Field guides for working devs

Name the AI work you already do.

Short guides for developers who use AI every day but need clearer vocabulary for CVs, interviews, architecture talks, and choosing tools without drowning in jargon.

Start here

The first four pieces cover the ecosystem, the naming mess, and the career vocabulary gap.

Full pipeline

Brief3 min read

06 / Model selection

Picking a Model

A practical model selection guide covering task fit, latency, cost, context length, reliability, privacy, deployment, and evals.

Read
Brief3 min read

07 / Local AI

Running Models Locally

Understand local model runners, GPU and RAM constraints, privacy tradeoffs, quantized models, and when local beats hosted APIs.

Read
Brief3 min read

08 / Ecosystem

The AI Dev Toolkit Landscape

A practical map of AI developer tools: frameworks, observability, evals, model hubs, benchmark sites, and provider cookbooks.

Read
Brief4 min read

09 / Reliability

Evals for People Who Ship Code

Learn how developers can create practical LLM evals with test cases, expected behavior, graders, traces, and regression checks.

Read
Brief3 min read

10 / Reliability

Observability for LLM Apps

Understand LLM observability: traces, prompts, retrieved context, tool calls, latency, cost, errors, and user feedback.

Read
Brief3 min read

11 / Agents

Multi-Agent Orchestration

Understand multi-agent systems, orchestration patterns, routing, planner-worker loops, tool scopes, and the risks of adding agents too early.

Read
Brief4 min read

12 / Agents

MCPs: APIs But Make It Weird

Understand MCP servers, local stdio transport, remote HTTP transport, tool lists, configuration scope, FastMCP, and MCP tradeoffs.

Read
Brief4 min read

13 / Agents

How Does an LLM Call a Function When It Just Generates Text?

Learn how function calling and tool use work: schemas, model output, runtime dispatch, tool results, and agent loops.

Read
Brief3 min read

14 / Agents

Your Agent's Instruction Manual

Understand project instructions for coding agents, including AGENTS.md, CLAUDE.md, local overrides, global instructions, and scope.

Read
Brief4 min read

15 / Agents

Skills: Teaching Your Agent New Tricks

Understand AI agent skills: folder structure, SKILL.md instructions, references, helper scripts, installation scope, triggers, and security risks.

Read
Brief4 min read

16 / Ecosystem

Hugging Face: The GitHub of AI

Learn how to browse Hugging Face models, understand filters, read model cards, check licenses, inspect datasets, and use Spaces.

Read
Brief3 min read

17 / RAG

What Are Embeddings and Why Should I Care?

Understand embeddings as vector representations of meaning and how they power semantic search, RAG, similarity, clustering, and vector databases.

Read
Brief3 min read

18 / Core concepts

Transformers: The Architecture Behind Everything

Learn the practical meaning of transformer models, attention, context, and the difference between the architecture and the Hugging Face Transformers library.

Read
Brief3 min read

19 / Local AI

Quantization: Making Big Models Fit Small Computers

Understand quantization, GGUF files, Q4 and Q8 tradeoffs, memory savings, quality loss, and choosing local model formats.

Read
Brief3 min read

20 / Local AI

Running Local Models: The Software Guide

Compare local model software for developers across CLI, GUI, server, and production use cases.

Read
Brief3 min read

21 / Model selection

Open Weights vs Open Source

Learn the difference between open-weight models and open-source AI, including licenses, training code, datasets, and commercial use.

Read
Brief3 min read

22 / Developer tools

Gradio and Streamlit: Ship a Demo in 20 Minutes

Understand Gradio and Streamlit for quick AI demos, Hugging Face Spaces, internal tools, and prototype UIs.

Read
Brief3 min read

23 / Core concepts

Datasets: Where AI Models Learn

Understand AI datasets, data quality, Common Crawl, Hugging Face datasets, synthetic data, evaluation sets, and licensing.

Read
AILookup

Research utility for AI tools. Compare reviewed profiles, distinguish listed tools from reviewed coverage, and track tool changes without marketing fluff.

© 2026 AILookup. All rights reserved.