AI operations infrastructure: a routing layer that connects your models by cost and capability, cost attribution your CFO can read, governance documentation your legal team can work from, and an audit trail that survives a compliance question.
Built and run in production: AIOS is the AI operations system I built for my own consulting practice. It routes tasks across Claude, local models (Ollama), and GitHub Copilot based on cost and capability. Every task is logged with billing attribution — I can answer “what did AI cost this week” at any time. The system maintains over 50 specialized agent personas. Every client implementation is an adapted version of this architecture, not a theoretical framework.
This page is for organizations where AI adoption has already happened — or is about to — and the infrastructure layer hasn’t kept up. Editorial teams using AI without content governance. L&D departments deploying AI into learning environments without accountability documentation. Brands where the comms and marketing teams are running AI tools with no audit trail. The common problem is not the model; it’s the missing layer between the model and the organization.
Who this is for
- ✅ Editorial organizations and publishers where AI tools are already in the newsroom but there’s no routing layer, no cost attribution, and no clean answer when the editor-in-chief asks what the AI is actually doing.
- ✅ Corporate L&D departments and post-secondary institutions deploying AI into learning environments — where governance, accountability, and pedagogical integrity questions carry additional weight beyond a typical AI deployment.
- ✅ National brands where marketing, comms, and product teams have adopted AI tools without a governance layer — no audit trail, no cost attribution by team or project, and no documentation that legal and finance can work from.
- ✅ Organizations that have received an AI strategy report and are now trying to implement it but don’t have the technical depth to build the infrastructure layer themselves.
- ❌ Organizations at the “should we try AI?” stage. This work assumes adoption has happened or is imminently decided. For pre-adoption strategy, book a discovery call first — the engagement scope is different.
- ❌ AI implementations that are purely a vendor integration — plugging in a single product API with no routing, governance, or multi-model architecture required. That’s a development task, not an AI ops engagement.
What I build
Routing architecture
A decision layer that routes tasks to the right model based on cost, capability, and context — not just defaulting everything to the most expensive frontier model. Claude for complex reasoning and voice work. Local models (Ollama) for routine generation, formatting, and syntactic tasks. GitHub Copilot for code generation within the Copilot subscription. The routing rules are documented, auditable, and tunable as the model landscape changes.
Agent persona library
Specialized agent personas scoped to your team’s actual roles — not generic chatbots. An editorial agent that knows your style guide. An instructional design agent that works within your curriculum standards. A legal review agent that flags the right things for your organization’s exposure. Personas are built from role-specific context, documented, versioned, and maintained as team needs change.
Cost attribution and billing
A logging layer that captures every AI task: model used, tokens consumed, estimated cost, routing decision, and the team or project it belongs to. Output is a structured ledger that answers “what did AI cost this week, by team” — not an estimate and not a vendor dashboard. Finance can read it; so can a procurement audit.
Governance documentation
The documentation layer that makes AI adoption legible to stakeholders who aren’t running it: routing policy, model selection rationale, human-review thresholds, data handling rules, and the approval trail for decisions that have downstream accountability. Written for legal and compliance review, not for developers. Structured to survive a procurement question or a board inquiry.
WordPress and LMS integration
For organizations whose content and learning infrastructure runs on WordPress and LearnDash: the AI ops layer integrated directly into the existing stack — not a parallel system that lives outside the tools your team already uses. AI-assisted content workflows, intelligent LMS interactions, and the audit trail that survives a compliance review inside the platform your team already operates.
Engagement model
- AI Ops Audit — $4,800 CAD flat. Ten-day diagnostic of your current AI adoption: what models are in use, what tasks are being routed to them, what the governance gaps are, and what the infrastructure layer needs to look like. Written report and a 90-minute debrief session. If you proceed to implementation within 90 days, the audit fee is credited in full.
- AI Ops Implementation — $22,000–$32,000 CAD. Full build of the routing layer, agent persona library, cost attribution system, and governance documentation. Scoped after the audit. Fixed price — confirmed before the implementation starts. Includes a handoff session with your team and 30 days of post-launch support.
- AI Ops Retainer — from $2,800/month CAD. Ongoing advisory and maintenance for organizations that have implemented the infrastructure and need a senior technical voice as the model landscape evolves — new model evaluation, routing rule tuning, governance documentation updates, and the monthly review session that keeps the system calibrated.
Book a discovery call or email at cross@thisismyurl.com. A 20-minute call is enough to determine whether the audit is the right starting point and what the implementation scope is likely to look like.
Product names referenced on this page — including Claude, GitHub, and WordPress — are trademarks or registered trademarks of their respective owners. Training offered here is independent and is not affiliated with, endorsed by, or sponsored by any of these companies.