Process
A practical how-to or methodology.
Why we don't do prompt tracking.
Instead of infinite prompt variations, this measurement framework tracks canonical core entities across AI models to score brand visibility over time.
AI Models Encode Brand Data but Fail to Recall a Third of It
Google Research found frontier AI models encode 95-98% of brand facts in parametric memory but fail to recall 26-34% of them. The bottleneck is retrieval, not storage.
Gemini picks whichever web page it reads first 92% of the time. Only pages rewritten to its measured preferences ever beat that.
Shown two web pages, Gemini picks the first one 92% of the time. Pages rewritten to 31 measured text preferences win 15% from the second slot. Ordinary pages: 0%.
Introducing eCommerce Optimization Engine
The eCommerce Optimization Engine uses Google's multimodal embedding model to align product text with images to improve search retrieval and SEO performance.
Content Optimization Engine Insights by DEJAN AI
We spent 2.71 Billion tokens teaching a machine to reverse-engineer how AI search ranks pages. What it found overturns the usual SEO playbook: structure and intent beat every credential you've been told to add, and the engine that proved it reached #1 in 1,554 of 2,246 runs.
Introducing LinkjeBERT a Dutch Language Model
LinkjeBERT is a Dutch language model trained on structured Markdown to predict where humans will place links in text using token-level confidence levels.
Google Uses Chrome to Supply Context to Gemini Chat
An analysis of Chrome's Page Content Agent, which builds a structured tree of page elements to provide Gemini with grounded context for reading and interaction.
Better Vector Clustering With Head Noun Extraction
An exploration of how standard embeddings can create a semantic soup by grouping search queries by adjectives rather than head nouns during clustering.
Advanced Prompting Techniques for AI SEO
Explore prompt engineering techniques for SEO, including zero-shot, few-shot, role, and chain-of-thought prompting to improve content and automate tasks.
To block or not to block? Bot is the question.
An overview of AI bots, distinguishing between training data scrapers used for LLM development and agentic bots designed for autonomous, goal-oriented tasks.
From Free-Text to Likert Distributions: A Practical Guide to SSR for Purchase Intent
Semantic Similarity Rating (SSR) maps LLM free-text responses to Likert distributions to improve purchase intent realism and match human response patterns.
Comprehensive Guide to Identifying AI Comment Bots
Identify AI-generated comments through statistical analysis of sentiment, formulaic linguistic patterns, repetitive vocabulary, and a lack of human imperfection.
Dynamic per-label thresholds for large-scale search query classification with Otsu’s method
Explore how to use Otsu's algorithm to solve the problem of inconsistent confidence thresholds in search-query intent classifiers using dynamic, per-label tuning.
Prompt Engineer’s Guide to Gemini Schemas
A technical guide to the Gemini API GenerateContentResponse schema, detailing the structure of candidates, usage metadata, safety ratings, and parsed data.
Training Gemma‑3‑1B Embedding Model with LoRA
Gemma-Embed is a bespoke 256-dim embedding model created by fine-tuning google/gemma-3-1b-pt with LoRA to enable high-fidelity query reformulation.
Training a Query Fan-Out Model
Google generates high-quality query reformulations by traversing the mathematical latent space between queries and documents to train the qsT5 model.
Query Fan-Out Prompt Implementation in Google’s Open-Source Agentic Framework
Google’s Gemini Fullstack LangGraph Quickstart uses Gemini 2.5 and LangGraph to build a citation-driven research agent with a React and FastAPI architecture.
Advanced Interpretability Techniques for Tracing LLM Activations
This page explores mechanistic interpretability techniques, including activation logging, causal tracing through activation patching, and attention head analysis.