditions. Programmes still waiting on evidence say so: NWB-7140 has 9 of 11 documents in and is not scored yet.
“Criteria templates: Target → Hit v3.1 · Hit → Lead v3.4 · Lead → Candidate v4.2 · Candidate → IND v2.8”
The dossier opens on its scorecard: 86 of 100, with a score for each of seven dimensions weighted by the template — Safety 60, IP & market 65, Manufacturing 75, the rest 100. Beside it, the source passage for the weakest criterion: the 14-day rat dose-range-finding study, a CRO draft report, with the ALT rise highlighted. Maya checked and released the agents’ build before Omar saw it.
“Built by 6 agents from 10 documents and template v4.2 in 3 min 12 s · today 07:40 · checked and released by Dr. Maya Chen at 08:05”
Omar presses Rebuild. The science reader, the CMC and IP reader and the market and cost reader read the programme’s reports in parallel; the criteria scorer, the risk analyst and the dossier writer follow. Each step says what it read: the final safety pharmacology report now gives hERG at 42 µM, where the draft said 38, and the Oct 3 finance estimate puts the cost at $11.8 M, down from $12.4 M.
“Dossier rebuilt — 2 values changed since Oct 1 · score still 86”
Each criterion shows what was measured, where it sits against the threshold, the result, a confidence and its source. The two new values carry their old ones beside them. Three are partly met: the exposure margin at NOAEL (7.8× against at least 10×), the solid form (form B converts at 60 °C / 75 % RH) and competitive differentiation (6 clinical rivals; low brain exposure).
The template, quoted: a margin of 5–10-fold is “partly met and needs a mitigation plan agreed with Nonclinical Safety.”
Recommendation, programme summary, criteria, risks and mitigations, cost, timeline and value, and the decision requested — in the house order, marked confidential to committee members and the programme team. It leads with the gap: the margin comes from a mild, reversible liver enzyme rise at the top dose and can be closed with a 28-day study before GLP work begins. Every number is cited; click one to see its passage.
The writer never expresses a vote or a decision — that belongs to the committee.
Six risks on a likelihood-by-impact matrix, each with a mitigation, an owner from the function that holds the evidence, and its source. Two are rated high: the liver enzyme rise that could narrow the clinical margin (Dr. Ines Moreau) and a crowded class with six clinical-stage rivals (Lena Ortiz).
Lena Ortiz, Dr. Ines Moreau and Priya Raman vote Go with conditions; Sam Patel votes Go — the $11.8 M is already in the FY27 plan. Each vote carries the member’s reason. Omar’s is the last vote.
Dr. Ines Moreau: “7.8× is workable for a long-term skin indication only if the 28-day study confirms the liver change reverses. Condition 1 is mine.”
Omar chooses Go with conditions. The risk analyst has drafted three from the partly-met criteria, each measurable and dated: a 28-day rat study with a liver panel confirming at least a 10× margin before GLP (Dr. Ines Moreau, Jan 15, 2027), a locked form B control strategy and clinical packaging (Priya Raman, Feb 26, 2027), and a re-test of competitive differentiation at the next gate (Lena Ortiz). He can edit the rationale or add a condition.
Omar signs with his password and the meaning of his signature — “I approve this portfolio decision and its conditions”. With all five votes in, the decision is taken by written procedure and noted at the Oct 14 meeting. Record PD-26-038 is sealed with its rationale, the three conditions open with their owners, and the programme moves to the candidate-to-IND gate.
“A correction later becomes a new record that points to this one.”
The same nomination, seen by five people around the committee table — what preparing a gate looked like, and what it looks like now.
Six specialist agents read the science, CMC, IP, market and cost, score the criteria and write the dossier; the portfolio committee decides.
Reads target assessments, pharmacology, in vivo, DMPK, toxicology and safety pharmacology reports and extracts every value a criterion needs, with the passage it came from. When two reports disagree it takes the newer final report and flags the older one.
Reads route, solid-form and stability reports and Legal’s IP memos — steps, scale, polymorph risk, filing dates and freedom to operate.
Reads competitive-landscape briefs and the finance cost and timeline model: rivals by phase, differentiators, cost and months to the next gate, risk-adjusted value.
Applies the gate’s criteria template — thresholds and weights — marks each criterion met, partly met or not met, and computes the weighted score.
Turns partly-met criteria and source caveats into a risk register — likelihood, impact, owner, mitigation — and drafts conditions for the committee.
Drafts the six-section gate dossier — recommendation, programme summary, criteria, risks, cost and value, decision requested — for a committee that reads in ten minutes.
Votes, the chair signs. The agents propose; a named person decides.
Committee members and programme teams can ask about any dossier, criterion or decision — or ask for a change to a template. Every answer points to its source.
Summarise NWB-4417 for the committee
NWB-4417, an oral NLRP3 inhibitor for hidradenitis suppurativa, meets 11 of 14 lead-to-candidate criteria and scores 86. Potency is 18 nM in human whole blood with more than 300× selectivity, and the predicted dose is 120 mg once daily. The gap is safety: the exposure margin is 7.8× against a 10× criterion, from a reversible ALT rise at 300 mg/kg. The agents recommend Go with conditions — a 28-day rat study before GLP.
Which dossiers have a safety margin below 10×?
Three: NWB-8803 (Claudin 18.2 ADC) at 3×, candidate to IND; NWB-5521 (LRRK2 inhibitor) at 4.2×, lead to candidate; and NWB-4417 (NLRP3 inhibitor) at 7.8×, lead to candidate. NWB-8803’s margin is at the highest non-severely toxic dose; NWB-5521 shows lung changes; NWB-4417’s liver change is mild and reversible.
What changed since the last committee?
Since the Sep 30 committee, 2 decisions were signed — NWB-6610 Go with conditions, NWB-0412 Go. In NWB-4417 two values changed: hERG IC50 is now 42 µM (was 38) and the IND estimate fell to $11.8 M (was $12.4 M); the score stays at 86. One condition is overdue — NWB-2204’s 28-day monkey report, due Oct 3.
Add a criterion: patient-selection biomarker at lead to candidate
Done — Lena Ortiz’s v4.3 is approved, adding Patient-selection biomarker to the lead-to-candidate template: threshold “assay feasible; prevalence known in the target population”, dimension Target. New dossiers score on v4.3 from today; dossiers already in committee keep v4.2 so their votes stay valid.
13 screens from the working solution, on its sample data. Pick one to see it large.
What differs between research organisations — criteria, signers, confidentiality and how much the agents draft — is a setting, not a project.
| Setting | Default | Choose from |
|---|---|---|
| Criteria template per gate | Lead → Candidate v4.2 | Target → Hit · Hit → Lead · Lead → Candidate · Candidate → IND — new versions proposed and approved |
| Who signs Lead → Candidate | Committee chair · full review | Dr. Omar Haddad · Lena Ortiz (deputy chair) |
| Who signs Candidate → IND | Chair, with Finance co-signing the budget | Dr. Omar Haddad + Sam Patel · Lena Ortiz (deputy chair) |
| Market-sensitive information | Committee and programme team only | On · Off |
| Watermark every export | On | On · Off |
| Block forwarding outside the company | On | On · Off |
| Rebuild a dossier when new evidence lands | On | On · Off |
| Write the first dossier draft | On | On · Off (agents only score and cite) |
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 portfolio data · “target” = the design goal, measured in the live solution · “estimated” = our estimate (the 19-day by-hand figure; 2–4 weeks per governance deck is common practice). People and programmes named on this page are characters in the working solution.
The paper a portfolio committee decides on at each research milestone — target to hit, hit to lead, lead to candidate, candidate to IND. It sets the programme’s evidence against the gate’s criteria, lists the risks and the cost to the next gate, and asks for a decision: Go, Go with conditions, Hold or Stop.
The criteria scorer applies the gate’s template exactly as written — each threshold, the partly-met band where there is one, and the dimension weights — and marks every criterion met, partly met or not met. It records the template version on the score and never changes a threshold.
From your programme’s own documents: study reports, the DMPK summary, toxicology and safety pharmacology reports, route and solid-form reports, IP memos, competitive briefs and the finance cost model. Every value carries its source passage; when a draft and a final report disagree, the newer final report is used and the older one flagged.
No. The agents recommend and draft; committee members vote with their reasons, and the chair decides and signs. The dossier draft contains no vote or decision language, and every condition is edited and approved by the chair.
The chair signs with a password and the meaning of the signature. The decision record is sealed in the decision registry with its rationale, conditions, signers and the dossier version it was based on. At candidate to IND, Finance can co-sign the budget.
Yes. By default only committee members and the programme team can open a dossier, every export is watermarked with the reader’s name and time, exports cannot be emailed outside the company, and readers of a partnered programme’s dossier are added to the insider list.
The dossier can rebuild when new evidence lands. Scores update, values that changed are flagged beside the criterion and in the text, and the programme leader is told.
The Agentic Solution Engine builds and deploys it from your requirements and documents — your gate criteria, your dossier house style and a sample of past programmes — and it goes live once every quality gate has passed. We will walk you through it on one of your own programmes first.
Ask the literature in plain words and get a sourced answer in seconds.
1-min filmPipeline WatchEvery rival trial, readout and approval lands in a sourced brief for each programme, every Monday.
1-min filmPreclinical ReportsRaw study data becomes a draft report in hours, with every number traced to its source.
1-min filmWe’ll build a Stage-Gate Decision Dossier on one of your own programmes and your gate criteria.