Beau Lebens talked about agentic commerce at Stripe Sessions, where AI agents do the shopping. My take on the hard parts: live inventory data, checkout security for bots, and what MCP and the Abilities API actually change.
The data science job has moved. Production AI in 2026 is mostly orchestration: async APIs, vector databases and cost per request. Here is what changes when you start working as an AI architect instead.
LLM summarization pipelines invent facts when the schema demands a value the transcript cannot support. A three-stage design, extraction then synthesis then an audit stage that can only weaken claims, and why empty sections are correct.
Why scenario modelling is mostly about calibrated uncertainty rather than clean predictions, using an English local elections case study and a small PHP class for bootstrapping residuals.
A 2021 vector quantization algorithm called EDEN still outperforms its 2026 successor TurboQuant, and the reason comes down to how each one handles the scale parameter S.
The CSPNet architecture splits feature maps so a lighter CNN does not cost you accuracy. What it fixes in DenseNet, how the two paths work, and the PyTorch code for the bottleneck block.
Where the WordPress Core AI work stands before 7.0: the MCP adapter moving to a standalone plugin, the connector approval experiment, and a release plan that puts polish ahead of new features.
RAG re-derives everything on every query, so nothing accumulates. This is the Raw and Wiki folder layout, the three control files, and the daily, weekly and monthly jobs I use to keep an AI context layer my agents can read.
WordPress 7.0 (Armstrong) is past the foundational AI work and into ecosystem plumbing. The connector approval experiment blocks plugins from your API keys until an admin says otherwise, and RC1 lands May 14, so provider plugins need updating now.
Dynamic typing is fine in a notebook and expensive in a long-running pipeline. Notes on using type annotations, TypedDict, Literal and union types so a bad value fails at check time instead of four hours into a run.