AI Engineering

Claude Code Best Practices: Reliable, Cheap, High-Leverage Sessions

Synthesise the whole Claude Code track into working habits: manage the context window deliberately, always give Claude a check it can run, plan before touching code, prompt with acceptance criteria, scope permissions narrowly, control cost, and know how to recover when a session goes wrong.

Claude Code Fundamentals

Learn what makes Claude Code an agentic tool rather than an autocomplete engine: the read-act-observe loop, the built-in tools it uses to explore and change your codebase, the permission modes that govern its autonomy, and where its configuration lives. By the end you'll be able to trace exactly what happens, tool call by tool call, when you ask it to fix a bug.

MCP Servers and Subagent Orchestration

Understand why the Model Context Protocol exists and how an MCP server extends what an agent can see and do, why that access model demands more careful trust and credential design than local file edits, and how subagents let you decompose a task across isolated context windows — sequentially for context hygiene, or in parallel for wall-clock speed — with git worktrees keeping concurrent writers from clobbering each other.

Plan Mode and Autonomous Workflows

Understand the concrete mechanisms Claude Code exposes for trading oversight against speed — plan mode's research-then-approve flow, including how to review, edit, and iterate on a plan before anything executes, plus self-pacing loops and goal conditions for unattended work. By the end you'll know when each mode earns its cost, how to steer a plan instead of just accepting or rejecting it, and where to go next when a task outgrows a single conversation entirely.

CLAUDE.md and Context Configuration

Understand why CLAUDE.md exists and how it composes with auto memory and settings.json, how to write instructions that survive a growing context window instead of bloating it, and how to back a probabilistic agent with deterministic guardrails using permissions and hooks.

Memory Systems for LLM Applications

A working taxonomy for one of the most conflated terms in AI engineering: the conversation window (short-term), persistent facts across sessions (long-term), what-happened-last-time (episodic), and externalized scratchpads (working memory). Covers durability criteria for what to persist, eager-load-vs-retrieval-triggered design, the failure modes — staleness, injection, bloat, conflicting facts — and a concrete walkthrough of how CLAUDE.md and context compaction implement exactly this taxonomy in a real product.

Git Workflows with Claude Code

Learn how Claude Code reads git state for context, generates commits and PRs with proper attribution, reviews diffs with /code-review, resolves conflicts and rebases, and isolates parallel work with git worktrees — plus the safe-habits checklist that keeps an agent with git access from doing something you can't undo.

Transformers for AI Engineers

Covers what an AI Engineer interview actually probes about transformer internals: scaled dot-product and multi-head attention, why decoder-only architectures won, why the KV cache exists and how its memory footprint is computed, what parameter count does and doesn't predict, and positional encoding — with worked numbers for KV cache memory and prefill-vs-decode cost.

MCP and Tool Integration Protocols

The concept and design-interview layer above MCP: why a standard client-server protocol replaced bespoke per-app tool integrations, the server/client/resource/tool abstractions at an architectural level, what MCP adds on top of plain function calling (and when bespoke calling is still the right answer), the trust boundary a third-party server introduces, and how to frame the 'build a server vs write a function' decision when an interviewer asks.

Multi-Agent Orchestration

A vendor-neutral treatment of multi-agent LLM systems: the supervisor/worker pattern, handoffs versus shared state, pipeline-vs-barrier synchronization for parallel fan-out, a worked cost-multiplication example, and the honest heuristic for when a single stronger model beats a fleet of coordinating agents. Cross-links `mcp-and-subagents` as the concrete Claude Code implementation and `plan-and-loop-modes` for the pipeline and adversarial-verification mechanics.

Case Study: Shipping a Fix with Claude Code, End to End

Follow one bug — CSV exports intermittently missing rows in a TypeScript/Node monorepo — from a ten-minute setup audit through exploration, a wrong hypothesis, a checkpoint recovery, implementation, a workflow that generalizes the fix, a PR with /code-review, CI, and a follow-up routine. Every decision is named, justified, and linked back to the track subject that owns it, so you can see the whole toolkit working together instead of one mechanism at a time.

LLM Observability and Evaluation

Interview-ready coverage of running LLM systems in production: what a full request trace must capture, token/cost/latency dashboards as product metrics, the precise line between offline evals and online monitoring, LLM-as-judge as a general technique with its biases and calibration, human review workflows, CI regression suites that treat prompts and models as code, canarying prompt and model changes, and a worked dashboard-diagnosis example.

Case Study: Design a Coding Agent

Model interview answer for designing a terminal coding agent that reads, edits, runs and verifies code in a repository: requirements and threat model, the agentic loop, a minimal tool set with output caps, a permission model that separates read from write from execute, context management for a finite window (truncation, compaction, subagents, cached prefixes), layered memory, cost and step budgets, prompt-injection defence, evaluation on task suites, and observability.

Agent Architectures and the Agentic Loop

A precise, vendor-neutral treatment of the agentic loop for AI engineering interviews: the observe-decide-act loop itself, the ReAct pattern and why explicit reasoning traces help tool selection, the plan-act-observe-reflect variant and when its extra LLM calls are worth it, single-agent vs multi-agent at a glance, termination and budget controls, failure modes with mitigations (loops, tool hallucination, runaway cost, context poisoning, analysis paralysis), a worked compounding-error-rate calculation, and a worked workflow-vs-agent decision.

Skills, Slash Commands & Plugins

Learn how Claude Code's built-in commands, custom skills (which have absorbed custom slash commands), and plugins let you turn a one-off prompt into a reusable, shareable capability — and how to decide which of the four extension mechanisms fits a given piece of team knowledge.

Case Study: Design a Customer-Support Assistant

Model interview answer for designing an LLM customer-support assistant: requirements and non-goals, workflow-vs-agent decision, tenant-safe RAG over a help centre, tool calls for account lookups and refunds with confirmation, conversation state, escalation and the 'I don't know' path, layered guardrails, offline and online evaluation, cost and latency numbers with levers, and a rollout plan.

Claude Code Workflows and Agent Teams

Go beyond one conversation delegating a few subagents at a time. Learn dynamic workflows — scripts Claude writes that a runtime executes in the background to coordinate dozens to hundreds of agents — how to start, watch, save, and resume one, and the cost and scale controls that keep a run bounded. Then learn agent teams, an experimental peer-coordination model with a shared task list and direct messaging between teammates, and when reaching for a lead-and-teammates structure beats both a single agent and a scripted workflow.

Prompt Engineering

A practitioner's tour of prompt engineering as an AI Engineer interview topic: what belongs in the system prompt vs the user prompt and why, when few-shot examples help and when they stop paying off, what chain-of-thought actually buys you mechanically, structured outputs and schema-constrained decoding, treating prompts like versioned code with regression tests, and the decision framework for when a longer prompt is the wrong answer and RAG or fine-tuning is the right one.

Context Engineering Fundamentals

The discipline that succeeds prompt engineering once a system has retrieval, tool calls, and conversation history: treating the entire context window — not just the prompt string — as an assembled, budgeted, ordered artifact. Covers the anatomy of a real app's context window, token-budget allocation across fixed and variable regions, selection and ordering strategies, compaction (summarization, truncation, structured notes), isolation between trust boundaries, the four named context failure modes with repro sketches, and a fully worked, real-numbers example of assembling one turn of a support bot's context.

Settings, Permissions & Hooks

Master Claude Code's settings hierarchy, the full permission-rule syntax and mode set, and the hooks system's lifecycle events, JSON contract, and exit-code semantics — the three mechanisms that turn an agent you supervise into one your whole team can trust unattended.