Financial services
∎ proven“A transfer never leaves an account below zero.”
Limits, entitlements, reconciliation. Evidence ready for the audit before the audit is scheduled.
formal verification, applied
Banks, hospitals and safety-critical teams now ship code written by AI agents. Predictable Machines proves that code does what your requirements say, on every change. The product is Predictable Code.
A requirement is one sentence your team already says out loud. We turn it into a formal specification that a program checks deterministically. The examples below are illustrative.
“A transfer never leaves an account below zero.”
Limits, entitlements, reconciliation. Evidence ready for the audit before the audit is scheduled.
“A record is read only by a member of the care team.”
Access rules, clinical workflows, data handling. The same check for a contractor's code and an agent's.
“No command is sent while the interlock is open.”
State machines, interlocks, failure modes. Every path through the code, not the ones a test happened to take.
“Every telemetry frame is validated before it is used.”
Parsers, protocols, units. A defect is reported with the line that causes it.
Also used in scientific research and streaming media.
Every change is checked against every requirement, plus the defects no spec mentions, like a crash on a missing value.
A program decides what passes, not a model. The same code and spec give the same answer in the editor, in CI and a year later. That determinism is what turns a check into evidence.
The developer knows before pushing, on the line that causes it. A fix counts once it has been checked again.
Agents write the code. We verify it.
Nov 19, 2026 · Formal Verification
What David and I talked about at Lambda World 2026: why AI-written code needs formal verification, how Lean gives us the tools, and how Predictable Code checks Java, Kotlin, TypeScript and C# with one engine.
May 6, 2026 · Engineering
AI writes the code. AI reviews the code. A human clicks merge. Who is actually responsible? We explore the accountability gap in AI-generated code, why it matters most in regulated industries, and how cryptographically verifiable proof chains change the equation.
May 5, 2026 · Engineering
Stale docs are now context for AI tools generating new code. We explore three-way drift between specs, docs, and code, and how Predictable Code keeps them in sync.
Apr 14, 2026 · Engineering
AI coding tools lose context between sessions and across teams. We explore how Predictable Code addresses the fragmentation problem by turning your codebase into shared, AI-readable specifications.
Mathematicians and software verification engineers in Seattle and Cádiz, built around one concern: AI is moving faster than the verification needed to scale it responsibly.
Use Predictable Research to get accurate proven research results with sources and proof traces.