Skip to content
NewIntroducing Lemma

Reasoning you can check

An applied AI research lab. Lemma, our reasoning engine, shows every step, so people can check AI instead of trusting it.

How Lemma works

Five steps to an answer you can check

  1. Is n² + n even for every integer n?
    n² + n = n(n + 1)
    n, n + 1 consecutive
    One of them is even

    01

    Decompose

    Breaks a question into claims small enough to check one at a time.

    • Factorisation holds✓ proof checked
    • Consecutive integers alternate parity✓ proof checked
    • Product with an even factor is even✓ proof checked

    02

    Check

    Verifies each claim with code, a proof assistant, a search or a second model.

  2. 0.97confidence · above threshold

    03

    Score

    Gives every step a calibrated confidence, so people know where to look first.

  3. ⚑ 0.62 · pattern, not proofSmall cases look like squares
    Reviewer

    04

    Review

    Sends the steps it is least sure of to a person before anything counts.

  4. claim · n² + n = n(n + 1)

    check · lean · passed

    score · 0.97

    review · approved by reviewer

    Trace saved · trace_4f2a

    05

    Record

    Keeps the whole trace: every claim, check and decision, ready to audit.

Try Lemma

Pick an example or ask your own question. Flagged steps open to show why.

Recorded trace

What is the sum of the first 100 odd numbers?

For developers

One engine.
Every step on record.

Every Lemma answer comes back as a trace: each claim, the check behind it, its confidence, and what went to a person. There is no public API yet; these are sample traces.

{
  "id": "odd",
  "question": "What is the sum of the first 100 odd numbers?",
  "steps": [
    {
      "kind": "claim",
      "text": "The first 100 odd numbers are 1, 3, 5, …, 199.",
      "confidence": 0.99,
      "status": "verified"
    },
    {
      "kind": "claim",
      "text": "Small cases look like perfect squares: 1, 4, 9, 16.",
      "confidence": 0.62,
      "status": "flagged",
      "flag": "Pattern, not proof",
      "why": "A few matching cases suggest a pattern but do not prove it, so Lemma proves the general case by induction before this step counts."
    },
    {
      "kind": "check",
      "text": "Proving 1 + 3 + … + (2n − 1) = n² by induction",
      "result": "Proof checked"
    },
    {
      "kind": "claim",
      "text": "Base case holds. Adding 2n + 1 to n² gives (n + 1)², so it holds for every n.",
      "confidence": 0.99,
      "status": "verified"
    }
  ],
  "answer": {
    "text": "100² = 10,000",
    "confidence": 0.99
  },
  "source": "recorded"
}

Work with us

For research teams

Work with Conjecture

  • Hypotheses with their evidence attached
  • The cheapest test that could prove each one wrong
  • Negative results kept on record
  • Domain review before every project

For enterprises

Strategy and agents on Lemma

  • Find where AI creates value, and what to do first
  • Agents built and run inside your workflows
  • Every action logged with its reasoning
  • Your cloud or your premises