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
Understand agents
See how a framework assembles the model, tools and application-controlled context.
See the 8-concept route
For engineers who know software but are new to AI applications. Open the related definitions whenever a term is unfamiliar.
- 01The modelStart with what produces the text. Separate the model from the application using it.
- 02TokensSee the units a model reads and produces before reasoning about its input limits.
- 03ContextDecide what information reaches the model for this particular request.
- 04The agent loopPut the model inside an application that can execute permitted actions and check the result.
- 05WorkflowsSeparate a fixed sequence from a model-selected next action before choosing a framework.
- 06LangChainYou are here
- 07LangGraphMake the steps and shared state explicit when work needs to branch, wait or resume.
- 08MCPConnect capabilities through a shared protocol while keeping permission checks in the application and server.
Bookmark this page to return to this concept. The number shows your place in the reading route; it is not an assessment result.
An open-source software framework
What is LangChain?
LangChain is a software framework with building blocks for applications that use language models. You use it from languages such as Python or JavaScript to connect a model, give it tools and run an agent loop. LangChain is not a model, a programming language or a replacement for your application's security rules.
It can save you from writing every model integration and tool-calling loop yourself. You still need to understand the task, validate tool inputs and test the behavior you deliver.
UNDERSTAND THE SYSTEM
LangChain assembles models, tools and an agent loop
LangChain is an application framework. Its model integrations, tool interfaces and agent abstractions help you assemble an AI application without writing every integration from scratch.
Read the connections in plain English
- 01Your application → LangChain agent
The application supplies a task and trusted execution context.
- 02LangChain agent → Model integration
The agent passes messages and allowed tool definitions to the model.
- 03Model integration → Your lookup tool
Framework orchestration dispatches a proposed call; the tool still enforces access.
- 04Your lookup tool → LangChain agent
The result returns to the agent loop for the next model call or stopping decision.
- 05LangChain agent → Application result
The application receives the final output and handles it according to its contract.
Check your understanding: Does choosing LangChain also choose your model?
No. The framework integrates with model providers. You still select a supported model, credentials, data policy and cost limits; the framework is not the model itself.
CONNECT IT TO WHAT YOU KNOW
Start with something familiar.
If you have used a web framework to assemble routing, handlers and middleware, the role is familiar: LangChain provides building blocks and abstractions for assembling model-and-tool applications.
LangChain is a software framework. It does not supply the business authority of a tool or guarantee that an agent's answer is correct.
Words worth knowing
- Framework
- Reusable software that supplies structure and common building blocks for your application.
- Integration
- Code that connects your application to another model, tool or service.
- create_agent
- LangChain's entry point for configuring and running an agent loop.
Useful foundations
Open a definition and diagram here. Your lesson stays in place.
An application built around an AI modelWhat is an AI agent?
QUICK REFERENCE / 101
What is an AI agent?
An AI agent is software that uses an AI model to choose some of the steps needed to complete a task. It can call tools, inspect their results and decide what to do next within limits set by the application. The model is one component; the agent also needs code, tools and rules about when to stop.
An FDE needs to decide when model-driven choices help a real task and when a predictable sequence is enough. An agent is useful only if it improves the work and stays within its allowed scope.
A software development kitWhat is an SDK?
QUICK REFERENCE / 101
What is an SDK?
An SDK is a collection of code and supporting tools that helps you use a platform from a programming language. A model-provider SDK can turn a Python method call into an authenticated HTTP request and parse its response. The SDK is not the model or the remote service.
FDEs integrate models, gateways and business systems. Knowing the underlying contract lets you diagnose failures when an SDK hides details.
ONE EXAMPLE / FICTIONAL CASE
Follow the connections.
Think about the maintenance assistant. LangChain helps connect the model to a lookup function. Your own application still decides which procedures the signed-in person can read and whether any action may run.
UNDERSTAND THE SYSTEM
LangChain assembles models, tools and an agent loop
LangChain is an application framework. Its model integrations, tool interfaces and agent abstractions help you assemble an AI application without writing every integration from scratch.
See what moves and why.
Read the connections in plain English
- 01Your application → LangChain agent
The application supplies a task and trusted execution context.
- 02LangChain agent → Model integration
The agent passes messages and allowed tool definitions to the model.
- 03Model integration → Your lookup tool
Framework orchestration dispatches a proposed call; the tool still enforces access.
- 04Your lookup tool → LangChain agent
The result returns to the agent loop for the next model call or stopping decision.
- 05LangChain agent → Application result
The application receives the final output and handles it according to its contract.
Check your understanding: Does choosing LangChain also choose your model?
No. The framework integrates with model providers. You still select a supported model, credentials, data policy and cost limits; the framework is not the model itself.
Work through it, step by step.
Connect a model
Choose a model integration. The model will interpret the request and propose a response or tool call.
What you have now: A model that accepts your application's messages
Provide a tool
Describe a procedure-lookup function and its inputs. Check permissions in the function's application boundary.
What you have now: A lookup the model can request, not unrestricted database access
Run and inspect
Let the agent loop use the returned information. Inspect which tool it requested and whether the final draft is supported.
What you have now: A draft plus a record of how it was produced
FROM RECOGNITION TO REASONING
Draw the smallest useful one-tool agent.
- 01
Name the model, one read-only tool and the task.
- 02
Put identity and data scope outside model-supplied arguments.
- 03
Add a maximum number of tool calls and an insufficient-evidence result.
A four-part diagram: model, tool, trusted context and stop rule.
Compare your reasoning when you are ready
The framework coordinates calls, while trusted application context limits which data the tool may read. The loop must stop even when the model keeps requesting more work.
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 LangChain for model, tool and agent-loop building blocks. Your application remains responsible for access, limits and useful results.
Academy lessons use your existing training access. Free guides stay open.