Questions every software engineering student should be asking

  1. 01

    Could I explain and debug every line of this AI-generated pull request if production broke while the assistant was offline?

  2. 02

    Has faster code generation reduced technical debt on the team, or multiplied the volume of poorly understood code entering review?

  3. 03

    What security vulnerabilities, outdated patterns or licensing issues can slip in when developers accept suggestions on autopilot?

  4. 04

    When syntax becomes cheap, which fundamentals (systems design, data structures, testing, domain modelling) matter even more for juniors?

  5. 05

    How do you write tight specifications and automated tests first so the model works inside clear guardrails rather than guessing architecture?

Want a repeatable checklist for testing any vendor claim or headline in software engineering? Read our full guide on how to think critically about AI →

Articles on Software Engineering

Key terms for Software Engineering

  • A large language model (LLM) is an AI system trained on text to predict tokens in sequence, letting it draft, summarise, translate and write code.

  • An AI agent is software that uses a model to plan steps, call external tools, read results and pursue a set goal rather than replying once in chat.

  • Agentic AI describes workflows where models break goals into tasks, run tools, check intermediate outputs and adjust course with bounded autonomy.

  • A context window is the maximum amount of text, code or files an AI model can hold and process at one time across both your input and its response.

  • Fine-tuning continues training an existing AI model on a smaller, curated dataset so it follows specific formats, tone or domain conventions reliably.

  • A token is the basic chunk of text, code or data an AI model processes, often equal to a word, part of a word, a number or a punctuation character.

  • A neural network is a mathematical model made of connected layers of weighted nodes that adjust during training to map raw inputs to useful outputs.

  • A transformer is a neural network architecture using attention mechanisms to weigh relationships across sequences, powering modern language AI models.

  • AI alignment is the technical and design challenge of ensuring AI systems pursue human intentions safely without gaming metrics or causing side harm.

  • AI safety studies how to test, constrain and monitor AI systems so failure modes, misuse risks and unexpected behaviours do not cause serious damage.

  • Vibe coding is building software mainly by prompting AI coding tools in plain English and iterating on behaviour rather than writing every line manually.

  • Model Context Protocol (MCP) is an open standard connecting AI assistants safely to external databases, files and workplace tools without custom glue.

  • An open-weight model is an AI model whose trained numerical parameters are publicly downloadable, letting teams inspect, fine-tune and self-host it.

  • An AI copilot is an assistant embedded inside everyday software that drafts, summarises or suggests next steps while the human user stays in control.

Guides

Practical playbooks for software engineering students preparing for coursework, internships and graduate roles alongside AI.

Get future software engineering articles by email

Written by students, every two weeks. Grounded in primary sources and real workflows.