LOCKEDIN / FORWARD-DEPLOYED ENGINEERING 101
Understand it.
Then build it.
You can be an experienced engineer and still be new to agents. Start with what each thing is and how it helps a person do useful work. Explore 58 original introductions across software, agents, cloud, security and delivery. Start here without a model key; each topic connects to deeper instruction and practice.
A place to start.
Choose a short reading route, or look up a concept below.
- 101UnderstandPlain language, visual walkthrough, vocabulary
- 102Build with guidanceOriginal lessons, examples and knowledge checks
- 103Practise and explainRunnable labs, failure cases and handover
Connect the software
Bring commands, configuration and checks into a bounded coding-assistant task.
See the 9-concept route
For people who want the software vocabulary behind AI tools, or a refresher before their first local build.
- 01Terminal & CLIBegin with a person issuing a command to a program; the terminal is not itself an agent.
- 02ConfigurationUnderstand how that program receives its settings and why different processes can behave differently.
- 03JSON & schemasRead the messages programs exchange. Separate a field's name, type and meaning before following an API request.
- 04APIsMove from a person using a command to one program requesting something from another.
- 05RESTSee how resource addresses, HTTP methods and status codes organize a web API.
- 06SDKsFollow the library code that turns a convenient method call into an API request.
- 07TestsDecide what observable behavior to check before trusting a change made by a person or an agent.
- 08GitSeparate editable files, selected snapshots and recorded commits. Match the tested content to the change you hand over.
- 09Claude CodeYou are here
Bookmark this page to return to this concept. The number shows your place in the reading route; it is not an assessment result.
An agentic coding tool
What is Claude Code?
Claude Code is a coding tool from Anthropic that can read a project, help explain it, propose edits and run development commands when permitted. Its terminal interface lets you work with it from a command line. Claude is the model family; Claude Code is a tool built around models for software work.
An FDE often enters an unfamiliar codebase. A coding agent can help you navigate and implement a change, but you still need to understand the code, inspect the diff and prove the behavior with tests.
UNDERSTAND THE SYSTEM
A coding agent works through engineering tools
A coding agent uses a model to propose and execute development steps through permitted tools. Claude Code is one such development tool. Its changes still need inspection, tests and a bounded acceptance decision.
Read the connections in plain English
- 01Engineer + task → Coding agent
Define allowed changes and observable acceptance evidence.
- 02Coding agent → Editor + terminal
The tool execution layer enforces permissions and records outcomes.
- 03Editor + terminal → Working repository
Inspect the project and change a bounded part of it.
- 04Working repository → Coding agent
File content and test output inform the next step; output may contain untrusted text.
- 05Coding agent → Diff + test review
A completed agent response is not a substitute for reviewing the diff and relevant checks.
Check your understanding: Is this the same agent your customers will use?
Usually not. A coding agent helps build software. A customer-facing runtime agent has its own identity, tools, data boundaries and operating lifecycle.
CONNECT IT TO WHAT YOU KNOW
Start with something familiar.
A coding agent works alongside your editor and command-line tools. It can propose a sequence of engineering actions; you still inspect what changed and what the checks actually prove.
Claude Code helps develop an application. It is separate from a runtime agent that serves your customers. Keep their credentials, permissions and responsibilities separate.
Words worth knowing
- CLI
- Command-line interface: using text commands in a terminal.
- Repository
- The project's files and version history.
- Diff
- A view of what changed between two versions of the files.
- Test
- An executable check of the behavior the software should provide.
Useful foundations
Open a definition and diagram here. Your lesson stays in place.
Interfaces to programsWhat are a terminal, a shell and a CLI?
QUICK REFERENCE / 101
What are a terminal, a shell and a CLI?
A terminal is the window where you type and see text. A shell interprets your commands. A command-line interface (CLI) is how a program accepts those commands. An AI coding agent can use a terminal, but the terminal itself does not reason or decide what to do.
You need to understand what will run, in which folder, and with whose authority before approving a coding agent's action.
Version control and reviewable changesWhat is Git?
QUICK REFERENCE / 101
What is Git?
Git is a distributed version-control tool. It records selected snapshots of files so you can compare changes, recover earlier versions and collaborate. It runs on your computer; a hosting service such as GitHub can hold another copy of the repository. Git is separate from your editor, coding agent and deployment system.
When you or a coding agent change an application, an FDE must explain what changed and which version was checked. Saving a file, selecting it for a commit and recording that commit are distinct actions. Understanding them keeps unrelated work out of a handoff.
ONE EXAMPLE / FICTIONAL CASE
Follow the connections.
A ticket-triage project routes a request incorrectly. Ask the coding tool to explain the routing function, reproduce the failure and propose a small correction. Review the actual change before accepting it.
UNDERSTAND THE SYSTEM
A coding agent works through engineering tools
A coding agent uses a model to propose and execute development steps through permitted tools. Claude Code is one such development tool. Its changes still need inspection, tests and a bounded acceptance decision.
See what moves and why.
Read the connections in plain English
- 01Engineer + task → Coding agent
Define allowed changes and observable acceptance evidence.
- 02Coding agent → Editor + terminal
The tool execution layer enforces permissions and records outcomes.
- 03Editor + terminal → Working repository
Inspect the project and change a bounded part of it.
- 04Working repository → Coding agent
File content and test output inform the next step; output may contain untrusted text.
- 05Coding agent → Diff + test review
A completed agent response is not a substitute for reviewing the diff and relevant checks.
Check your understanding: Is this the same agent your customers will use?
Usually not. A coding agent helps build software. A customer-facing runtime agent has its own identity, tools, data boundaries and operating lifecycle.
Work through it, step by step.
Orient
Open the repository, read the project instructions and identify how to run its tests. A repository is the project's files and recorded version history.
What you have now: An explanation of the existing behavior
Make one change
Ask for a limited correction. Review the diff: the exact lines added or removed. Keep command and file permissions appropriate to the task.
What you have now: A change you can explain line by line
Verify and hand over
Run relevant tests, inspect failures and describe the remaining limits to another engineer. Generated code still needs engineering review.
What you have now: A reviewed change with reproducible checks
FROM RECOGNITION TO REASONING
Write a bounded request to a coding assistant.
- 01
Ask it to explain the existing behavior before editing.
- 02
Name one allowed change and one behavior that must remain unchanged.
- 03
Specify the test and diff evidence you will inspect.
A task request that another engineer can review.
Compare your reasoning when you are ready
A useful request has a stopping point and observable acceptance evidence. 'Improve everything' gives neither the agent nor the reviewer a clear boundary.
Keep notes in your own working copy. Moving through these cards does not record completion.
TURN THE IDEA INTO USEFUL WORK
You can now go deeper.
Use a coding agent to help with engineering work. Understanding, permission and verification remain part of your job.
Academy lessons use your existing training access. Free guides stay open.
Learn with the original creators
Use the introductory workflow lessons to see a coding assistant in context, then reproduce the method with our starter project.