understandingdata.com valid

Understanding Data

James Phoenix on AI-native software engineering and context engineering: the vocabulary, the patterns, and the failure modes, written from building the systems rather than reading about them.

Their llms.txt

The beginning of the file, from our validated copy saved 2026-10-26T06:15:29.104Z. Cached copy · Source on understandingdata.com

# Understanding Data

> James Phoenix on AI-native software engineering and context engineering: the vocabulary, the patterns, and the failure modes, written from building the systems rather than reading about them.

This file indexes every reference entry and essay on https://understandingdata.com. Entries are human-written and human-reviewed, and each carries its type (pattern, antipattern, or concept) and, where it makes a claim, how well established that claim is (proven, validated, emerging, experimental, theory).

Append `.md` to any dictionary entry or film URL for a clean Markdown copy, e.g. https://understandingdata.com/ai-coding-dictionary/harness.md or https://understandingdata.com/ai-engineering-visualised/kv-cache.md

## Field guides

- [AI Native Software Engineering](https://understandingdata.com/ai-native-software-engineering/): The vocabulary and workflow of building software with AI coding agents, from tokens and context windows through harnesses, subagents, and review discipline.
- [Context Engineering](https://understandingdata.com/context-engineering/): A practical guide to deciding what a model sees: retrieval, agent patterns, reliability, evaluation, and the ways long-context systems break.

## AI Engineering Visualised (33 narrated films, 19 interactive labs)

Short films and labs on how language models work, each with a written explanation and the maths. A film's Markdown copy carries its full transcript by chapter; its captions are at <film URL>captions.vtt, e.g. https://understandingdata.com/ai-engineering-visualised/kv-cache/captions.vtt.

### Foundations and representations

- [Activation functions and normalisation](https://understandingdata.com/ai-engineering-visualised/activations/) (film, 1:27): An activation function is the non-linear step a network applies after each matrix multiply, so that stacked layers can represent more than one linear map. Normalisation and dropout sit beside it to keep the values well behaved.
- [Attention as geometry](https://understandingdata.com/ai-engineering-visualised/attention-geometry/) (interactive lab): Attention scores a query against every key with a dot product, then turns the scores into weights with a softmax. It is geometry: aligned vectors win weight, and longer vectors sharpen the distribution.
- [Attention head fingerprints](https://understandingdata.com/ai-engineering-visualised/attention-heads/) (interactive lab): An attention head is one independent copy of the attention mechanism inside a layer, with its own query, key and value projections. Different heads learn different jobs, from copying the previous token to matching earlier patterns.
- [Byte pair encoding](https://understandingdata.com/ai-engineering-visualised/tokenisation/) (interactive lab): Byte pair encoding is the tokenisation algorithm most language models use. It starts from single characters and repeatedly merges the most frequent adjacent pair, so common words become one token and rare words split in
…

Machine-readable: GET /v1/resolve?q=understandingdata.com · GET /v1/domain/understandingdata.com · this page as Accept: application/json or text/markdown · MCP lookup_domain

Automatically discovered from public files. Inclusion does not imply endorsement or publisher participation.

Claim my listing on Agent Web Map for understandingdata.com:
1. POST https://agentwebmap.com/v1/sites/understandingdata.com/claims and keep claim_id and claim_secret private.
2. Publish the verification line "AgentWebMap verification: <token>" (token from step 1) in https://understandingdata.com/llms.txt, or use the DNS, meta-tag or well-known method the response describes. This only verifies the listing; your website and domain remain yours.
3. POST https://agentwebmap.com/v1/sites/understandingdata.com/verify with {"claim_id": "...", "claim_secret": "..."}.
4. Save the api_key from the answer; it manages the listing (PATCH https://agentwebmap.com/v1/sites/understandingdata.com).
MCP equivalent: tools begin_ownership_claim, then verify_domain, at https://agentwebmap.com/mcp. Docs: https://agentwebmap.com/docs#verify

Corrections or removal requests: contact the directory.