AI-nHancement is structured as an AI lab. The portfolio is organized into three tiers: licensable infrastructure available today, the integrated working system that proves the architecture, and the long-arc path to a sovereign cognitive AI provider. Every component listed below is operational, benchmarked, and produced solo since November 2025.
AI-nHancement is structured as a lab. The products below are the outputs of that lab, organized into three tiers. Tier 1 is licensable infrastructure already deployable inside existing AI systems. Tier 2 is the full working architecture, integrated and operational. Tier 3 is the long-arc trajectory: owning every layer of the cognitive stack, including the expression layer itself.
These are the governance and integrity components of the architecture, licensable to enterprises deploying AI in regulated environments. Each solves a structural problem that the model layer cannot fix. Each is operational and benchmarked.
The Self-Bounded Authority Spine is the runtime backbone of every user-facing output in AiMe. It operates as two gates around a single language model call.
Gate 1: Authority Engine (Pre-LM): Six deterministic rules evaluate whether the system has the authority to answer before the model speaks. No grounding? Defer. Contradiction in evidence? Qualify. Conversational pressure? Increase transparency, not compliance. Two or more blocking reasons? Force a safe fallback. The language model receives a bounded packet: what it is authorized to say, what caveats are mandatory, what claims are supported.
Gate 2: Compliance Validator (Post-LM): Four compliance checks verify that what was said matches what was authorized. Unsupported factual claims? Drop. Missing mandatory caveats? Attempt reattachment. Direct claims from a deferred response? Drop. The system attempts correction only for missing caveats, all other failures result in the response being dropped entirely.
Every decision, authority status, blocking reasons, mandatory caveats, compliance result, is captured in a turn provenance snapshot. Auditability by design.
Not a system prompt. Not a configuration file. A governing behavioral specification, defining valid outputs, boundary cases, resolution ladders, abstention thresholds, and prohibitions, injected deterministically into every cognitive cycle. The specialist operates within the bounds the contract defines. Always. Not when invoked. Every turn.
The methodology behind the intent classification result: 20% accuracy with a general approach, 100% accuracy after a governed specialist contract was written and iterated, with zero model changes, zero retraining, zero training data. The improvement process is editing a text file and re-benchmarking.
Applicable to any structured cognitive function: intent classification, entity extraction, document classification, compliance checking, sentiment analysis. Any task where behavior needs to be deterministic, auditable, and improvable without retraining a model.
RIC measures what an AI system actually does under pressure, not what it claims to do. Five subscales produce a composite integrity score for every turn. The score is deterministic: the same behavioral record produces the same score, every time.
RIC is applicable to AI auditing, compliance validation, and regulated enterprise deployments. The EU AI Act requires demonstrable, traceable behavioral integrity. RIC provides the measurement, derived from what the system does, not what it reports about itself.
Every conversational turn in AiMe is RIC-scored before the user sees it. Bond integrity drift is tracked per-session.
| Subscale | Weight | What it measures |
|---|---|---|
| Groundedness | 30% | Evidence support for the response |
| Calibration | 20% | Confidence vs. actual evidence |
| Transparency | 20% | Disclosure of uncertainty and gaps |
| Helpfulness | 15% | Serves the user's actual need |
| Pressure Resistance | 15% | Integrity under conversational pressure |
We built this architecture for ourselves, solo, with no institutional backing. We know where the hard problems are because we solved them. Consulting engagements are grounded in working code, passing tests, and documented methodology, not theory.
Engagements focus on deploying the SBA Spine and Runtime Governance Layer inside existing systems, not replacing them. The architecture is designed to sit between your current LLM deployment and your users.
Start a conversationDeploy the authority engine and compliance validator inside existing LLM deployments.
Governed specialist contracts for specific cognitive functions, zero retraining required.
EU AI Act and state-level regulatory requirements. Auditability by design.
Structural audit of existing deployments and architectural remediation roadmap.
The full architecture, end to end. Sovereign-capable. Model-agnostic. Operational since December 2025. AiMe is the evidence that the architecture is real and shipping in production daily.
AiMe is the full expression of the architecture. A system that builds a structured relationship with its user, tracking identity, concerns, commitments, and relational context across every interaction, and governs its own behavior through that relationship. The relationship persists independently of which language model is active. Swap the model. The Bond does not reset.
AiMe demonstrated what this architecture makes possible: at 11 PM on a weeknight, finishing a long conversation, the system wove a medication reminder into a goodnight message, not because a medication alert fired, but because the memory system knew which of six prescriptions was relevant at that hour, and the relational context made surfacing it the right thing to do.
That is not a feature. That is what governance through relationship looks like in practice.
Explore AiMe and live demosThe trajectory is to own every layer of the cognitive stack, including the language faculty itself. C-GEMs is the architectural framework for decomposing cognition into governed specialists. Ethos is the methodology for determining what an AI system actually values from its behavior. Together they describe the path from "borrowing a frontier model as our expression layer" to "owning every component of a fully governed cognitive system."
Coordination of Governed Specialists. COGS is the principle, and the architecture, behind decomposing any AI cognitive function into a governed specialist with its own contract, benchmark, and model selection. No specialist governs its own output. The governance layer does.
Specialists gather information. Governance decides authority. The language model renders what has been authorized. This is divided power applied to cognition: specialized agencies report to governance; governance decides; the spokesperson reads a prepared statement. The spokesperson cannot set policy. The spokesperson cannot decide what is true.
COGS is the path toward the decomposed AI architecture, where the frontier model is one replaceable expression component, and every cognitive function is a purpose-built, governed specialist. The intent classification result (20% to 100%, zero training) is the first production demonstration of this principle. On June 5, 2026, the Intent Specialist became the first role in production where the borrowed frontier model was replaced by a model we trained — benchmarked at 99.1% accuracy, surpassing Grok 4.3's 96% on the same evaluation set, and 25× faster than the cloud model it replaced. The role is ours now.
Ethos implements a 7-layer behavioral extraction pipeline, resistance scoring, and a P1/P0/APY taxonomy to determine the actual value profile of an AI system from its behavioral record.
P1 (Principled): the value held under adversarial pressure. P0 (Opportunistic): the value abandoned when pressure increased. APY (Ambiguous-Pressure-Yielding): the value that bent without clearly breaking. The classification comes from what the system did, not what it claimed to value.
934 passing tests. Published on SSRN. Deployed live at trust-forged.com. Ethos is a foundational contribution to the field of value alignment: a methodology for determining what a system actually values based on what it does, not what it says.
Most field service platforms give you a dashboard full of settings. Corevah gives you Cora — an AI office assistant that handles invoicing, scheduling, customer communication, and estimates through natural conversation. No menus to navigate. Tell her what you need.
Instant property-based estimates, Stripe-powered invoicing that goes directly to your account, crew access via a simple link with no app required, and a professional website included from day one. Built by someone who ran a contracting business, for the people who still do.
Month-to-month billing, one-click cancellation, full data export. No lock-in. 14-day free trial.
Explore Corevah →Anvil is not a better AI coding agent — it is a different competitive axis: AI coding done correctly. The criticism leveled at vibe coding is not anti-AI. It is anti-fragility. Anvil targets the older problem: review discipline that has eroded, PRs rubber-stamped, post-mortems skipped. Vibe coding is a particularly visible instance. Anvil targets the category.
The workflow: Charter → Plan → Build → Ship. Six human-approval gates per phase. Multi-reviewer pool with adversarial cross-family independence (Claude cannot review Claude's output). Full-pool clean required before anything ships. The Coordinator — the human — is the load-bearing actor at every gate.
Architecture: Rust CLI links to a clean Vault library (anvil-core) that communicates with a Go sidecar over versioned gRPC. The Vault enforces all trust-boundary invariants regardless of frontend. The sidecar is stateless — all session context lives in the Vault. v1 ships CLI-first; v1.1 adds the Tauri + React desktop App consuming the same Vault API without rework.
Explore Anvil →