Skip to content
Contact usOpen Mantis

Use cases

Built for the teams pushing science forward.

Representation superintelligence changes the work of every research team: the whole of what it knows, in view at once, with an agent that reasons over it and shows its evidence.

Trusted by teams at

  • Massachusetts Institute of TechnologyMIT Computer Science and Artificial Intelligence Laboratory
  • Broad Institute of MIT and Harvard
  • Tsinghua University
  • Stanford University
  • University of California, Berkeley
  • University of Oxford
  • Harvard University
  • The University of Texas at Austin
  • University of Cambridge

01

Discovery biology

Every cell, sample and study in one representation. Mantis finds the population that carries a signal, compares conditions inside it, and cites the cells.

  1. Bring cells, samples and studies into one Space; each record keeps its metadata.
  2. Search the map by meaning to find the populations that carry a signal.
  3. Outline a population, save it as a bag, and compare conditions inside it.
  4. Ask Mantis for the answer, with the cells and studies it rests on cited.

On real data:The immune response to severe COVID-19, cell by cell Which neurons Alzheimer’s disease takes first The human proteome, read by a protein language model

02

Chemistry

Compounds placed by structure and activity. Mantis triages leads with their computed properties and their neighbours on the map beside them.

  1. Lay compounds out by structure, with their targets and properties as fields.
  2. Read a compound beside its computed properties and its neighbours on the map.
  3. Triage leads and analogues into bags the team shares.
  4. Ask Mantis which scaffolds hit a family, and see the compounds behind the answer.

On real data:Kinase inhibitors by structure and target

03

Literature and evidence review

A field read at once. Mantis groups thousands of papers by what they say and links each finding to the papers behind it.

  1. Map a field: thousands of papers placed by what they say, grouped into named topics.
  2. Compare topics over time by year, journal and citations.
  3. Select a region and read its papers without leaving the map.
  4. Ask Mantis for a synthesis that links each finding to the papers behind it.

On real data:Alzheimer’s disease research since 2000

04

Data science

Any table, notebook or repository embedded and navigable. Agents work through the same tools as you, and every step is inspectable.

  1. Embed a table, notebook or repository from the workspace or with the Mantis CLI.
  2. Let agents work through MCP and the Mantis CLI with the same tools you use.
  3. Run code against the points behind any selection.
  4. Keep every step of an investigation in its thread, in order, inspectable.

On real data:A map of Mathlib

05

Research leadership

Situational awareness across every project: what changed, what is related, and what matters now, with the evidence one click away.

  1. See every project’s Spaces in one place, shared with the people who need them.
  2. Read the shape of a field or a portfolio before reading a single document.
  3. Share findings as bags and threads the whole team can open.
  4. Ask Mantis what matters now, and follow each answer to its evidence.

On real data:The S&P 500 by business model

Work with us

Bring representation superintelligence to your team.

Start in the workspace today, or talk to us about your data, your deployment and your questions.

Open Mantis Talk to us