Skip to content
AImpact
IT EN
← Reading paths
⌘

Reading path

Junior dev starting with AI

A chronological onboarding for devs who want to use AI professionally.

You are a developer with little AI exposure and you want to understand how it became a normal part of the job. This path walks you in chronological order from the first tools (Copilot, ChatGPT) to the 2025 agentic environments (Cursor, Claude Code), so you see why each step came after the previous one.

  1. 01

    Why it matters to you

    The moment 'ask an LLM' became a daily reflex: it explains why chat is now your second IDE.

    Landmark Foundation Models

    ChatGPT: AI lands in everyone's browser

    OpenAI launches ChatGPT, a free conversational interface on GPT-3.5 aligned via RLHF. It crosses one million users in five days.
  2. 02

    Why it matters to you

    The first real AI autocomplete inside the editor: it introduces the idea that you write code paired with a model.

    High AI Coding

    GitHub Copilot: autocomplete grows up

    GitHub and OpenAI launch a technical preview of an assistant that suggests entire lines and functions right in the editor, based on a GPT-3-derived model trained on public code.
  3. 03

    Why it matters to you

    Letting an LLM call functions is the key shift from using AI for chatting to using it to build products.

    High AI Infrastructure

    Function calling: GPT learns to speak JSON

    OpenAI adds 'function calling' to the API: the model returns structured JSON conforming to a schema, enabling reliable tool integrations without fragile prompt engineering.
  4. 04

    Why it matters to you

    The first model many junior devs actually use for serious refactoring and debugging: it raises the bar for what a coding assistant should do.

    High Foundation Models

    Claude 3.5 Sonnet: the mid-tier that beats everything

    Anthropic releases Claude 3.5 Sonnet: outperforms Claude 3 Opus (the previous flagship) at Sonnet pricing ($3/$15). Introduces 'Artifacts': side-panel output for code, documents, charts.
  5. 05

    Why it matters to you

    Shows what an IDE designed around AI feels like versus an editor with a glued-on plugin: it reshapes your daily workflow.

    High AI Coding

    Cursor Composer: agentic multi-file editing in the AI-native editor

    Anysphere ships Composer in Cursor 0.40: a multi-file mode where the editor simultaneously edits multiple files following a coordinated plan, a first step toward a fully IDE-integrated coding agent.
  6. 06

    Why it matters to you

    The standard that lets you plug your assistant into any company tool: learning it early makes you much more employable.

    High AI Infrastructure

    Model Context Protocol: the open standard to connect LLMs and data

    Anthropic open-sources the Model Context Protocol (MCP), a JSON-RPC standard that lets AI assistants talk to tools, file systems, databases, and SaaS without per-model ad-hoc integrations.
  7. 07

    Why it matters to you

    The agent that works on your repo from the terminal: a starting point to learn how to delegate whole tasks, not just lines of code.

    Landmark AI Coding

    Claude Code: the coding agent lands in the terminal

    Anthropic ships Claude Code alongside Claude 3.7 Sonnet: a CLI that reads the codebase, edits files, runs commands, runs tests, makes commits — the 'agent in terminal' pattern goes mainstream.