Agentic AI transparency without the black box or the log dump
Two bad defaults for agent UIs: hide everything behind a spinner, or stream every raw log. What I map instead, and how I decide which agent decisions a user actually needs to see.
Category: AI
Open source MMM: marketing mix modeling you can audit
Proprietary MMM platforms hand you a number and hide the math behind it. This is the stack I use instead: Google Meridian for the Bayesian side, a local Mistral 7B to turn coefficients into something a marketing manager can act on.
Behavioral biometrics analysis: why MFA alone stops working
A RAT sitting on the victim’s own phone gets a clean IP, a real device fingerprint, and a valid MFA code. What it cannot fake is how the owner scrolls, and that is the signal behavioral biometrics reads.
WordCamp Asia 2026: what the Mumbai schedule is telling us
The WordCamp Asia 2026 schedule is out: Mumbai, April 9 to 11, leaning hard on AI, enterprise scale, and the Interactivity API. My notes on which sessions are worth a slot in your day.
A speaker guide for WordPress Core AI projects needs review
The Core AI team has a draft guide for anyone presenting on Abilities, the AI Client or the MCP Adapter at a WordCamp or meetup. Comments on it close on 21 April 2026.
Embedding models: how AI search actually finds a match
Embedding models turn text into coordinates, and that is what vector search is really matching on. This covers tokenization, chunking, cosine similarity and fine-tuning a model so it fits your own catalog rather than the general web.
AI in WooCommerce workflows: the missing piece is context
AI tools guess at your store because they cannot see it. MCP gives them real context: your files, your data, your WP-CLI. We talk it through at WooCommerce office hours on April 15, 2026, on Slack.
The Google Memory Agent pattern replaced my vector DB
Pinecone and Chroma are a lot of machinery for a few hundred Markdown notes. The Google Memory Agent Pattern keeps structured memories in SQLite, consolidates them in the background, and loads them straight into a large context window.
The geometry behind the dot product: projections and unit vectors
Why dot product geometry matters if you build search relevance or recommendations. Unit vectors, scalar and vector projections, the shadow analogy, and a plain PHP cosine similarity function you can read.
Recursive reasoning: how a 7M model beat DeepSeek R1
A 7M-parameter Tiny Recursion Model beat DeepSeek R1 on the ARC-AGI benchmark by looping over the problem instead of scaling up. What that says about trading parameters for iterations.