Open server rack showing RIG's production infrastructure and AI deployment setup

The mechanism · the math · the code

How we actually do this.

Q: Can I see the source code?

Yes. The core engine, rigforge, is open source under MIT on GitHub, and the ProofPacket sealing template is free. Several studios are public teasers with source available on purchase.

Q: What is a ProofPacket?

A cryptographically signed, hash-bound record of a result: the evidence behind every claim, the gates it passed, and the verifier that signed off. It makes agent output re-verifiable instead of taken on faith.

Q: Why statistics instead of a dashboard?

A green dashboard can't tell signal from noise. We model results as count distributions and report tail p-values, use robust z-scores to catch drift, and only promote a decision once its confidence is Brier-calibrated.

Most AI services sell effort: a person, working harder, with better tools. We sell a governed system — one whose quality is proven before it ships and whose proof you can read. This page is the engine room: the harness, the statistics that replace the dashboard, and the open-source repositories that back every claim. No mechanism, no claim.

Read the source → Talk to an engineer →

01 · the objective

What the system is built to minimize.

Every engagement points at one objective: deliver the outcome with the fewest moving parts and the least surprise. Stated formally, we minimize a free-energy functional — the gap between what the system predicts and what actually happens, plus the cost of complexity.

free-energy objective

F = 𝔼_q[ −ln p(o | s) ] + D_KL( q ‖ p )

The first term is surprise — how badly the system's model of "done" predicts the real outcome o given state s. The second is complexity — how far our chosen approach q strays from the simplest one that works. Minimizing both at once is the whole discipline: maximum fidelity, minimum machinery. Effort that doesn't reduce surprise or complexity isn't progress.

02 · the harness

The offering is one signed tuple.

We don't ship prompts. We ship a versioned, signed harness — six components that turn a vague "AI project" into a governed system with a contract.

the harness

H = ( E, T, C, S, L, V )

Component	What it is in your system
EEnvironment	The workspace and the real data sources the agent is allowed to touch — scoped, not the open internet.
TTools	An allowlist of executable procedures. Anything external or destructive — sends, deploys, payments — requires a human approval gate.
CContract	The proof obligation. Every cycle must produce a ProofPacket of measured results. The agent never self-declares "done."
SSafety gates	Validators that block bad output before it ships — and ceilings that stop an agent from acting outside its bounds.
LLoops	An inner quality loop per deliverable, a weekly evolution loop, and a self-breeding loop that crystallizes repeated wins into reusable skills.
VVerifier	An independent evaluator with sole authority to terminate. It holds the result against threshold and decides whether it ships. Nothing else can call it done.

03 · separation of powers

The maker is never the grader.

The single most important rule. The thing that does the work is not allowed to decide the work is finished — that's where silent failures come from. We separate four roles, and no agent reviews its own output.

— generator

Does the work

Builds the artifact: the audit, the automation, the result. Optimized to produce, not to judge.

— evaluator

Critiques it

Checks each artifact: is it grounded in real data, or plausible-but-invented? Catches the hallucination.

— verifier

Decides ship

Holds the ProofPacket against threshold θ. Sole termination authority. Only this clears a cycle.

— human

Approves risk

You approve external, irreversible, or paid actions. Everything safe runs autonomously.

04 · honest statistics, not a dashboard

A green dashboard can't tell signal from noise.

Most AI work is graded by eyeballing a chart. We grade on probability. Three instruments do the work.

surprisal — is this result real?

S(o) = −ln P(o)

Before a reported lift goes in a report, we score how surprising it is under the noise model. A "win" that's statistically unremarkable is noise wearing a suit. Counts get modeled as Poisson / Negative-Binomial and we report an upper-tail p-value — not a screenshot of a number going up.

robust drift detection

z = 0.6745 · ( x − median ) / MAD

A robust z-score (median + median-absolute-deviation, immune to outliers) watches every metric. A reading that crosses ±5σ — a sudden rank drop, a quality collapse, an anomalous spike — automatically triggers deep review instead of quietly riding along.

calibrated confidence before we commit

promote iff Brier-validated · E_open ≈ 0

We only promote a decision — "scale this," "this is done" — once its confidence is Brier-calibrated (our stated probabilities match reality over time) and the deliverable's residual open energy is near zero. Confidence is the gate, not the calendar.

05 · when the machine acts vs when you do

Autonomy is earned, not assumed.

Each capability gets a build-mode score (BMS). The higher the proven confidence, the more autonomy it's granted — and anything below threshold escalates to a human.

build-mode routing

BMS ≥ .75 → A1 · .45 → A2 · .25 → A3 · < .25 → A4

A1 runs deterministically, on its own. A2 is a supervised hybrid. A3 is agent-bounded with checkpoints. A4 is human-led with the AI assisting. Any public or irreversible action requires your approval regardless of mode. The system knows what it doesn't know.

06 · why it compounds

It gets cheaper every time.

Three loops turn a one-off build into a system that improves itself.

— inner

Grill loop

Each deliverable runs ≥3 question/answer cycles and only advances when its open energy is ≈0. Kills confident-but-ungrounded output at the source.

— weekly

Evolution loop

We log (input, output, energy, outcome) every cycle, update reliability weights, and recalibrate thresholds. We fix the worst-performing part first.

— on repeat

Self-breeding loop

On the third repeat of a pattern, the proven blocks crystallize into a sealed, reusable harness. The tenth instance is near-instant.

07 · don't take our word — read the source

The repositories that back this.

The core engine is open source. The free template lets you seal your own build into a verifiable ProofPacket today. This is the difference between a claim and a receipt.

rigforgeopen · MIT

The engine. Catch your AI coding agent when it lies about "done." Cryptographically signed ProofPackets make agent output re-verifiable — MCP + OpenTelemetry.

request access →

proofpacket-sealing-templatefree

Seal any build into a hash-verifiable ProofPacket. Proof, not vibes. The fastest way to feel the mechanism on your own code.

request access →

rig-deterministic-build-starteropen

A Vite + TypeScript starter that ships with a sealed ProofPacket — deterministic CI/CD, green tests, and a signed Definition of Done.

request access →

rig-prediction-studioteaser

Offline, Brier-calibrated 12-persona forecasting swarm — the calibration math on this page, made executable. Full source on purchase.

request access →

rig-operating-proceduresteaser

Deterministic spec-to-app scaffold generator with packet-chain enforcement — the harness discipline as a tool. Full source on purchase.

request access →

RIG-Doctrine-Repoopen

The canonical operating doctrine, agent packs, and proof standards. The rules every RIG build follows — in writing.

request access →

Studios marked teaser are public previews; full source ships on engagement — get in touch.

08 · how an engagement runs

Wire the verifier first.

The sequence is deliberate: we stand up measurement and the independent verifier before a single deliverable, so nothing can ship unproven. Intent → Questions → Research → Spec → Quality → Plan → Implement — looping until confidence, not until the clock runs out.

— days 1–3

Wire E + seal V

Connect the data sources and stand up the independent verifier and ProofPacket schema before any build. Measurement first.

— days 4–10

Crystallize generators

Install the work as governed procedures with allowlists and approval gates. Grill-loop on a test target until open energy ≈ 0.

— days 11+

Ship under GEV

First real deliverable runs end-to-end under verifier gating, with a human approval on every external action. Then the evolution loop goes live.

09 · straight answers

What engineers ask first.

Can I see the source code?

Yes. The core engine, rigforge, is open source under MIT, and the ProofPacket sealing template is free — both linked above. Several studios are public teasers with full source available on purchase.

What exactly is a ProofPacket?

A cryptographically signed, hash-bound record of a result: the evidence behind every claim, the gates it passed, and the verifier that signed off. It makes agent output re-verifiable instead of taken on faith.

Why statistics instead of a dashboard?

A green dashboard can't tell signal from noise. We model results as count distributions and report tail p-values, use a robust z-score to catch drift at ±5σ, and only promote a decision once its confidence is Brier-calibrated.

Does the AI ever act on its own against my systems?

Only inside the allowlist and only on actions scored safe. Anything external, irreversible, or paid stops for your typed approval — the human is always the decision-maker on risk.

10 · the next move

Bring me a result you can't currently trust.

Tell me where your AI output is taken on faith. I'll show you exactly how the verifier, the math, and the proof packet would close that gap. It goes straight to my inbox and I answer it myself.

Book a 20-min fit call → See governed agents →

Prefer email or text? mike@rodgersintelligence.com · (262) 343-5680. I reply within 24h, personally.