Under the hood.
Panels push past the boxes on your diagram. Go one level down: each component's real run, internal states, code, technology choices and interview questions.
Mobile components · low-level design
5 pagesHow the parts inside an offline-first app actually work, with production code.
Front-end architecture for offline, real-time and AI apps
Front ends in data-heavy apps own far more than pixels: what the user sees, each screen's state machine, perceived speed, offline behaviour, real-time updates, streaming AI and accessibility. Stron…
Read the deep dive →The sync engine
Sync engines move local changes to the server and server changes into the local database. No UI, and no business logic beyond merging. The OS will start, stop and kill it at any line, so every line…
Read the deep dive →The transfer manager
Transfer managers move large files between phone and object storage. They hash, split and send parts that succeed or fail alone, record progress after each, and survive network switches, app kills …
Read the deep dive →The background-work layer
Background layers adapt your app to the OS scheduler. They turn many triggers (app open, network back, push, timers, user actions) into a few jobs, give each a time budget, and report results so th…
Read the deep dive →The server sync service
Server sync completes the protocol. It accepts pushes idempotently, applies merge rules, gives every change a sequence number in a per-tenant log, serves pulls by cursor with permission filtering, …
Read the deep dive →AI handbook
7 pagesInternals, acceleration, retrieval, customisation, agents, integration and team adoption.
How an LLM works inside
LLMs map a token sequence to a probability for every possible next token. Generation repeats that function, appending one token at a time. Latency, cost, hallucination and context limits all follow…
Read the deep dive →Making inference fast and cheap
Inference limits come in three kinds: GPU compute during prefill, memory bandwidth during decode, and memory capacity for weights and KV cache. Each acceleration technique relaxes one: smaller numb…
Read the deep dive →Embeddings and vector search
Embedding models turn text, images or audio into vectors, so similar meanings land close together. Approximate indexes find the nearest vectors quickly. Together they power semantic search, recomme…
Read the deep dive →Prompting, RAG or fine-tuning?
Three levers fit a general model to your product: better prompts, retrieval at query time, and new weights. Prompts and retrieval change what the model sees; fine-tuning changes how it behaves.
Read the deep dive →Tool use, agents and MCP
Tool use lets a model call your functions: it outputs a structured request, your code runs it, and the result returns to the conversation. Agents loop that pattern towards a goal. MCP standardises …
Read the deep dive →Integrating LLMs into products
LLM features behave like ordinary software with one unreliable, slow, expensive dependency. The patterns from payments or search apply: a gateway, contracts, retries, fallbacks, caching, budgets an…
Read the deep dive →Using AI to accelerate engineering teams
AI adoption questions test principal engineers: how AI changes the way teams build, and how you roll it out responsibly. Cover tools, workflow, guardrails, measurement and culture, not just which a…
Read the deep dive →