CODExSIMS Systems, made visible

Models · inference · agents · evaluation

Understand the systems behind modern AI applications

From transformer internals to agent loops, retrieval, prompting and real-time inference. Follow a guided path from first principles to the behavior that matters in production.

Choose a path
Prompt and context pass through a tokenizer and model layers, augmented by retrieval and tool calls, producing a token stream that feeds an evaluation loop.
  1. 01 Model foundations0 of 5 complete Tokens · architecture · reasoning
  2. 02 Application systems0 of 9 complete Retrieval · agents · prompting
  3. 03 Production quality0 of 5 complete Inference · evaluation · safety

01 / Pick where to begin

Choose a learning path

19 guides across 3 paths

01 / Tokens · architecture · reasoning

Model foundations

0 of 5 runs complete

02 / Retrieval · agents · prompting

Application systems

0 of 9 runs complete
Recommended first guide

How does LangChain grow one model call into a real LLM app?

How one model call grows into prompts, memory, chains, evals and agents across the full LangChain course arc.

7 stages · ~5 min
Prompt Systems

How do OpenAI prompts become reliable production artifacts?

Why prompt order matters, how examples shape behavior, what structured outputs actually guarantee and the eval loop that hardens it all.

8 stages · ~6 min
LLM Application Lab

What turns one model call into a reliable LLM application?

A software engineering tour of context budgets, instruction authority, sampling, reasoning, streaming, schemas, tools, routing, retries and token cost.

9 stages · ~7 min
Agent Learning

How does a self-learning agent turn conversations into lasting capability?

How a fresh agent turns conversations into memory, skills and searchable episodes so the next session is smarter than the last.

8 stages · ~6 min
Agent Console

How does Claude Code route prompts, tools, hooks, and plugins?

How prompts, tools, hooks and plugins actually flow through Claude Code from the CLI entry point to the edges where MCP takes over.

8 stages · ~5 min
Infra Detective

How does Clanker Cloud turn one prompt into grounded cloud evidence?

How one prompt gets cleaned up, routed to the right backend, hydrated with credentials and fanned out into parallel evidence gathering.

8 stages · ~6 min
Gateway Garage

What is OpenClaw actually doing in local control mode?

What one local gateway actually does: normalizing channels, mapping sessions, running the agent loop and coordinating paired devices.

8 stages · ~6 min
Mission Loop

Why does an AI agent loop feel more structured than it looks?

Why an agent loop feels more structured than it looks: planning, tool calls, memory and guardrails working as one deliberate cycle.

7 stages · ~5 min
Code Lab

How do you wire Java, Claude and OpenSearch into a working agent?

A practical code walkthrough: Maven dependencies, system prompt, tool schemas, the agent for-loop, switch-case handler and a live end-to-end trace.

8 stages · ~7 min

03 / Inference · evaluation · safety

Production quality

0 of 5 runs complete
About this collection

An LLM application sits on top of several different systems. Tokens move through an architecture that produces probabilities, inference servers turn those probabilities into a streamed response and application code surrounds the model with context, tools, retries and evaluation. Treating all of that as one black box makes failures difficult to reason about. This collection separates the layers and shows how information moves across each boundary.

Begin with the large language model guide for the core path from tokenization to generation. From there you can inspect real-time streaming, retrieval-augmented generation, agent execution loops, prompt authority, model evaluation and the architecture choices behind specific frontier models. The visual guides distinguish confirmed mechanisms from uncertain or product-specific details. They are designed for engineers building AI features, reviewing an unfamiliar stack or trying to locate whether a problem belongs to the model, the runtime or the surrounding application.