THE NEUROBROWSER FIELD GUIDE

A field guide. Thirty-six ways in.

Follow your question across browser practice, AI models, visual data, and neural research. Every topic leads to a complete guide and relevant Lab reading.

FIELD / 01

Browser & platforms

Start with the browser you already use. Explore source-first reading, extension permissions, and practical differences across desktop and mobile environments.

Neuro Browser

An introduction to source-first research across AI, neural computing, and the browser. Start with concepts, then follow a focused learning path.

Web browser

Plan a browser-based research workspace around tabs, provenance, readable exports, and user control rather than an assumed all-in-one product.

Chrome

A research guide to Chrome extension access, browser profiles, and deliberate sharing of page context. No official Chrome product or extension is offered here.

Safari

Explore Safari research workflows and extension questions without assuming that Chrome behavior transfers unchanged to Apple platforms.

Windows

Organize desktop research on Windows with attention to files, browser boundaries, and evidence portability. This is a planning guide, not a Windows application.

iOS

Consider mobile reading, source sharing, and lightweight review on iOS without confusing a responsive website with a native app.

Android

A mobile-first guide to reading AI research, handling source links, and evaluating resource demands on Android devices.

Browser plugin

An extension evaluation checklist: scope, permissions, data flow, updates, and uninstall behavior. There is no plugin download on this site.

FIELD / 02

AI & language models

Separate language models from agents, prompts from permissions, and local inference from remote services. Build a useful mental model before choosing a tool.

AI browser concepts

Understand where AI can support browsing: drafting summaries, organizing evidence, and suggesting follow-up questions—with a reviewer in control.

LLM fundamentals

Learn the role of large language models in a research workflow and separate text generation from retrieval, verification, and action.

AI agents

Explore agents as workflows with tools and action boundaries, not just conversational interfaces. Begin with read-only tasks and explicit review gates.

AI bots

Plan narrow, repeatable research helpers with observable inputs and outputs rather than loosely defined autonomous behavior.

AI prompts

Design prompts around a task, evidence, output structure, and an honest unknown state. Measure the result instead of collecting impressive wording.

Frontier model evaluation

Evaluate advanced model services with a task-specific scorecard, a data boundary, and a clear account of review effort.

Local AI models

Explore on-device and in-browser inference as deployment choices, with attention to memory, model fit, downloads, and the surrounding application.

LLM evaluation

A practical evaluation track for language-model reading assistants: traceability, unsupported answers, schema checks, and reviewer agreement.

FIELD / 03

Data & decisions

Good decisions begin with explicit labels, traceable datasets, and understandable contracts. These guides turn broad AI ideas into reviewable workflows.

Decision models

Turn a broad decision into explicit alternatives, assumptions, tradeoffs, and review responsibilities before involving an AI model.

Data science

Connect exploratory analysis with a documented question, meaningful labels, and a reproducible account of how the evidence was prepared.

AI API concepts

Learn how to describe an AI interface with clear request fields, output states, validation rules, and evidence references. No live API is offered here.

AI datasets

A guide to finding, evaluating, and documenting research datasets. This is not a live data catalog or a repository of participant records.

LLM data classification

Build an understandable label system for text and documents, with evidence excerpts, unresolved cases, and a human review queue.

FIELD / 04

Vision & imagery

Explore photos, video, image processing, and classification with attention to context, evaluation, and the original evidence behind every visual result.

Image classification

Understand the steps behind a visual label: dataset definition, preprocessing, evaluation, and inspection of mistakes.

Imagery

Learn to manage visual evidence with source information, captions, rights, and a clear distinction between a picture and its interpretation.

Photos

Prepare photographic material for responsible visual research with consistent labels, source context, and careful review of crops and metadata.

Video analysis

Treat video as a sequence with time and context, not simply a pile of independent image labels.

Image processing

Examine the preparation steps before classification: decoding, resizing, channel handling, and a traceable transformation history.

FIELD / 05

Brain & imaging

Read clear introductions to neuroimaging, brain scans, and cognitive-health information. Research literacy matters; an image or model output is not a diagnosis.

Brain research

Find a careful starting point for reading brain-related AI and computing research while keeping biological and computational claims distinct.

Neuroimaging

Explore neuroimaging terminology, metadata, and dataset organization without treating a web image as a clinical interpretation.

Alzheimer’s scan literacy

Understand why brain-imaging information belongs within a clinical assessment, not an isolated browser prediction or image label.

Cognitive-health information

Learn to read cognitive-health claims without turning browsing behavior, model output, or a single observation into a measure of a person’s ability.

Brain scan terminology

A reading guide to brain scan labels, report context, and the difference between structural images and other kinds of measurement.

FIELD / 06

Interfaces & discovery

Navigate brain–computer interfaces, wearable signals, neuromorphic ideas, and pharmaceutical imagery without confusing research concepts with available products.