Platform · Tools

Workflows, agents, and analytics for science

Your dream assistants: Deep hypothesis agents, evidence extractors, clinical trial designers, researcher benchmarkers, organization analyzers, and more.

Deep hypothesis exploration

Hypothesis exploration, the way science should be done

Take any hypothesis — one of your own or one already in the literature — and the agent finds the context and gathers supporting and refuting evidence. See exactly where a claim stands across the whole corpus, not limited to a single paper's perspective.

HypothesisB-cell depletion lowers relapse rate in RRMS
First proposed 2019 · 3 variants · linked to 22 hypotheses
18 supporting4 refutingfrom 22 sources
SupportsNEJM 2022 · 46% fewer relapses vs. placebo
SupportsLancet 2023 · effect sustained at 24 months
RefutesCohort 2021 · no benefit in progressive MS
Workflows

Deep research with a click

Have agents made for the task conduct deep literature reviews, competitive landscape mapping, and asset risk and opportunity assessments. Each step is grounded in the graph and every claim traces back to its source.

Competitive landscape · anti-CD20 in MSRun ▸
  1. Pull every trial, asset and program for the target
  2. Cluster by mechanism, phase and sponsor
  3. Draft a benchmarked summary with citations
AERIS · grounded in 214 sources
Clinical trials

Analyze trials and design better ones

Map relevant trials by molecules, targets, phases, sponsors, endpoints, and outcomes. Assess gaps in inclusion or exclusion criteria, geography, powering, and more. Design your own trials armed with data and agentic support.

Trial landscapeAnti-CD20 in relapsing-remitting MS
38active trials
Phase IIImost advanced
12sponsors
I · 9II · 14III · 11IV · 4
Design support · incorporating insights
Primary endpoint: annualised relapse rate — used in 82% of comparable trials
Suggested arm size: 300+ per prior Phase III power calculations
Watch: B-cell rebound at week 24 — observed in 3 prior trials
Agents

AERIS chat that reads a trusted graph

Ask in plain language. The agent is constrained to AllSci's trusted scientific corpus and brings back fully cited, supporting and refuting content so you have the real picture on any topic.

AERIS Agent · drafting assessment
Across three Phase II readouts, the asset shows a consistent ORR benefit vs. standard of care, though overall-survival data remain immature…
NCT05*****ASCO 2025Hypothesis #4,102
Benchmark

Identify leading voices on any scientific concept

Rank researchers and organizations by any concept according to a wide range of metrics from publications to patents to clinical trials to geography.

#ResearcherOrganizationHypothesesArticlesClinical TrialsPatents
1Massimo FilippiUniversità Vita-Salute San Raffaele221,42050
2Ludwig KapposUniversity of Basel2898910
3Xavier MontalbánVall d'Hebron University Hospital2398240
4Frederik BarkhofAmsterdam UMC · Vrije Universiteit2386220
5Gavin GiovannoniQueen Mary University of London1685430
6Maria A. RoccaSan Raffaele Scientific Institute1281220

Illustrative example for demonstration — not live platform data.

Comparisons

Compare individuals and organizations

Analyze how organizations or individuals compare with each other in terms of grants or scientific output over time.

Grant funding · immunology · last 5 yrsAwarded
Broad Institute
$412M
Dana-Farber
$348M
MD Anderson
$317M
Scripps Research
$244M
Automation

Alerts and reports on your topics

Set a watch on a target, a competitor or your own work. AERIS surfaces new evidence when it lands and can draft a running report you never have to start from scratch.

New Phase III result for anti-CD20 in RRMS2h
3 new hypotheses cite your 2024 paper1d
A competitor filed a patent in your area2d
Tools

~4× better at grounding claims in evidence.

General models assert; AERIS cites. On the Evidence-Grounding axis of ASC-QA-Val, AERIS answers stay tied to real, retrievable sources — including the refuting ones.

frontier best · 32.1
17.8%
GPT-5.2
32.1%
Opus 4.7
69.2%
AERIS-discovery