v2 Entry Point

AI Changed Everything.
Except the Hard Parts.

The cost of writing software collapsed. The cost of trusting it didn't. That gap is the biggest problem in software right now.

The Shift Everyone Feels

AI writes code 5-10x faster. So why aren't teams moving 5-10x faster?

AI writes code, tests, and scaffolding at superhuman speed. That's real. But ask anyone shipping software at scale: are you actually going faster?

Pre-AI Developer Time Distribution
Writing Code
Review
Security
Architecture
With AI Developer Time Distribution
Writing
Reviewing AI Code
Security Audit
Architecture
Understanding AI
Writing Code
Code Review
Security
Architecture
Understanding AI Output
The work didn't disappear. It shifted.
What Sam Is Solving

The Factory Inspector Problem

Imagine a factory where robots now do all the assembly — 10x faster. Amazing! But someone still has to inspect every product, check for safety, make sure it all fits together.

Those inspectors are now the bottleneck. The factory can build faster, but it can't ship faster.

Sam is building a tool that lets the robots prove each product is correct as they build it — so you don't need as many inspectors.

Spell-Check vs. Grammar-Check

Spell-check doesn't help with "their vs. there" — you still need a human to read the whole thing. Sam's tool is like grammar-check that catches the things spell-check misses, automatically.

Current AI coding tools are spell-check. Sam's tool is the grammar-check layer that's missing.

Why It Matters

Software runs everything.

Your banking app, your car's navigation, hospital records, airline bookings — all software. AI is writing more and more of it. Someone needs to make sure it's correct.

Sam's tool does that automatically, for all possible cases, not just the ones you think to test.

What Success Looks Like

Sam's tool becomes the standard way software teams verify their code is correct — like how Excel became the standard for financial calculations. Every team uses it, because the alternative is trusting code you can't fully check.

The Verification Crisis

The numbers tell the story

AI code generation is exploding. Trust is collapsing. The gap between the two is the opportunity.

0%
of devs don't fully trust AI-generated code
0%
actually verify AI output before shipping
0x
longer AI PRs wait for human review
0%
of AI-generated code fails security tests
0%
of committed code is now AI-generated
0%
projected AI-generated code by 2027

Trust is falling as adoption soars

Developer trust in AI code dropped from 40% to 29% while adoption rose from 67% to 84%. These lines are diverging fast.

AI Adoption Trust in AI Code
The $40B Problem

Developer tools market — verification is the fastest growing segment

The trust infrastructure for the AI coding era. As AI writes more code, the market for verifying that code grows proportionally. This isn't a feature — it's a new category.

The Business Model

Open Source
AG Framework

Adoption flywheel

Compiled Evaluator

Production performance

Enterprise
Verification Infra

CI/CD integration

See full business model →

Tao Saw This First

AI made generating academic research cheap. Peer review became the bottleneck. Terence Tao's answer: formal verification. Let machines check proofs instead of waiting for humans.

We're doing the same thing for software.

Comparable Trajectories

Prisma — made databases safe via schema
Vercel — made deployment trustworthy
Rust — the compiler proves memory safety

Each removed a class of human review by making correctness automatic. We do the same for code verification.

The P vs NP Insight

Verification is easy. Knowing what to verify is hard.

Verifying a property is computationally cheap (P). Discovering where to assert it, what annotations to write, how to restructure code for provability — that's the hard part (NP-like).

Traditionally humans did the NP part. That's why formal methods were expensive — not because verification is hard, but because annotation authoring is hard.

AI agents change this equation entirely.

🤖
AI Agents
Generate candidate annotations
NP → Cheap
AG Framework
Formally verifies each claim
P → Always Cheap
💡
Cascade
Each proven fact enables more inference
Sudoku Effect
What You Can Prove

Not testing. Proving. Over all possible inputs.

🔒
Security

Prove user input never reaches SQL without sanitization — across all code paths, not just tested ones.

🏛
Architecture

Prove external API calls only happen through the integration layer. No backdoor imports. Enforced at compile time.

Properties

Prove idempotency, purity, commutativity of specific functions. Mathematical guarantees, not test coverage.

📊
Higher Abstraction

C4 architecture diagrams where every arrow is a verified property. Documentation that can't drift from reality.

How

AG-based analysis + abstract interpretation

🎯

Proving, not sampling

Abstract interpretation over all possible inputs. Not fuzzing — mathematical proof.

📝

TypeScript-native syntax

Annotations embedded in code using familiar TS patterns. Zero new language to learn.

Bidirectional inference

Top-down AND bottom-up analysis. Traditional static analysis only goes bottom-up.

Compiled evaluator

Self-hosted validator. Production-ready compiled evaluator for CI/CD performance.

The Agent Symbiosis

A feedback loop that gets smarter

AI agents generate annotations (the NP part — now cheap). The framework verifies them formally (P — always cheap). Each verified property enables inferring more properties. And here's the key:

The agent can restructure code to make properties more provable.

Each refactor makes more things provable. Each proof constrains the space of possible bugs. The system gets more certain over time, not less. This is the opposite of how testing works — tests give diminishing returns. Proofs compound.

// Agent discovers: this function isn't provably pure
// Agent refactors: extracts side-effect to boundary
// Framework proves: inner function is now pure
// Cascade: 14 downstream properties now provable
// Total verification coverage: 34% → 61%
This Is Already Working In Another Field

Mathematics solved this problem first

You don't need the same level of trust when the system checks correctness.

Terence Tao — Fields Medalist, on using Lean for formal verification in mathematics

The Equational Theories Project: 99.9963% completion in 19 days

AI made generating mathematical conjectures cheap. Peer review became the bottleneck. Lean replaced peer review with formal verification. We apply the same principle to software: replace code review with formal verification.

Want to go deeper?

Each page explores a different angle.