Skip to content
Work with us

Research roadmap

Lemma runs today on leading foundation models with our own verification and evaluation layer. This page shows what comes next, and where each stage stands.

Stages

  1. In production

    Now

    The Lemma engine

    Our verification layer on leading foundation models, running in our product and in enterprise agents.

    • –Step-level confidence and review routing
    • –Step Validity evaluation on real work
    • –Full reasoning traces for every answer
  2. In development

    Next

    Our first model

    A model trained on verified reasoning traces, built to check steps more reliably and more cheaply than a general model.

    • –Trained only on data we have the right to use
    • –Measured on Step Validity before it ships
    • –Published with its evaluation results
  3. Planned

    Then

    Our models under the engine

    Theoratix models do most of Lemma's work, with foundation models wherever they are still the better choice.

    • –Same product, lower cost per answer
    • –Private deployment inside client networks
    • –Research published as we go
  4. Goal

    Goal

    The frontier of reasoning you can check

    The most reliable reasoning systems for decisions that have to be explained, measured in public.

    • –Leading results on public reasoning evaluations
    • –A safety framework applied to every release

How we will get there

Our safety framework
  1. Status, not datesEach stage says whether it is in production, in development or planned. We will not call something launched until it is.
  2. Measured before it shipsA Theoratix model replaces a foundation model inside Lemma only when it does better on Step Validity and on the work itself.
  3. Data we have the right to useModels are trained only on data we own, public data, or client data covered by a written agreement.
How Lemma worksHelp us build it