From a one-line indication to a cited protocol synopsis.
Most drafting tools start from a library of your documents. At the earliest stage of a program you don't have one yet — you have an indication and an idea. Asthra's seed-then-expand flow drafts the whole synopsis forward from that seed, structures it to ICH M11, grounds each design choice in comparable registered trials, and hands you a confident, cited draft to steer. It's the newest capability we're building, and it's open for early-access pilots.
Start from one line
A bare indication is enough to begin — the thinner the seed, the more Asthra surfaces for your review.
ICH M11 structured
Mapped to the harmonized protocol template, with objectives paired to endpoints per ICH E9(R1).
Every claim cited
Design choices grounded in comparable registered trials; background drawn from the literature.
Seed-then-expand, not retrieve-and-ground.
When there's a source library, Asthra drafts by retrieving from and grounding in it. When there isn't one yet, it inverts the model: you start from a bare indication, and Asthra generates the synopsis forward — then that synopsis becomes the seed for the full protocol.
Start from a sentence, or a fuller picture.
Intake is open-ended by design — you're never stuck at a form.
A one-line indication
“A Phase 3 trial of an oral agent in adults with type 2 diabetes.” Enough to generate a complete first synopsis.
Or a fuller brief
Population, comparator, phase, target outcome — the more you give, the fewer assumptions Asthra has to make.
Registered trials
ClinicalTrials.gov, for the design commitments — endpoints, eligibility, sample size — drawn from comparable trials.
Published literature
PubMed, for disease background, epidemiology, and standard of care.
Draft-through, not a checklist.
Seed the run
Give Asthra the indication — a sentence or a brief. It confirms the design intent and begins generating forward.
Auto-draft what's known
Background and rationale are drafted from a light pass over the literature — a few high-signal references synthesized into a brief, cited narrative.
Guide what's decided
Objectives, endpoints, eligibility, design, and statistics are handled as evidence-guided decisions: Asthra weighs what comparable trials did, chooses the best-supported option, drafts it, and shows its work.
Review the decisions
Every design commitment surfaces as a reviewable decision — chosen value, one-line rationale, citations, and two or three cited alternatives from comparable trials. Swap any choice in a single action.
Cascade & carry forward
Swaps cascade: change the primary endpoint and the sample-size justification and analysis approach re-derive to match. Once approved, the synopsis seeds the full protocol.
The work shifts from authoring to deciding.
Rationale: the standard registrational endpoint for Phase 3 type 2 diabetes trials.
Evidence: multiple comparable registered Phase 3 studies.
Alternatives: Proportion achieving HbA1c < 7.0%; Time to initiation of rescue therapy — each with its own supporting trials.
Swap in the responder endpoint, and the sample-size assumptions and analysis approach update to match — because in a real protocol those things were never independent. Reviewing a confident, cited draft and steering it is faster, and truer to how experienced writers work, than answering a checklist cold.
Indication → synopsis → full protocol.
The synopsis is step one, and deliberately the seed for the next artifact. Once approved, it grounds the full protocol, where the body sections expand from the design the synopsis locked in — a cascade, each stage feeding the next.
On AI-assisted protocol synopsis drafting.
What is an AI protocol synopsis tool?
It drafts the protocol synopsis — the concise, decision-dense summary that anchors a clinical study — from a short description of the trial. Asthra generates it forward from a one-line indication, structures it to the ICH M11 template, grounds design choices in comparable registered trials, and surfaces each choice as a cited decision the writer can keep or swap.
What do you need to generate a synopsis?
As little as a one-line indication — for example, “a Phase 3 trial of an oral agent in adults with type 2 diabetes” — or a fuller picture with population, comparator, and target outcome. Whatever is missing, Asthra fills with a conservative, cited assumption and flags it for review rather than blocking to demand it.
Where does the evidence come from?
For design commitments — endpoints, eligibility, sample size — Asthra draws on ClinicalTrials.gov, synthesizing the recurring, regulatorily-accepted choices from comparable registered trials. For disease background and standard of care, it draws on PubMed. Every claim is captured with its citation and rolled into the bibliography automatically.
Is this available today?
The seed-then-expand synopsis flow is in active development and available for early-access pilots. The full protocol drafting it feeds into, and Asthra’s grounding, citation, and audit machinery, are already part of the platform. Talk to us to join early access.
Get early access to
seed-generated synopses.
This is the newest flow we're building. Tell us about your program and we'll bring you into early access — and put Asthra's protocol and safety drafting in front of you today.