Blog
Notes from the build.
Serverless databases: how they work and when to use one
What makes a database serverless, the main families and current products, where they save money and where they cost more, with a table and a decision guide.What an AI agent really costs to build and run
A breakdown of AI agent costs: build phases, tokens per task, tools, human review and maintenance, with a worked example you can redo at current prices.Vision language models vs classic computer vision: what to use
How to choose between vision language models and trained detectors for reading, inspecting and counting, with a decision table, hybrids and a test plan.AI memory and privacy: what to store, what to forget
Memory makes an assistant a store of personal data. How to handle consent, minimisation, retention, erasure, isolation, poisoning and audit under GDPR.AI product photography and image editing for online shops
What AI image editing does reliably for a shop with hundreds of products, where it fails, and a batch workflow that keeps every picture true to the item.Agentic workflows vs RPA: what changes and what stays
An honest comparison of agentic workflows and RPA on determinism, exceptions, maintenance, audit and cost per run, with an invoice-exceptions walkthrough.Hybrid search and reranking: getting retrieval right
Why vector search misses exact terms and keyword search misses meaning, how to fuse the two, when to add a reranker, and how to measure the result.Edge AI: running models on the device, next to the sensor
What edge AI is, when to run a model on the device instead of the cloud, which hardware fits which workload, and how to update and monitor a deployed fleet.Cutting LLM costs: caching, routing, batching and small models
A ranked list of what reduces an LLM bill: measuring cost per feature, trimming context, prompt caching, model routing, batch APIs and smaller models.Optimise a serverless database: connections, cold starts, cost
Practical tuning for serverless databases: pooling and HTTP drivers, N+1 queries, indexes, replicas and caching, cold starts, spend caps and cost per request.