Reference › Suggested Repository Layout
GitHub Login Glossary

Suggested Repository Layout

Annotated directory tree showing the anchor project's structure as it emerges across Modules 2-6. Each directory maps to a module's teaching content; each file is introduced in a specific lesson.

This layout isn't prescribed upfront -- it's what you'll have built by the time you finish the curriculum. Use it as a reference when you need to find where something lives or where new code should go.

Full directory tree

anchor-repo/
│
├── benchmark-questions.jsonl              # Module 2: 30+ questions with gold answers
│                                          #   Fields: id, question, category, gold_answer
│                                          #   Extended with: expected_files, expected_symbols,
│                                          #   expected_tools, expected_route (Modules 4-6)
│
├── harness/                               # Module 2 + Module 6: experiment framework
│   ├── schema.py                          #   Run-log schema definition (SCHEMA_DESCRIPTION)
│   ├── run_baseline.py                    #   Module 2: manual baseline runner
│   ├── run_harness.py                     #   Module 6: unified harness runner
│   ├── grade_baseline.py                  #   Module 2: interactive hand-grading tool
│   ├── summarize_run.py                   #   Module 2: run summary and metrics
│   ├── compare_runs.py                    #   Module 2: compare two graded runs
│   ├── ci_eval.py                         #   Module 6: CI-friendly eval runner
│   ├── graders/                           #   Module 6: automated grading
│   │   ├── answer_grader.py              #     LLM-as-judge answer evaluation
│   │   ├── retrieval_grader.py           #     Rule-based retrieval evaluation
│   │   ├── tool_grader.py               #     Tool-use evaluation
│   │   ├── trace_labeler.py             #     Trace-level labeling taxonomy
│   │   └── ragas_metrics.py             #     RAGAS-style retrieval metrics
│   └── runs/                              #   Saved JSONL run logs
│       ├── baseline-*.jsonl              #     Module 2: first baseline
│       ├── traced-*.jsonl                #     Module 6: traced runs
│       └── harness-*-graded.jsonl        #     Auto-graded runs
│
├── agent/                                 # Module 3: tool-calling agent
│   ├── tools.py                           #   Tool definitions (read_file, search_code, etc.)
│   ├── schemas.py                         #   JSON schemas for tool arguments
│   ├── loop.py                            #   Raw tool-calling loop
│   ├── run_benchmark.py                   #   Agent benchmark runner
│   ├── mcp_server.py                      #   MCP server (stdio transport)
│   ├── mcp_server_http.py                 #   MCP server (Streamable HTTP transport)
│   ├── tools_langchain.py                 #   LangChain tool wrappers
│   └── graph_agent.py                     #   LangGraph agent implementation
│
├── retrieval/                             # Module 4: code retrieval pipeline
│   ├── chunk_files.py                     #   Tier 1: naive file chunking
│   ├── embed_and_store.py                 #   Tier 1: embedding and Qdrant storage
│   ├── naive_retrieve.py                  #   Tier 1: basic vector retrieval
│   ├── parse_ast.py                       #   Tier 2: AST parsing for Python files
│   ├── chunk_ast.py                       #   Tier 2: AST-aware chunking
│   ├── embed_ast_chunks.py                #   Tier 2: embed AST chunks
│   ├── build_metadata_index.py            #   Tier 3: file/symbol metadata index
│   ├── query_metadata.py                  #   Tier 3: metadata-aware queries
│   ├── compare_substrates.py              #   Tier 3: substrate comparison
│   ├── build_graph.py                     #   Tier 3: call-graph construction
│   ├── query_graph.py                     #   Tier 3: graph traversal queries
│   ├── hybrid_retrieve.py                 #   Tier 3: vector + lexical + graph fusion
│   ├── context_compiler.py                #   Tier 4: five-stage context compilation
│   ├── detect_context_rot.py              #   Tier 4: context quality checker
│   ├── run_naive_benchmark.py             #   Tier 1 benchmark runner
│   ├── compare_tiers.py                   #   Cross-tier comparison
│   └── run_compiled_benchmark.py          #   Tier 4 benchmark runner
│
├── rag/                                   # Module 5: RAG pipeline and grounding
│   ├── grounded_answer.py                 #   Grounded answer generation with citations
│   ├── evidence_bundle.py                 #   Evidence bundle schema
│   ├── pack_to_bundle.py                  #   Context pack → evidence bundle converter
│   ├── retrieval_service.py               #   Routed retrieval service
│   ├── rag_with_routing.py                #   Full RAG pipeline with routing
│   ├── test_routing.py                    #   Routing accuracy tests
│   └── benchmark_bundles.py               #   Raw vs. bundled benchmark comparison
│
├── observability/                         # Module 6: telemetry and cost tracking
│   ├── traced_pipeline.py                 #   Langfuse-instrumented RAG pipeline
│   ├── traced_benchmark.py                #   Traced benchmark runner
│   ├── cost_tracker.py                    #   Per-request cost estimation
│   ├── cache_metrics.py                   #   Prompt cache hit rate analysis
│   ├── model_router.py                    #   Model routing by task complexity
│   ├── token_budget.py                    #   Per-request token budget enforcement
│   ├── rate_limit_telemetry.py            #   Rate-limit event tracking
│   └── success_cost.py                    #   Cost per successful task metric
│
├── orchestration/                         # Module 7: multi-agent coordination
│   ├── router.py                          #   Question classifier and routing logic
│   ├── specialists.py                     #   Specialist implementations (code, docs, debug, general)
│   ├── graph.py                           #   LangGraph orchestration graph
│   ├── approval.py                        #   Human approval gate for side-effecting actions
│   └── benchmark_specialists.py           #   Specialist split vs single-agent comparison
│
├── memory/                                # Module 7: memory layers
│   ├── thread_memory.py                   #   Thread/session memory with summarization
│   ├── workflow_state.py                  #   Multi-step workflow state tracking
│   ├── long_term_memory.py                #   Mem0-backed long-term memory with write policies
│   └── memory_eval.py                     #   Memory usefulness evaluation
│
├── .env                                   # API keys (git-ignored)
├── .gitignore                             # Ignores .env, .venv/, runs/, etc.
├── requirements.txt                       # Python dependencies
└── .venv/                                 # Virtual environment (git-ignored)

Directory-to-module mapping

DirectoryModulePurpose
harness/2 (Benchmark) + 6 (Observability & Evals)Experiment framework: run benchmarks, grade results, compare runs
agent/3 (Agent & Tools)Tool definitions, the tool-calling loop, MCP servers, framework agents
retrieval/4 (Code Retrieval)Four retrieval tiers: naive, AST-aware, hybrid, compiled
rag/5 (RAG & Grounding)Evidence bundles, grounded answers, retrieval routing
observability/6 (Observability & Evals)Traces, cost tracking, caching, budgets, rate limiting

Key files by function

FunctionFiles
Running experimentsharness/run_harness.py, harness/ci_eval.py
Grading answersharness/graders/answer_grader.py, harness/graders/retrieval_grader.py
Retrievalretrieval/hybrid_retrieve.py, retrieval/context_compiler.py
Answer generationrag/grounded_answer.py, rag/rag_with_routing.py
Telemetryobservability/traced_pipeline.py, observability/cost_tracker.py
Schema definitionsharness/schema.py, rag/evidence_bundle.py, retrieval/context_compiler.py

How the project grows

The directory structure isn't created all at once. Here's the build-up order:

  1. Module 2: benchmark-questions.jsonl and harness/ with the baseline runner and grading tools
  2. Module 3: agent/ with tool definitions and the tool-calling loop
  3. Module 4: retrieval/ with four tiers of progressively better retrieval
  4. Module 5: rag/ with evidence bundles, grounded answers, and retrieval routing
  5. Module 6: observability/ with traces and cost tracking; harness/graders/ with automated evaluation
  6. Module 7: orchestration/ with specialists and routing; memory/ with thread, workflow, and long-term layers

Each module's code builds on the previous modules. The retrieval/ directory feeds into rag/, which feeds into observability/traced_pipeline.py, which feeds into harness/run_harness.py. By Module 7, the full pipeline includes orchestration and memory.

Module 1 project

Module 1 (Foundations) uses a separate project directory:

ai-eng-foundations/
├── main.py                # FastAPI application
├── requirements.txt       # Dependencies
└── .env                   # API keys

This foundation project is a learning scaffold. Starting in Module 2, you'll switch to the anchor repository shown above. The Code Continuity Contract in AGENTS.md explains the relationship between the two projects.

Your Notes
GitHub Sync

Sync your lesson notes to a private GitHub Gist. If you have not entered a token yet, the sync button will open the GitHub token modal.
Glossary
API (Application Programming Interface)Foundational terms
A structured way for programs to communicate. In this context, usually an HTTP endpoint you call to interact with an LLM.
AST (Abstract Syntax Tree)Foundational terms
A tree representation of source code structure. Used by parsers like Tree-sitter to understand code as a hierarchy of functions, classes, and statements. You'll encounter this more deeply in the Code Retrieval module, but the concept appears briefly in retrieval fundamentals.
BM25 (Best Match 25)Foundational terms
A classical ranking function for keyword search. Scores documents by term frequency and inverse document frequency. Often competitive with or complementary to vector search.
ChunkingFoundational terms
Splitting a document into smaller pieces for indexing and retrieval. Chunk boundaries significantly affect retrieval quality. Split at the wrong place and your retrieval will return half a function or the end of one paragraph glued to the start of another.
Context engineeringFoundational terms
The discipline of selecting, packaging, and budgeting the information a model sees at inference time. Prompts, retrieved evidence, tool results, memory, and state are all parts of context. Context engineering is arguably the core skill of AI engineering. Bigger context windows are not a substitute for better context selection.
Context rotFoundational terms
Degradation of output quality caused by stale, noisy, or accumulated context. Symptoms include stale memory facts, conflicting retrieved evidence, bloated prompt history, and accumulated instructions that contradict each other. A form of technical debt in AI systems.
Context windowFoundational terms
The maximum number of tokens an LLM can process in a single request (input + output combined).
EmbeddingFoundational terms
A fixed-length numeric vector representing a piece of text. Used for similarity search: texts with similar meanings have nearby embeddings.
EndpointFoundational terms
A specific URL path that accepts requests and returns responses (e.g., POST /v1/chat/completions).
GGUFFoundational terms
A file format for quantized models used by llama.cpp and Ollama. When you see a model name like qwen2.5:7b-q4_K_M, the suffix indicates the quantization scheme. GGUF supports mixed quantization (different precision for different layers) and is the most common format for local inference.
HallucinationFoundational terms
When a model generates content that sounds confident but isn't supported by the evidence it was given, or fabricates details that don't exist. Not the same as "any wrong answer"; a model that misinterprets ambiguous instructions gave a bad answer but didn't hallucinate. Common causes: weak prompt, missing context, context rot, model limitation, or retrieval failure.
InferenceFoundational terms
Running a trained model to generate output from input. What happens when you call an API. Most AI engineering work is inference-time work: building systems around models, not training them. Use "inference," not "inferencing."
JSON (JavaScript Object Notation)Foundational terms
A lightweight text format for structured data. The lingua franca of API communication.
Lexical searchFoundational terms
Finding items by matching keywords or terms. Includes BM25, TF-IDF (Term Frequency–Inverse Document Frequency), and simple keyword matching. Returns exact term matches, not semantic similarity.
LLM (Large Language Model)Foundational terms
A neural network trained on large text corpora that generates text by predicting the next token. The core technology behind AI engineering; every tool, pattern, and pipeline in this curriculum runs on top of one.
MetadataFoundational terms
Structured information about a document or chunk (file path, language, author, date, symbol type). Used for filtering retrieval results.
Neural networkFoundational terms
A computing system loosely inspired by biological neurons, built from layers of mathematical functions that transform inputs into outputs. LLMs are a specific type of neural network (transformers) trained on text. You don't need to understand neural network internals to do AI engineering, but knowing the term helps when reading external resources.
Reasoning modelFoundational terms
A model optimized for complex multi-step planning, math, and logic (e.g., o3, o4-mini). Slower and more expensive but better on hard problems. Sometimes called "LRM" (large reasoning model), but "reasoning model" is the more consistent term across provider docs.
RerankingFoundational terms
A second-pass scoring step that re-orders retrieved results using a more expensive model. Improves precision after an initial broad retrieval.
SchemaFoundational terms
A formal description of the shape and types of a data structure. Used to validate inputs and outputs.
SLM (small language model)Foundational terms
A compact model (typically 1-7B parameters) that runs on consumer hardware with lower cost, latency, and better privacy (e.g., Phi, small Llama variants, Gemma). The right choice when privacy, offline operation, predictable cost, or low latency matter more than peak capability.
System promptFoundational terms
A special message that sets the model's behavior, role, and constraints for a conversation.
TemperatureFoundational terms
A parameter controlling output randomness. Lower values produce more deterministic output; higher values produce more varied output. Does not affect the model's intelligence.
TokenFoundational terms
The basic unit an LLM processes. Not a word. Tokens are sub-word fragments. "unhappiness" might be three tokens: "un", "happi", "ness". Token count determines cost and context window usage.
Top-kFoundational terms
The number of results returned from a retrieval query. "Top-5" means the five highest-scoring results.
Top-p (nucleus sampling)Foundational terms
An alternative to temperature for controlling output diversity. Selects from the smallest set of tokens whose cumulative probability exceeds p.
Vector searchFoundational terms
Finding items by proximity in embedding space (nearest neighbors). Returns "similar" results, not "exact match" results.
vLLM (virtual LLM)Foundational terms
An inference serving engine (not a model) that hosts open-weight models behind an OpenAI-compatible HTTP endpoint. Infrastructure layer, not model layer. Relevant when moving from hosted APIs to self-hosting.
WeightsFoundational terms
The learned parameters inside a model. Changed during training, fixed during inference.
Workhorse modelFoundational terms
A general-purpose LLM optimized for speed and broad capability (e.g., GPT-4o-mini, Claude Haiku, Gemini Flash). The default for most tasks. When someone says "LLM" without qualification, they usually mean this.
BaselineBenchmark and Harness terms
The first measured performance of your system on a benchmark. Everything else is compared against this. Without a baseline, you can't tell whether a change helped.
BenchmarkBenchmark and Harness terms
A fixed set of questions or tasks with known-good answers, used to measure system performance over time.
Run logBenchmark and Harness terms
A structured record (typically JSONL) of every system run: what input was given, what output was produced, what tools were called, how long it took, and what it cost. The raw data that evals, telemetry, and cost analysis are built from.
A2A (Agent-to-Agent protocol)Agent and Tool Building terms
An open protocol for peer-to-peer agent collaboration. Agents discover each other's capabilities and delegate or negotiate tasks as equals. Different from MCP (which connects agents to tools, not to other agents) and from handoffs (which transfer control within one system).
AgentAgent and Tool Building terms
A system where an LLM decides which tools to call, observes results, and iterates until a task is complete. Agent = model + tools + control loop.
Control loopAgent and Tool Building terms
The code that manages the agent's cycle: send prompt, check for tool calls, execute tools, append results, repeat or finish.
HandoffAgent and Tool Building terms
Passing control from one agent or specialist to another within an orchestrated system.
MCP (Model Context Protocol)Agent and Tool Building terms
An open protocol for exposing tools, resources, and prompts to AI applications in a standardized way. Connects agents to capabilities (tools and data), not to other agents.
Tool calling / function callingAgent and Tool Building terms
The model's ability to request execution of a specific function with structured arguments, rather than just generating text.
Context compilation / context packingCode Retrieval terms
The process of selecting and assembling the smallest useful set of evidence for a specific task. Not "dump everything retrieved into the prompt."
GroundingCode Retrieval terms
Tying model assertions to specific evidence. A grounded answer cites what it found; an ungrounded answer asserts without evidence.
Hybrid retrievalCode Retrieval terms
Combining multiple retrieval methods (e.g., vector search + keyword search + metadata filters) and merging or reranking the results.
Knowledge graphCode Retrieval terms
A data structure that stores entities and their relationships explicitly (e.g., "function A calls function B," "module X imports module Y"). Useful for traversal and dependency reasoning. One retrieval strategy among several, often overused when simpler metadata or adjacency tables would suffice.
RAG (Retrieval-Augmented Generation)Code Retrieval terms
A pattern where the model's response is grounded in retrieved external evidence rather than relying solely on its training data.
Symbol tableCode Retrieval terms
A mapping of code identifiers (functions, classes, variables) to their locations and metadata.
Tree-sitterCode Retrieval terms
An incremental parsing library that builds ASTs for source code. Used in this curriculum for code-aware chunking and symbol extraction.
Context packRAG and Grounded Answers terms
A structured bundle of evidence assembled for a specific task, with metadata about provenance, relevance, and token budget.
Evidence bundleRAG and Grounded Answers terms
A collection of retrieved items grouped for a specific sub-task, with enough metadata to evaluate whether the evidence is relevant and sufficient.
Retrieval routingRAG and Grounded Answers terms
Deciding which retrieval strategy or method to use for a given query. Different questions need different retrieval methods.
EvalObservability and Evals terms
A structured test that measures system quality. Not the same as training. Evals measure, they don't change the model.
Harness (AI harness / eval harness)Observability and Evals terms
The experiment and evaluation framework around your model or agent. It runs benchmark tasks, captures outputs, logs traces, grades results, and compares system versions. It turns ad hoc "try it and see" into repeatable, comparable experiments. Typically includes: input dataset, prompt and tool configuration, model/provider selection, execution loop, logging, grading, and artifact capture.
LLM-as-judgeObservability and Evals terms
Using a language model to evaluate or grade the output of another model or system. Useful for scaling evaluation beyond manual review, but requires rubric quality, judge consistency checks, and human spot-checking. Not a replacement for exact-match checks where they apply.
OpenTelemetry (OTel)Observability and Evals terms
An open standard for collecting and exporting telemetry data (traces, metrics, logs). Vendor-agnostic.
RAGASObservability and Evals terms
A specific eval framework for retrieval-augmented generation. Measures metrics like faithfulness, relevance, and context precision. One tool example, not a foundational concept. Learn the metrics first, then the tool.
SpanObservability and Evals terms
A single operation within a trace (e.g., one tool call, one retrieval query). Traces are made of spans.
TelemetryObservability and Evals terms
Structured data about system behavior: what happened, when, how long it took, what it cost. Includes traces, metrics, and events.
TraceObservability and Evals terms
A structured record of one complete run through the system, including all steps, tool calls, and decisions.
Long-term memoryOrchestration and Memory terms
Persistent facts that survive across conversations. Requires write policies to manage what gets stored, updated, or deleted.
OrchestrationOrchestration and Memory terms
Explicit control over how tasks are routed, delegated, and synthesized across multiple agents or specialists.
RouterOrchestration and Memory terms
A component that decides which specialist or workflow path to use for a given query.
SpecialistOrchestration and Memory terms
An agent or workflow tuned for a narrow task (e.g., "code search," "documentation lookup," "test generation"). Specialists are composed by an orchestrator.
Thread memoryOrchestration and Memory terms
Conversation state that persists within a single session or thread.
Workflow memoryOrchestration and Memory terms
Intermediate state that persists within a multi-step task but doesn't survive beyond the workflow's completion.
Catastrophic forgettingOptimization terms
When fine-tuning causes a model to lose capabilities it had before training. The model gets better at the fine-tuned task but worse at tasks it previously handled. PEFT methods like LoRA reduce this risk by freezing original weights.
DistillationOptimization terms
Training a smaller (student) model to reproduce the behavior of a larger (teacher) model on a specific task.
DPO (Direct Preference Optimization)Optimization terms
A method for preference-based model optimization that's simpler than RLHF, training the model directly on preference pairs without a separate reward model.
Fine-tuningOptimization terms
Updating a model's weights on task-specific data to change its behavior permanently. An umbrella term that includes SFT, instruction tuning, RLHF, DPO, and other techniques. See the fine-tuning landscape table in Lesson 8.3 for how these relate.
Full fine-tuningOptimization terms
Updating all of a model's parameters during training, as opposed to PEFT methods that update only a small subset. Requires significantly more GPU memory and compute. Produces the most thorough adaptation but carries higher risk of catastrophic forgetting.
Inference serverOptimization terms
Software (like vLLM or Ollama) that hosts a model and serves inference requests.
Instruction tuningOptimization terms
A specific application of SFT where the training data consists of instruction-response pairs. This is how base models become chat models: the technique is SFT, the data format is instructions. Not a separate technique from SFT.
LoRA (Low-Rank Adaptation)Optimization terms
A parameter-efficient fine-tuning method that trains small adapter matrices instead of updating all model weights. Dramatically reduces GPU memory and compute requirements.
Parameter countOptimization terms
The number of learned weights in a model, commonly expressed in billions (e.g., "7B" = 7 billion parameters). Determines memory requirements (roughly 2 bytes per parameter at FP16) and broadly correlates with capability, though training quality and architecture matter as much as size. See Model Selection and Serving for sizing guidance.
PEFT (Parameter-Efficient Fine-Tuning)Optimization terms
A family of methods (including LoRA) that fine-tune a small subset of parameters instead of the full model.
Preference optimizationOptimization terms
Training methods (RLHF, DPO) that use human or automated preference signals to improve model behavior. "This output is better than that output" rather than "this is the correct output."
QLoRA (Quantized LoRA)Optimization terms
LoRA applied to a quantized (compressed) base model. Further reduces memory requirements, enabling fine-tuning on consumer hardware.
QuantizationOptimization terms
Reducing the precision of model weights (e.g., FP16 → INT4) to shrink memory usage and increase inference speed at some quality cost. A 7B model at FP16 needs ~14 GB VRAM; quantized to 4-bit, it fits in ~4 GB. Common formats include GGUF (llama.cpp/Ollama), GPTQ and AWQ (vLLM/HuggingFace). See Model Selection and Serving for format details and tradeoffs.
OverfittingOptimization terms
When a model memorizes training examples instead of learning generalizable patterns. The model performs well on training data but poorly on new inputs. Detected by monitoring validation loss alongside training loss.
RLHF (Reinforcement Learning from Human Feedback)Optimization terms
A training method that uses human preference signals to improve model behavior through a reward model. More complex than DPO (requires training a separate reward model) but offers more control over the optimization objective.
SFT (Supervised Fine-Tuning)Optimization terms
Fine-tuning using input-output pairs where the desired output is known. The most common fine-tuning approach.
TRL (Transformer Reinforcement Learning)Optimization terms
A Hugging Face library for training language models with reinforcement learning, SFT, and other optimization methods.
Consumer chat appCross-cutting terms
The browser or desktop product meant for human conversation (ChatGPT, Claude, HuggingChat). Useful for experimentation, but not the same as API access.
Developer platformCross-cutting terms
The provider's API, billing, API-key, and developer-docs surface. This is what you need for this learning path.
Hosted APICross-cutting terms
The provider runs the model for you and you call it over HTTP.
Local inferenceCross-cutting terms
You run the model on your own machine.
ProviderCross-cutting terms
The company or service that hosts a model API you call from code.
Prompt cachingCross-cutting terms
Reusing computation from repeated prompt prefixes to reduce latency and cost on subsequent requests with the same prefix.
Rate limitingCross-cutting terms
Constraints on how many API requests you can make per unit of time. An operational concern that affects system design and cost.
Token budgetCross-cutting terms
The maximum number of tokens you allocate for a specific part of the context (e.g., "retrieval evidence gets at most 4K tokens"). A context engineering tool for preventing any single component from dominating the context window.