Data/ML/AIBackendEmergingAround since 2023
LangGraph
A framework (built by the LangChain team) for building AI agents as explicit graphs of steps and state, rather than a single linear chain — making it easier to model loops, branching decisions, and multi-agent handoffs reliably.
Think of it like
Like a flowchart with clearly labeled decision points and loops, instead of a single straight recipe card — built for workflows that branch, retry, or hand off between different 'roles.'
Junior or senior?
Junior sounds like
Followed a tutorial's exact graph structure.
Senior sounds like
Modeled the state and control flow themselves and can walk through where it branched or looped.
Ask them
“Walk me through a LangGraph graph you built — what were the nodes, and where did it branch or loop?”