Search

Find insights, training programs, and workshops

AI Knowledge Systems — RAG, Search, Memory & Internal Knowledge
Intermediate4-5 hoursKnowledge system map + RAG decision framework + memory design checklist

Many useful AI systems are not smarter because the model is smarter. They are smarter because the system can retrieve, search, remember, and ground itself in the right knowledge at the right time.

...Navigation Before we start — why knowledge feels smarter than it is Why model knowledge is not enough Search, retrieval, memory, and grounding When to use RAG Internal knowledge design Chunking, freshness,...

1 DaySystems Thinking
Knowledge DesignPractical
Architecture Patterns That Travel Across Industries
Architecture Patterns That Travel Across Industries

The patterns that solve your hardest distributed systems problems were already solved — in a submarine, a postal sorting office, and an electrical panel. Most architects never look.

...Pattern Transfer Model CDPT operates across three layers. Layer 1: Problem Shape Identification Before searching for a pattern, name the problem in domain-agnostic terms. Not "our microservices are cascading...

Monitoring Added After Deployment Is Not Observability. It Is Archaeology.
Monitoring Added After Deployment Is Not Observability. It Is Archaeology.

Observability is not a monitoring add-on. It is an architectural constraint. Systems built without observability baked in cannot be understood, cannot be governed, and cannot be improved. The OSAF model tells you exactly where your architecture is blind.

...occurs at 11pm. The on-call engineer opens five dashboards. They correlate log timestamps manually. They search for the trace ID in three different tools. Forty minutes later, they have a hypothesis. Ninety...

Quality Attributes / -ilities
SA, EA — Intermediate5-6 hoursQuality attribute reference card + -ility prioritisation matrix

The non-functional characteristics that determine whether a system is truly fit for purpose — scalability, reliability, availability, performance, security, maintainability, and more.

...system. They're often invisible when present and devastating when absent. The distinction: Examples: A search system that returns correct results in 10 seconds is functionally correct but not fit for purpose....

1 DayIntensive
SA · EARoles
Requirements, Constraints, Trade-offs & Compromise
All levels — SA, EA, TS5-6 hoursTrade-off framework + constraint register template + requirements classification guide

The art of making the best possible architectural decision given what is required, what is constrained, and what must be sacrificed.

...requirements define what the system must do: "The system must process orders." "Users must be able to search products." "Invoices must be generated monthly." Non-functional requirements define how well the...

1 DayIntensive
PracticeReal decisions
Solution Decomposition
Intermediate (SA, EA)4-6 hoursDecomposition canvas + domain/service/component hierarchy guide

How to break large, complex systems into smaller, independently manageable parts — so different teams can build, own, and change them without stepping on each other.

...data. By capability — split along what the system can do. Authentication, notification, reporting, search. These are shared capabilities that serve multiple domains. By data — split along data ownership....

1.5 DaysIntensive
FoundationSA · EA
AI Agents and Automation
Intermediate to Advanced6-8 hoursAgent use case map + architecture blueprint + governance framework

AI agents — what they are, how they work, the protocols shaping them (MCP, A2A), and the governance you need before you let one act on your behalf. The bridge between AI that talks and AI that does.

...Component What it does Example Observe Gathers information from tools, context, and memory Reads a file, searches the web, checks a database Orient Assesses current state and progress toward goal "I have 3...

2 DaysIntensive
Agent DesignWorkshop
Future of AI
Intermediate to Senior Leaders3-4 hoursAI horizon scan + strategic implications analysis + preparation roadmap

What's coming in AI — multimodal models, on-device AI, open-source momentum, protocols, regulation, and the shift to AI-native organisations. See around the corner without falling for hype.

...(ElevenLabs, OpenAI) Voice assistants, accessibility Video understanding Early production Content moderation, search Video generation Early (Sora, Runway) Content creation, simulation The architecture underneath:...

Half DayIntensive
Horizon ScanDeliverable
Data & AI Direction
Intermediate to Advanced (SA, EA, TS)5-6 hoursData and AI direction framework + AI readiness assessment + governance overlay

How data strategy and AI direction connect to architecture — covering data quality, governance, data architecture for AI, AI enablement, responsible AI, data products, data mesh, and building a data and AI roadmap.

...— ETL/ELT + feature engineering + embedding generation. Serving — APIs + real-time queries + vector search. Governance — catalogue + lineage + quality + access control. ML pipeline — training + serving...

1.5 DaysIntensive
CurrentSA · EA · TS
Technical Debt & Rationalisation
Intermediate to Advanced (SA, EA, TS)5-6 hoursTechnical debt taxonomy + rationalisation prioritisation framework + modernisation criteria

How to understand, measure, prioritise, and reduce technical debt — the accumulated cost of shortcuts, outdated decisions, and deferred maintenance.

...patches stop Fixed — deadline approaching High Platform team TD-003 Deliberate No caching on product search Product Service Low — acceptable for current load Low — manageable until 10x Medium Team lead...

1 DayIntensive
StrategicSA · EA · TS