Articles & Insights
Thoughts on web development, Python, design, and the craft of building software.
Featured
Building Python Flask Web Apps That Last
A personal reflection on building Flask applications that are maintainable, secure, and enjoyable to work with over time.
Read ArticleSeries & Guides
Multi-part deep dives
Recent Articles
Latest from the blog
AI and Job Risks in London
A fifth of London's jobs face significant AI exposure according to a Greater London Authority report by economist Jeff Dwan-O'Reilly. The numbers deserve more scrutiny than the headline — and the 54% ...
AI Security & Chips: OpenClaw's Flaw and a US First
Two of the most consequential AI infrastructure stories of April 2026: Resonac formally opened the first US center dedicated to advanced semiconductor packaging in Union City, CA — while open-source a...
Key Concepts & Glossary
Quick-reference guide to all major technologies and concepts on the CCA exam: Agent SDK, MCP, Claude Code, Claude API, Message Batches API, JSON Schema, and built-in tools.
Hands-On Preparation Exercises
Four hands-on labs mapping to CCA exam domains: build a multi-tool agent, configure Claude Code for a team, implement a structured extraction pipeline, and design a multi-agent research system.
Sample Questions & Distractor Analysis
12 worked exam questions with full distractor analysis. Each question covers a realistic production scenario with correct answer explanation and analysis of why each wrong answer fails.
Scenario: Structured Data Extraction
Build a reliable data extraction pipeline with JSON schema design, validation-retry loops, few-shot examples for varied document formats, and confidence-based human review routing.
Scenario: Claude Code for Continuous Integration
Integrating Claude Code into CI/CD pipelines using non-interactive mode, JSON output formatting, and the Batch API for cost-optimized asynchronous review.
Scenario: Developer Productivity with Claude
Applying Claude Code to developer workflows: iterative refinement, context management in large codebases, and team-scoped configuration patterns.
Scenario: Multi-Agent Research System
Design a coordinator-subagent research pipeline with parallel execution, structured output, error propagation, and provenance tracking across sources.
Scenario: Code Generation with Claude Code
Using Claude Code for code generation workflows: plan mode for complex refactors, CLAUDE.md hierarchies, and slash commands for team automation.
Scenario: Customer Support Resolution Agent
Build a customer support agent with get_customer, lookup_order, process_refund, and escalate_to_human tools. Covers prerequisite gates, escalation criteria, and structured handoff protocols.
Domain 5: Context Management & Reliability (15%)
Managing conversation context across long interactions, error propagation in multi-agent systems, human review workflows, and provenance tracking during synthesis.
Stay in the Loop
New articles on development, design, and building things that matter.