Articles
Can My AI Agent Order Me a Burger With Mr D?
An agent experience audit that goes further than most: I reverse-engineered Mr D Food's ordering API, built a real MCP server, and had an AI agent place and pay for a real order end to end.
Which South African ISP Do AI Agents Recommend? Telkom vs Afrihost vs MWEB vs Webafrica
An agent experience audit comparing Telkom, Afrihost, MWEB, and Webafrica in South Africa. Which one AI agents recommend, and why the AI's favorite pick doesn't always match the human reviews.
Which Payment Processor Do AI Agents Recommend? Bobpay vs Peach Payments vs Ozow vs PayU
An agent experience audit comparing Bobpay, Peach Payments, Ozow, and PayU in South Africa. Which ones AI agents mention unprompted, which ones they trust, and why two of the four are functionally invisible.
Which Payment Processor Do AI Agents Recommend? Yoco vs PayFast vs Paystack
An agent experience audit comparing Yoco, PayFast, and Paystack in South Africa. Which one AI agents mention unprompted, which one they recommend, and the sharp gap between the two.
Agent Experience Audit: Release.com
A live, four-test agent experience audit of Release.com: discovery, recommendation, comparison, and agent tooling, run against Claude Code in a clean context.
Pro Max Ultra Fable Sol: AI Model Names Have Escaped Containment
A field guide to the AI naming mess: model tiers, subscription plans, effort settings, and product names now share the same words.
LLMs for Technical Editing: The Good, the Bad, and the Ugly
LLMs: A technical editor's tool or replacement?
Can Claude Opus 4.8 Be Used by Technical Writers to Evaluate Their Own Work?
A technical editor tests whether Anthropic's Opus 4.8 can act as a reliable critic of technical writing — flagging weaknesses, gaps, and quality issues before an editor sees the work.
Useful LLM Prompts for Editing Your Own Technical Writing
A practical set of LLM prompts technical writers can use to self-edit their work — catching structural, logical, and line-level issues before an editor sees the draft.