Skip to content
learning
Menu

Coding agents and agentic development

How coding agents work and how teams build with them, from vibe coding and written specs to MCP and saved session history.

Start here

What is a coding agent?

A coding agent is an AI system that edits files and runs commands in a loop to complete a programming task with little step-by-step direction.

10 min read

Concepts

  • What is vibe coding?

    Vibe coding is building software by describing the result to an AI and accepting the code it writes without reading it, judging it by how the app behaves.

  • What is spec-driven development?

    Spec-driven development is a way of working where a written specification, not a chat prompt, drives what a coding agent builds and how it is checked.

  • What is the Model Context Protocol (MCP)?

    The Model Context Protocol (MCP) is an open standard that lets AI applications connect to tools and data through a common client and server interface.

  • What is AI coding session history?

    AI coding session history is the set of saved coding agent transcripts, each holding the prompts, replies, tool calls, and results of one session.

  • What are acceptance criteria?

    Acceptance criteria are the conditions a change must meet to be accepted, written so that a person or a test can check each one as true or false.

  • What are agent skills?

    Agent skills are folders of instructions, scripts, and files that a coding agent loads when a task calls for them, so it can follow a set procedure.

  • What are background coding agents?

    A background coding agent works on a task without the developer watching, often in a cloud environment, and returns a branch or pull request at the end.

  • What are parallel coding agents?

    Parallel coding agents are several agents working on one codebase at once, usually in separate git worktrees or sandboxes so their edits do not collide.

  • What is a computer-use agent?

    A computer-use agent is an AI agent that operates software through its screen, reading screenshots and sending clicks and keystrokes instead of API calls.

  • What is a PRD, and does a coding agent need one?

    A product requirements document (PRD) describes what a feature should do and why, giving a coding agent the goals and limits a prompt leaves out.

  • What is agentic engineering?

    Agentic engineering is building software with coding agents while keeping engineering practices, from written specs and tests to review and verification.

  • What is AGENTS.md?

    AGENTS.md is a Markdown instruction file in a repository that tells coding agents how to set up, build, test, and change the project.

  • What is an agent harness?

    An agent harness is the software around a language model that gives it tools, context, memory, and a loop, which turns the model into a working agent.

  • What is context engineering?

    Context engineering is choosing what a model receives at each step, from instructions and files to tool results and history, so it has what the task needs.

  • What is harness engineering?

    Harness engineering is designing the tools, context, checks, and loop around a coding agent, so the agent's work can be run, checked, and corrected.

  • What is human-in-the-loop for coding agents?

    Human-in-the-loop means a person approves, corrects, or reviews an AI agent's work at set points, e.g. before code merges, while the agent does the rest.

  • What is plan mode in a coding agent?

    Plan mode is a coding agent setting in which the agent proposes a plan without editing files, so a person can review the approach before any code changes.

  • What is spec drift?

    Spec drift is the gap that opens when software changes but its specification does not, or the reverse, so the spec no longer describes what runs.

How-to guides

Comparisons

Terms in this topic

Acceptance criteria
Acceptance criteria are the conditions that a change must meet for the person who asked for it to accept it. They are written so that a person or a test can check each one.
Agent harness
An agent harness is the software around a language model that gives it tools, context, memory, and a loop, which turns the model into a working agent.
Agent loop
The agent loop is the cycle in which a model requests an action, the harness runs the tool, and the model reads the result. It ends when the model requests no tool, or when a step limit, a time limit, or a person stops it.
Agent skill
An agent skill is a packaged folder of instructions, scripts, and files that a coding agent loads when a task calls for it, so the agent can follow a set procedure.
Agent trajectory
An agent trajectory is the ordered sequence of an agent's actions, tool calls, and observations while it works on a task, which is what a transcript records.
Agentic engineering
Agentic engineering is a way of building software that directs coding agents while keeping engineering practices, from written specs and tests to code review and verification.
AGENTS.md
AGENTS.md is a Markdown file in a repository that gives coding agents project instructions, e.g. how to build, test, and change the code.
Background coding agent
A background coding agent is a coding agent that works on a task without a person watching and returns a branch or pull request when it finishes.
Coding agent
A coding agent is an AI system that edits files and runs commands in a loop to complete a programming task with little step-by-step direction.
Coding agent transcript
A coding agent transcript is a saved record that holds a coding session's prompts, replies, tool calls, and results. A collection of saved transcripts is called AI coding session history.
Computer-use agent
A computer-use agent is an AI agent that operates software through its graphical interface, reading screenshots and sending mouse clicks and keystrokes instead of calling an API.
Context window
A context window is the amount of text, measured in tokens, that a language model can take into account at once, including instructions, files, and history.
Git worktree
A Git worktree is an extra working directory attached to the same repository, so several branches can be checked out at once, e.g. one per parallel agent.
Harness engineering
Harness engineering is the practice of designing the tools, context, checks, and loop around a coding agent, so that the agent's work can be run, checked, and corrected.
Human-in-the-loop
Human-in-the-loop is a way of running an AI system in which a person approves, corrects, or reviews its work at set points before the work takes effect.
MCP server
An MCP server is a program that exposes tools or data to AI agents over the Model Context Protocol, so an agent can call them in a standard way.
Model Context Protocol (MCP)
The Model Context Protocol is an open standard that lets AI applications connect to tools and data through MCP servers, so an agent can call them in a uniform way.
Plan mode
Plan mode is a coding agent setting in which the agent reads the code and proposes a plan without editing files, so a person can review the approach before any change.
Product requirements document (PRD)
A product requirements document (PRD) is a written description of what a product or feature should do, for whom, and why, including its goals, scope, and limits.
Spec drift
Spec drift is the gap that opens when code and its specification change separately, so the written spec no longer describes what the software does.
Spec-driven development
Spec-driven development is a way of working that writes a specification of what software should do before a coding agent writes it. The spec is then used to guide and check the work.
Vibe coding
Vibe coding is a way of building software in which a person describes the result to an AI and accepts the code without reading it, judging it only by using the app.

22 terms from the Learning Center glossary.