AI-Assisted Dev NotesRohit’s interview study guide
/

Interview study guide

AI tools, used with judgement.

GitHub Copilot and the Model Context Protocol, from what they are to building, testing and securing your own MCP server. Every MCP example runs against the official TypeScript SDK and prints what the page says.

Chapters
9
Topics
48
Code samples
223
Added beyond the doc
48
Start readingWhat AI coding assistants doChapter 01 · AI-Assisted Development Today
01AI-Assisted Development TodayWhat coding assistants actually do (completion, chat, agents; in the editor, the terminal and the cloud), how they work just enough to use them well (tokens, context windows, sampling, why they invent APIs), where the evidence says they help and hurt, and why the developer still owns every line.4 topics02GitHub CopilotWhat Copilot is in October 2026 (completions, Chat, plan and agent mode, the cloud agent, code review, CLI and the Copilot app), how instruction and prompt files steer it, how agents ask for approval and use MCP, what admins control, and how to talk about it in an interview without overclaiming.6 topics03Prompting for CodeHow to ask for code so the answer has a chance of being right: giving the model the context it can't see, writing the spec and the tests before the code, iterating with exact failures instead of adjectives, and catching invented APIs and subtle bugs with checks against the real packages.5 topics04MCP FundamentalsThe Model Context Protocol from zero: why it exists, who runs what, the JSON-RPC messages on the wire, tools, resources and prompts, the two transports, and what servers can ask of the client.8 topics05Building an MCP ServerFrom an empty folder to a working, tested MCP server with the official TypeScript SDK: one tool over stdio, tools a model can actually use, resources and prompts, tests that talk real MCP, the config files that connect it to VS Code, Claude Desktop and Claude Code, and long-running tools with progress, cancellation and logs.6 topics06Remote MCP Servers and SecurityRunning an MCP server as a web service: hosting Streamable HTTP with Express, sessions versus stateless servers, OAuth-based authorization, and the security problems that come with letting a model read untrusted text and call tools: prompt injection, tool poisoning, least privilege, confirmations and trusting other people's servers.5 topics07MCP for a Device PlatformPutting a fleet of meeting-room devices behind an MCP server: why you would, read tools and confirmed write tools over a device REST API, logs and docs as resources, the guardrails that hardware needs, and an end-to-end troubleshooting run against a simulated device.5 topics08AI in the TeamLeading a team that uses AI assistants: guidelines people can follow, reviewing AI-generated changes, security, licensing and data, measuring honestly whether it helps, and making shared AI setups work across a US–India team.5 topics09Review QuestionsRapid revision before an interview: questions about AI-assisted development, GitHub Copilot and MCP, with answers you can say out loud in a minute, each linked to the topic that teaches it in depth.4 topics

Added marks topics that weren’t in my original doc. Tick Learned on a topic to track what you’ve revised.

Sync progress across devices

Type the same private phrase on your Mac and your phone, and your Learned ticks follow you between them — on every study site.

The phrase never leaves this device: only a fingerprint of it is sent, and the server stores a fingerprint of that. Anyone who knows the phrase could see or change your ticks, so pick something you don’t use elsewhere.

Sync is on in this browser.

Sync ID

This ID must be the same on every device. If another device shows a different one, its phrase is different (capital letters count): tap “Turn off here” on it and type the phrase again exactly.