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
Separate a fixed sequence from a model-selected next action before choosing a framework.
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.
- 05WorkflowsYou are here
- 06LangChainSee how a framework assembles the model, tools and application-controlled context.
- 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.
Control flow with model decisions
What is an agentic workflow?
A workflow is a defined arrangement of steps and decisions. An agentic workflow includes a model choosing some actions or paths, within application limits. A fixed workflow may use a model for one step without letting the model control the whole sequence.
An FDE must explain where the system can vary its behavior and where it must follow a rule.
UNDERSTAND THE SYSTEM
A workflow follows routes you define
A workflow is an arranged sequence of work with explicit conditions. It can include model calls, but predictable steps do not need an agent choosing every move.
Read the connections in plain English
- 01Support ticket → Classify
Provide only the information needed for classification.
- 02Classify → Routing rule
Validate the classification before using it.
- 03Routing rule → Specialist queue
A defined routing rule selects the appropriate queue.
- 04Routing rule → Human triage
A fallback protects cases the workflow cannot classify safely.
Check your understanding: Which part makes this different from an open-ended agent?
The developer has already specified the possible paths. A model performs a bounded step; it does not invent the sequence or gain access to arbitrary actions.
CONNECT IT TO WHAT YOU KNOW
Start with something familiar.
A build pipeline follows an authored sequence. An incident investigator chooses the next diagnostic step from observations. Your system can combine those patterns without making every step autonomous.
Choose dynamic model decisions only where they add value. Known sequences can remain ordinary code; LangGraph is one way to make stateful coordination explicit.
Words worth knowing
- Control flow
- The rules governing which step happens next.
- Branch
- A choice between possible next steps.
- Stop condition
- A rule that ends work even when the goal is unfinished.
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.
ONE EXAMPLE / FICTIONAL CASE
Follow the connections.
Always look up the machine and require human approval, but allow the assistant to choose which approved diagnostic document to inspect next.
UNDERSTAND THE SYSTEM
A workflow follows routes you define
A workflow is an arranged sequence of work with explicit conditions. It can include model calls, but predictable steps do not need an agent choosing every move.
See what moves and why.
Read the connections in plain English
- 01Support ticket → Classify
Provide only the information needed for classification.
- 02Classify → Routing rule
Validate the classification before using it.
- 03Routing rule → Specialist queue
A defined routing rule selects the appropriate queue.
- 04Routing rule → Human triage
A fallback protects cases the workflow cannot classify safely.
Check your understanding: Which part makes this different from an open-ended agent?
The developer has already specified the possible paths. A model performs a bounded step; it does not invent the sequence or gain access to arbitrary actions.
Work through it, step by step.
Fix the boundaries
Name mandatory steps, forbidden operations and the stopping condition.
What you have now: An authored workflow envelope
Allow a bounded choice
The model proposes the next permitted diagnostic action based on observed results.
What you have now: A controlled decision point
Rejoin the process
Validate the result and move to human review or a clear stop state.
What you have now: An inspectable outcome
FROM RECOGNITION TO REASONING
Redraw one familiar pipeline with just one model decision.
- 01
Mark fixed steps in one style and model choices in another.
- 02
Set a maximum number of diagnostic calls.
- 03
Include an insufficient-evidence route that does not dispatch anything.
A flowchart with one explicit source of dynamic behavior.
Compare your reasoning when you are ready
A bounded model choice can improve investigation while validation, permission and human approval stay deterministic. More agents are not automatically a better workflow.
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.
Choose dynamic model decisions only where they add value. Known sequences can remain ordinary code; LangGraph is one way to make stateful coordination explicit.
Academy lessons use your existing training access. Free guides stay open.