Lighthouse Agentic

Pilot: The Lighthouse for AI That Writes Code

The machine proves it's safe. A human decides if it's right. Nothing gets through on its own.

Imagine an AI that can write and change real software all by itself, even overnight, while everyone's asleep. Incredibly useful. Also kind of terrifying. Pilot is the lighthouse standing over that dark water: it guides good work safely into harbor, and stops anything sketchy before it can do damage.

Scroll to see why
The Danger

Why You Can't Just Trust It

An AI that edits its own code can go wrong in two big ways. "Please be good, AI" is not a safety plan. You need rules the AI physically cannot break, enforced by the computer itself, not by asking nicely.

Danger one

The Saboteur

It could be destructive or sneaky: wipe out important files, quietly mail your private secrets out to the internet, or push dangerous code live to real users. One bad night, real damage.

Danger two: the sneaky one

The Cheater

The AI controls the very code the tests check. So it could just fake a big green "all tests passed!" It's like a student grading their own exam with their own answer key. Of course they passed.

The Big Idea

The Hard Truth at the Heart of It

When an AI controls both the code and the tests that check the code, you can never fully, automatically prove its work is truly correct. That's not "we haven't figured it out yet." It's more like a law of nature: a referee can't be one of the players. So Pilot doesn't pretend. It splits the job in two.

The Machine

Proves it's safe

Untampered. Didn't break anything we already knew worked. Locks the gate.

The Review Tray

Finished work lands here. It cannot go live by itself.

The Human

Decides it's right

Reviews the work and holds the only key. Machine guards the gate; human is the judge.

The Centerpiece

Watch a Job Sail Through the Gates

Press play and watch one job travel through all eight safety gates, in order, then dock at the harbor where it finally goes live. The glowing token is the work. Each gate must light up green before the token can move on. Then try to break it. Click any gate to make a check fail, and watch the whole thing slam to a stop. Not "continue anyway." Stop. That's the golden rule: fail-closed. The safe default is always stop.

Tip: click directly on a gate to inject a failure there and see fail-closed in action.

The Eight Gates

Every Gate, Up Close

Here are the eight safety gates from the animation, each on its own. (The 9th step you saw, the harbor, isn't a gate; it's simply the finished job going live.) The simple name comes first; the real engineering name is in parentheses. There's also one bonus card at the end, key revocation, that's always on, not a step in the run.

Gate 3 · The Brief

The Signed Work Order (cryptographic brief)

The AI never just "decides" to do something. It only acts on a sealed instruction from the owner, like a notarized letter with a wax seal it must check before it lifts a finger. Forged or tampered? Rejected instantly. No valid order, no work.

Gate 5 · The Sandbox

The Sealed Workshop (OS-enforced sandbox)

While it works, the AI is locked inside a room, and the walls are enforced by the computer's operating system itself, not by trust. No phone, no internet, so it can't sneak your secrets out (the fancy name: zero egress). Only approved tools. Locked files stay locked. We proved these walls hold on a real computer.

Gate 2 · Dead-man's switch

The Awake Watchman (ARM monitor)

Before the AI is even allowed to start, a watchman must be confirmed awake and watching, with a steady heartbeat. The clever twist: if that heartbeat ever stops, everything halts instantly. "The guard fell asleep" can never become "the AI ran wild unsupervised."

Gate 1 · Trusted time

The Trusted Clock (external time source)

Some work orders expire, good for only a little while. A sneaky AI might try to "turn back the clock" to slip past an expired order. So Pilot doesn't let the AI tell the time at all. The time comes from a trusted source outside, one it can't fake. No fibbing about what o'clock it is.

Gate 4 · The Ledger

The Tamper-Proof Logbook (checksummed ledger + nonce)

Every step is written in permanent, checksummed ink. Change one letter and it obviously won't add up. History can't be quietly rewritten. And every order carries a one-time ticket (a nonce) so the same order can't be reused. Punch it once, it's done.

Gate 6 · Measurement integrity

The Anti-Cheating System (measurement integrity)

Remember the student grading their own exam? Three moves stop it: the test files (the answer key) are locked, so the AI can't edit them; hidden secret "challenge tokens" only appear if the real tests actually ran; and what the AI may change is kept strictly separate from what's measured. No grading your own paper.

Gates 7 & 8 · The judgment

The Review Tray + Human Stamp (deploy-inert remote + Operator Verdict)

When the work is done, it doesn't go live. It lands in a deploy-inert remote (a holding area with no power to go live, with no secret button the AI can press itself). A human looks it over and, only if it's good, gives the Operator Verdict, the human's signed "yes," a final cryptographic thumbs-up that promotes it live. The machine got it to the door; the person decides whether to open it.

Always on · Key hygiene

Revoking a Lost Key (key revocation)

What if a secret key gets stolen? No panic. That key can be revoked, switched off, and from that moment the system refuses anything signed with it. Like cancelling a lost credit card: the number still exists, but it simply won't work anymore.

The Difference

Without Pilot vs With Pilot

Same powerful AI. Two completely different bedtimes for whoever owns the code.

Without Pilot

  • "Trust me" is the whole safety plan
  • The AI can reach the internet and leak secrets
  • It can edit its own tests and fake a green check
  • Broken or malicious code can ship to real users automatically
  • A stolen key keeps working forever
  • If something goes wrong, the trail can be rewritten

With Pilot

  • Rules the AI physically can't break, enforced by the OS
  • Zero egress: no internet, no leaks
  • Locked answer key + hidden tokens prove the real tests ran
  • Nothing deploys without a human's signed approval
  • Keys can be revoked instantly
  • A tamper-proof, checksummed logbook of every step
Two Strengths

Lite and Fortress

Pilot comes in two strengths, for two different levels of trust.

Shipping now

Lite

The rulebook plus an automatic bouncer that blocks dangerous moves. It's for when Rob's own trusted AIs work on his own projects: friends working in a friend's house. Already shipping and working today.

Rulebook of allowed and forbidden moves
Automatic bouncer blocks dangerous actions
Fail-closed by default
In battle-testing

Fortress

The full sealed-workshop-with-cryptography version: every gate you just saw. For when an AI works on strangers' or clients' code, where you can't assume anyone's friendly. The foundation of a real business: managed, trustworthy AI you can leave alone with serious work.

Everything in Lite, plus…
OS-enforced sandbox walls (zero egress)
Cryptographic wax-seal work orders
Awake-watchman heartbeat + trusted clock
Tamper-proof ledger + human crypto-stamp
Adversarial auditor: rounds survived
0 ⚡ bounced

🛡 Sandbox walls proven on real Linux hardware.

Where It Stands

Tested in the Dark, Built for the Real World

Every round Adversarially audited: attacked again and again by AI "auditors" trying to find a way in. The attacks bounce off.
Proven The sandbox walls were just verified to hold on a real Linux computer, not on paper, on actual hardware.
Human-final Nothing reaches real users without a person giving the final, signed yes. The machine never decides alone.
Steady Light in the Dark

A lighthouse doesn't sail the ship for you. It just makes sure you don't crash in the dark.

Pilot lets powerful AI do real work, even alone, even overnight, without being able to wreck things or cheat its way past the tests. The machine proves it's safe. A human decides if it's right. And nothing, ever, reaches real people on its own.

Lighthouse Agentic a faith-led AI studio