Articles
Page 1 of 6Practical guides on automation, ecommerce optimisation, and data engineering by Fawad Hussain Syed.
Verification Is the Bottleneck Now
Generation got cheap and review did not. What the 2026 numbers on AI code quality actually measure, which of them you can check, and how to spend a fixed review budget on twice the code.
What to Actually Hand a Coding Agent
Coding agents are good at a narrower set of jobs than the marketing suggests and better at them than the scepticism suggests. Which tasks to delegate, how to write the brief, and why the handover matters more than the model.
Do You Still Need a Dashboard?
The case against dashboards is louder than it has ever been and thinner than it looks. What the evidence actually shows about chat, agents and semantic layers, and what a dashboard is still the only thing that does.
Can AI Build Your Dashboard Yet? What Works and What Breaks
AI can generate a dashboard from a prompt in seconds. Whether it generates a correct one is a different question, and the benchmarks answer it. What the evidence says about generated layouts, narratives, forecasts and chart choice.
Vision AI for Ecommerce: Tagging, Search, and QC That Actually Ship
Six vision AI workflows for online stores, from catalogue tagging and alt text to visual search, image compliance, and photo-verified returns, with the schemas, costs per 10,000 SKUs, and the checks that keep them honest.
Run Open LLMs Locally on Your Mac: What Works, Which Models, and What For
A practical guide to running open-weight models on Apple Silicon in 2026: the runtimes worth installing, which models fit 16, 32, and 64 GB, what you can genuinely do with them, and the pitfalls that waste a weekend.
Open-Source AI Agent Workflows: 8 GitHub Repos You Can Run This Week
Eight maintained open-source repos that implement complete AI agent workflows, from invoice processing and support triage to voice, coding, and browser agents, with what each one teaches and how to adapt it to your own stack.
AI Agent Examples: Real Workflows That Read, Decide, and Act
Practical AI agent examples from support, finance, engineering, ecommerce, and voice, each traced as a workflow: what the agent reads, which tools it calls, where a human signs off, and the open-source code you can start from. Every figure is linked and labelled by source.
Text-to-SQL Dashboards: Conversational Analytics Without a BI Team
Let non-technical people ask ecommerce data questions in plain English and get correct, governed answers. The trick is constraint — a semantic layer, read-only guardrails, SQL validation and result checks — not a bigger model.
AI Product Descriptions at Scale: A Shopify Bulk Generation Pipeline
A practical pipeline for generating on-brand, SEO-aware product descriptions in bulk for a Shopify catalogue using an LLM — grounded strictly on real product data, machine-checked claim by claim, gated by human review, and measured honestly.
n8n vs Make vs Custom Python: When to Stop Using No-Code Automation
A senior, honest comparison of n8n, Make, and custom Python for automation — where each genuinely wins, the real cost curves, and a clear framework for knowing when you have outgrown no-code and should graduate to code.
DuckDB for Ecommerce Analytics: Skip the Warehouse for Datasets Under 100GB
Most ecommerce stores never outgrow a laptop. DuckDB runs columnar analytics in-process over Parquet, CSV and Postgres with zero infrastructure — killing the cost and ops of a cloud warehouse for anything under roughly 100GB.