Loading...
Loading...
Reference cards and deep-dive guides on RAG, agents, and AI engineering careers. Free to download, keep one open next to your IDE.
Curated by Param Harrison
Stop guessing. Start investigating. The four-phase forensic process for bugs that refuse to die.
Build a Claude Code-style agent: streaming loop, permission-governed tools, context management, sandboxing.
Routing agents, relevance checks, reflection loops. The patterns that turn a RAG prototype into a self-improving system.
The patterns, budgets, and bulkheads that keep an AI system running when the model, the vendor, or the load turns against you.
HyDE, multi-query fan-out, decomposition, step-back. The rewriting layer that rescues vague user queries.
Indexing, HNSW vs IVF, hybrid wiring, scaling cost, migration. The vector DB reference you pin.
Event loops, tool contracts, memory tiers, evals, deploy flags. The agent patterns that survive production load.
Clean, normalize, dedup, gate. The preprocessing layer that decides RAG quality before retrieval runs.
JSON schemas, validators, repair loops, grounding checks. Structured output that holds under load.
Extractive, abstractive, hierarchical, map-reduce. The summarization strategies that survive long context and tight budgets.
Unicode, tokenization, encoding, language, PII. The text cleaning rules that keep RAG retrieval honest.
Sandbox, timeout, allowlist, audit. The shell layer that lets a coding agent run commands without burning the host.
Streaming, tool events, state visualization, error recovery. The UX patterns that make coding agents usable.
Layout-preserving PDFs, AST-aware code, table extraction, multi-modal. The parsing layer RAG needs for real docs.
The production RAG reference. Chunking, retrieval, reranking, evaluation, failure modes.
The reference for AI engineering interviews: scope by level, recurring questions, system design patterns, and portfolio shapes.
Prefer a walkthrough? Every cheatsheet ships with a recording.
Browse webinars