Biopharma due diligence, from scouting sweep to signed recommendation, with agents reading the data room
A first pass on a seller’s data room in hours, with cited memos for every function and a signed recommendation.
See one case, screen by screen ↓The seller opens the data room and the bid clock starts. Four hundred files land across corporate, clinical, nonclinical, CMC, regulatory, IP and contracts folders — final reports next to draft versions, an investor deck next to the study report it summarises. Every function lead has to find their documents, pull the facts and write a memo before anyone can say what the asset is worth.
Most of that time is reading, not judgement. And the risks that move the price hide in the gaps between documents: a response rate that counts unconfirmed responses, a safety table on an older data cut, a change-of-control clause on page 31 of a licence nobody in clinical will open. Found late, they become a surprise at committee — or after signing.
Estimated split for a first pass on one data room, in hours, by hand and with the solution.
Seven specialist agents scout, read the data room, review each function and catch contradictions; function leads sign and the deal committee decides.
Tessivo Pharma's bispecific ADC, TSV-208, is in diligence: 412 files in the data room, a binding bid due Oct 24. Here is the deal, screen by screen, in the working solution.
Priya opens the deal radar: 18,240 assets watched, 12 on the radar, one in diligence, one at committee. TSV-208 sits in the diligence ring — fit 92 of 100, 5 of 8 red flags open, 2 of 6 function memos signed. The deal clocks run down the side: the QLR-310 committee on Oct 15, the TSV-208 binding bid on Oct 24.
Needs you: “Change-of-control consent in the linker licence — Decide: condition to signing or walk away.”
Before anyone reads a page, the Data Room Reader has classified all 412 files across the eight folders — corporate, clinical, nonclinical, CMC, regulatory, IP, commercial, contracts — by function, document type and version. Each file the memos cite is marked, so a reviewer can go from a memo to the exact report, deck or licence it rests on.
“14 superseded drafts set aside so draft values never reach a memo.”
Six tiles across the top — clinical efficacy, safety & toxicology, CMC, IP & contracts, regulatory, commercial — each with its score, its reviewer and its flags. The clinical memo is signed: a confirmed response rate of 38.1% (16/42) at 2.4 mg/kg. The investor deck says 45% because it counts unconfirmed responses, and the valuation uses the confirmed figure.
Click a citation and the interim study report opens at section 11.4, the sentence highlighted.
Interstitial lung disease is the main safety question. The June interim study report counts 4 cases in 58 patients (6.9%), one Grade 3; the Investigator's Brochure and the deck still say 3 cases (5.2%) because they use the February cut. The 13-week monkey study gives a NOAEL of 6 mg/kg/week, about 2.5 times clinical exposure, with reversible corneal changes only at 10 mg/kg and above.
Covenant RF-08: no independent ILD adjudication yet — only planned for Part C.
Composition of matter runs to 2041 before any extension. But the linker platform is licensed in from Corvane Labs, and a change of control of Tessivo needs the licensor's prior written consent — or the licensor may terminate on 90 days' notice. The royalty stack is 6.5%, inside the 10% limit; freedom to operate was searched for the US only.
Deal-breaker RF-05: “Change of control needs the linker licensor's consent; without it the licence can be terminated.”
Each memo drafts its questions for the seller; the function lead approves them and they go through the data room's Q&A channel only. Q-14 is already answered: the deck counted 18 responses in 40 patients on 30 May, including unconfirmed ones — one was confirmed after the June cut, one was not. Two more are with the seller, two wait for approval.
One deal-breaker, four price-adjusting flags carried into the valuation, three covenants. Each has its sources, its owner and what happens to it: launch moved to Q3 2030 for the dose-optimisation the agency asked for, peak share cut from 18% to 14% for three competing ADCs in Phase 3, a root-cause report for the out-of-specification lot TSV-L005 before signing.
The scorecard weights each function's score with the agreed weights. After diligence, PTRS moves from 22% to 19%, rNPV from $1.42B to $1.18B and first launch from Q4 2029 to Q3 2030; bid guidance is $620–680M upfront, down from $720M. Four conditions are drafted, and the signature is blocked while the deal-breaker is open.
“1 deal-breaker needs a decision before you can sign.”
Priya makes RF-05 a condition to signing: licensor consent to change of control before signing. The signature opens. She signs with her password and the meaning of the signature — “I have reviewed this and approve it” — and Omar Haddad, the BD deal lead, is asked to countersign.
“Your electronic signature is recorded with your name, the date and time and its meaning, and cannot be edited afterwards.”
Omar countersigns and the recommendation goes to the investment committee: TSV-208 is on the Oct 22 special meeting, after QLR-310 on Oct 15, with two of its three signatures in place — the third is the committee chair's, Dr. Henrik Vale. The committee sees the score and the conditions, and every past decision on record with its reason.
The same deal, seen by five of the people who carry it — what their diligence looked like, and what it looks like now.
Seven specialist agents scout, read the data room, review each function and catch contradictions; function leads sign and the deal committee decides.
Sweeps registries, patents, congress abstracts and company news in nine languages; merges code names; ranks assets by fit with citations.
Classifies every data-room file by function, document type, version and data cut-off, and extracts the facts with their page references.
Drafts the clinical efficacy and safety memos: confirmed responses, adverse events of special interest, class risks, data cut-offs.
Reads lots, specifications, suppliers, patents and licences; finds out-of-spec lots, single sources, change-of-control clauses and royalty stacks.
Reads agency minutes and correspondence for what the agency asked and what it costs in time, and builds the competitive landscape from public sources in nine languages.
Compares the same fact across the deck, study reports and brochure, and explains why values differ — an older data cut, unconfirmed responses counted.
Scores the deal with the agreed weights, carries red flags into conditions and valuation inputs, and builds the committee pack.
Memos signed, then decides. The agents propose; a named person decides.
Ask about any deal, memo or red flag in plain words — or tell it what to change. Every answer cites the data-room page.
What could stop the Tessivo deal?
One deal-breaker and four price items on TSV-208. Deal-breaker RF-05: a change of control needs the linker licensor's consent, or the licence can be terminated — make it a condition to signing, or walk away. Price: lung disease up to 6.9%; dose optimisation adds about 9 months; the deck overstates the response rate; three competitors in Phase 3.
Does the investor deck match the study report for TSV-208?
Not quite. The June deck says 45% response (18/40, confirmed and unconfirmed); the interim study report confirms 38.1% (16/42). The deck says 3 lung disease cases, 5.2%, all low grade; the report has 4 cases, 6.9%, one Grade 3 — the deck uses the older February cut. Our valuation uses the study report.
Tell me about the lung safety signal
Interstitial lung disease is rising across data cuts: 4 of 58 patients (6.9%) in the June interim study report, including the first Grade 3 case, versus 3 cases (5.2%) in the brochure's February cut. All four occurred at 2.4 mg/kg or higher. Independent adjudication is only planned for Part C. PTRS moved from 22% to 19% partly for this reason.
Flag every change-of-control clause for Sam Patel
Done. New rule: whenever the CMC & IP Reviewer finds a change-of-control or assignment clause in any licence, it is raised as a red flag and assigned to Sam Patel for a decision before the recommendation can be signed. It matches one open clause today — RF-05 in the Tessivo linker licence.
13 screens from the working solution, on its sample data. Pick one to see it large.
What you look for, how a deal is scored and who signs are settings — changed in a minute, not a project.
| Setting | Default | Choose from |
|---|---|---|
| Therapy areas | Oncology · Immunology · Neuroscience · Cardio-metabolic | Assets outside these areas are not shortlisted |
| Modalities | ADCs, bispecifics, small molecules, peptides, in vivo cell therapy, RNA medicines | Click a modality to remove it |
| Royalty stack limit | 10% | Assets above the limit are flagged |
| Scouting sweep | Weekly · Monday 06:00 | Weekly · Daily |
| Recommendation weights | Clinical 30% · Safety 20% · CMC 15% · IP 15% · Regulatory 10% · Commercial 10% | Any split totalling 100% |
| Score bands | 3.5+ proceed · 3.0–3.4 proceed with conditions · 2.5–2.9 pause | Below 2.5: pass |
| Function reviewers | A named lead signs each function memo | Signs the memo · Reviews only |
| Sign-off rules | Deal-breakers block signing · two signatures before committee | Add a rule in one sentence |
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 deal data · “target” = the design goal, measured in the live solution · “estimated” = our estimate · “typical” = published figures (asset-scouting benchmark, arXiv 2602.15019: F1 79.7% for a purpose-built agent against 46–59% for general research tools). People and companies named on this page are characters in the working solution.
A single place where a business development team scouts external assets against its search criteria and runs the scientific diligence on a seller's data room — function memos, a red-flag register and a recommendation for the investment committee. In this one, specialist agents do the scouting, the reading and the first drafts; function leads and the deal team review, decide and sign.
The Data Room Reader classifies every file by function, document type, version and data cut-off, sets superseded drafts aside and extracts the facts with their page references. Specialist agents then draft the clinical, safety, CMC, IP, regulatory and commercial memos, each sentence cited to its page.
Yes. The Contradiction Checker compares the same fact across the deck, study reports and brochure, shows both sources side by side and explains why they differ — for example an older data cut, or unconfirmed responses counted. It never picks a value; a person does.
The Asset Scout sweeps trial registries, patents, congress abstracts and company news in nine languages on your schedule, merges code names that refer to one asset, checks rights and royalty signals, and ranks the shortlist by fit to your criteria with every claim cited. It uses public sources only, never deal data.
Yes. The agents serving a deal read only that deal's data room, with no cross-deal search or memory. Only wall-crossed people can open a deal, every view is logged, pages and exported memos are watermarked with the viewer's name, and exports need the deal lead's approval.
Yes. Every function memo is signed by its named lead, questions to the seller are sent only after the function lead approves them, an open deal-breaker blocks the recommendation signature, and the recommendation needs two signatures before the committee decides.
Yes. Therapy areas, modalities, the royalty stack limit, the sweep schedule, the weight of each function in the score, the score bands, the function reviewers and the sign-off rules are all settings.
The Agentic Solution Engine builds and deploys it from your requirements — your search criteria, memo templates, scoring weights and a past data room — and it goes live once every quality gate has passed. We will walk you through it on one of your own past deals 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 run the Diligence Workbench on a past deal of your own.