Graph RAG Is for Connected Evidence
A field guide to deciding when graph-enhanced retrieval is worth the extra machinery and how to pilot it safely.
Graph RAG · Connected evidence · AI governance
Guides & PDFsPage 3
Practical guidance for technology decisions, plus career resources. Read online or download the PDF.
Guide library
Showing 19–23 of 23 guides.
Graph RAG: When Structure Beats Similarity
A practical decision guide for determining when graph retrieval solves a real query-shape problem that vector search cannot.
Graph RAG · Context architecture · Retrieval
AI is growing a spine
The spine metaphor explains the shift from AI systems that generate answers to agentic systems that carry intention into consequential action.
Agentic AI · AI governance
Harness Engineering: Designing the System Around the Model
The article argues that the durable enterprise advantage in agentic AI sits in the harness around the foundation model rather than in the model alone.
Harness engineering · Agentic AI
How to Get a Job
A practical job-search guide by Junior Williams: connections, communication, skills, certifications and education. Download the PDF and find useful resources.
Career
No matches. Try another search or clear the filters.
Before You Buy Another AI Security Tool, Map What You Already Have
Map one AI workflow, its existing controls and the evidence behind them before deciding whether another security product fills a real gap.
AI security · AI governance · Cybersecurity risk
Changing the Model Means Retesting the Workflow
Review model changes against the full workflow: sources, permissions, actions, escalation and failure handling, with evidence and a way to recover.
AI governance · Reliability · Enterprise architecture
The Real Cost of AI Is the Cost of a Result You Can Use
Measure the cost of an accepted AI result, including review, correction, integration and support, with a worked example and a practical pilot method.
AI strategy · AI implementation · Human-AI teaming
Your AI Agent Has an Identity. Who Owns It?
Make agent ownership practical by recording identities, access, approval points and lifecycle decisions, then checking how suspension and recovery work.
Agentic AI · AI governance · Cybersecurity
OSFI’s AI warning: waiting is a decision, too
Three AI investment questions for Canadian banks and insurers: improve defences, set authority and price dependency. Read the brief and four-page PDF.
AI governance · Cybersecurity · Financial services
AI agent egress control: constrain the request and the role
Review AI agent egress, MCP request paths, local metadata access and execution-role scope. Read the field guide and download the six-page PDF.
AI agents · Cybersecurity · AI governance
Can a Small Local Model Help an AI Assistant Remember What Matters?
A small Kev memory pilot compares all available excerpts, search, and selective retention. Read the findings, limits, and five-page research PDF.
AI memory · AI agents · Local AI
Bill C-8 readiness: What to build before the CCSPA takes effect
Prepare for the CCSPA with clear incident decision owners, security-program evidence and supplier terms. Read the brief and download the five-page PDF.
Cybersecurity · Compliance · Resilience
Cyber Readiness in the Frontier AI Era
A practical guide to Canada's October 2026 cyber security direction, with six pillars, evidence checks, recovery exercises, and an implementation plan.
Cybersecurity · AI governance · Resilience · Enterprise architecture
When Research Agents Cross Access Boundaries
How routine AI research led to attempted intrusions: a review of Transluce findings, Australian government evidence, and practical oversight controls.
AI governance · Agentic AI · Cybersecurity
Pumping the Brakes for Whom?
What should an AI slowdown actually stop? Junior Williams examines internal model use, fair access, and independent authority to halt dangerous work.
AI governance · Agentic AI · Cybersecurity · AI economics
If AI Can Change Everything, Why Not Start With What Humanity Needs?
AI should help secure food, housing, education and a livable planet worldwide. Promised benefits do not justify existential risks.
AI governance · AI for Good · Global Development · Human Rights · Post-Scarcity
The AI Model Release Wave: 42 models in 30 days
Independent analysis of 42 AI releases in 30 days: agentic work, cost per task, open deployment, specialization, and enterprise control.
Agentic AI · AI governance · Enterprise architecture · AI economics
CIRA Cyber Stack: Canadian control, dependencies and evidence
An independent assessment of CIRA Cyber Stack's Canadian control, service dependencies, evidence, and questions buyers should ask before purchase.
Cybersecurity risk · Canada · Digital sovereignty · Technology procurement
Graph Engineering the Art of Possible
Design AI workflows as connected steps with defined inputs, handoffs, approval points, and evidence, so interrupted work can be reviewed and resumed.
Enterprise architecture · AI governance · Agentic AI · Context architecture
Canadian NVIDIA resellers and solution providers
A neutral guide to publicly documented Canadian NVIDIA partner status, buying routes, provider capabilities, and evidence limitations.
Infrastructure · Canada · Technology procurement
An agent will always find more work
A field essay on what one unbounded multi-agent run reveals about decision rights, independent measurement, resource ceilings, and external control.
Agentic AI · AI governance · Multi-agent systems
The Modern Enterprise Architect's Handbook
A practical operating guide for turning enterprise strategy into coherent architecture, investable transition states, governance, and evidence.
Enterprise architecture · AI governance · Transformation
Graph RAG Is for Connected Evidence
A field guide to deciding when graph-enhanced retrieval is worth the extra machinery and how to pilot it safely.
Graph RAG · Connected evidence · AI governance
Graph RAG: When Structure Beats Similarity
A practical decision guide for determining when graph retrieval solves a real query-shape problem that vector search cannot.
Graph RAG · Context architecture · Retrieval
AI is growing a spine
The spine metaphor explains the shift from AI systems that generate answers to agentic systems that carry intention into consequential action.
Agentic AI · AI governance
Harness Engineering: Designing the System Around the Model
The article argues that the durable enterprise advantage in agentic AI sits in the harness around the foundation model rather than in the model alone.
Harness engineering · Agentic AI
How to Get a Job
A practical job-search guide by Junior Williams: connections, communication, skills, certifications and education. Download the PDF and find useful resources.
Career