Where this comes from
Primary sources
- Graph API overview · LangChain (accessed 09/20/2026)
Thread
Graph engineering
Two uses of graphs that are often confused: graphs that connect information, and graphs that connect work.
The organizing sentenceKnowledge graphs connect information; agent graphs connect work.
Same shapes, different connections
Three illustrative graphs. Read the labels on the arrows: they tell you what each connection means.
Level 2
Knowledge graph
Nodes are things. Edges state how they relate.
Level 3
Workflow graph
Nodes are steps. Code sets the transitions.
Level 6
Agent graph
Nodes are agents. A model chooses a handoff.
A focused engineering & technical work example. Additional perspectives appear where they provide a useful contrast.
GUIDED WORKED EXAMPLE Fictional fixtures · scripted outputs · no live model or external actions
Graph engineering: see it in practice.
Distinguishing graphs of information from graphs that control workflows or agent handoffs.
What you’ll walk through
Compare different meanings of a graph within one task: relationships in information, transitions in a workflow, and coordination between agents. Follow what each representation helps explain.
The task in this version
Explain a recall using information, workflow, and agent graphs.
What you’ll learn to check
Three small linked graphs with explicit node/edge meanings and the same case followed across them.
The setting makes the example concrete. Carry the underlying pattern into your own work; adapt the sources, tools, and level of oversight to your task.
Engineering & technical workAn authored case with its own evidence, changed condition, and decision.
Explain a recall using information, workflow, and agent graphs.
Authored case. Select any record below; nothing is sent to a model.FOLLOW THE EXAMPLE1 / 6
Interpret this honestlySample evidence, not your actual data.No real messages, tools, training, or hardware operations run.The sequence illustrates the concept; it is not a recorded agent trace.
THE VISIBLE WORKStarting evidence
Input record
AUTHORED TEACHING RECORD · NOT A LIVE RUN
Information: lot L7 → board B2 → P8. Workflow: verify → draft notice → approve. Agents: investigator → reviewer.
What changed: Establish the facts supplied for this version of the task.
WHY THIS MATTERS
What this case assumes
Nodes and edges need an explicit meaning. A knowledge relationship is not an instruction to execute a step or delegate an action.
1 / 6
Apply this to your project
Describe your task to your own model and use Graph engineering as a reference. Ask whether it fits, which alternatives meet the same automation needs, and how you would implement and check the result.
Graphs describe connections. First ask what the connections mean: relationships between facts, or transitions between pieces of work.
A knowledge graph is a data model. Workflow and agent graphs describe execution. An application can combine them: an agent can query a knowledge graph during a workflow step.
Three meanings of an arrow
| Knowledge graph | Workflow graph | Agent graph | |
|---|---|---|---|
| A node represents | An entity, concept, or claim | An operation or subworkflow | An agent or another operation in a composed system |
| An edge represents | A named relationship | An allowed transition or dependency | A handoff or another allowed transition |
| A useful question | Which parts fit this model? | What runs after validation fails? | Which specialist handles the next subtask? |
| What you design | Identity, relationships, provenance, updates | Steps, state contracts, branch policy, recovery | Roles, tools, context, handoffs, authority, limits |
The boundary is about control
A conditional edge is not automatically agentic. A workflow can use a model to classify an input and route to a predefined handler. An agent can choose a next action based on what it discovers. A mixed system can do both.
This guide places common knowledge-graph applications at level 2, workflows at level 3, and teams at level 6. These are teaching groupings, not framework requirements. Several nodes do not necessarily make a team.
What the picture leaves out
Dynamic routing still needs design. Define destinations, handoff data, permissions, and termination behavior before allowing a model to choose between them.
Checkpointing is an implementation choice. A graph does not inherently save after every node. Configure persistence deliberately and check the framework’s recovery semantics.
Relationships need evidence. Knowledge graphs can be authored manually, imported from structured systems, or extracted from text. Entity identity, incorrect edges, stale facts, and missing relationships still need attention.
Choose a representation for the task
Use a knowledge graph when explicit relationships help answer your questions. Use a workflow graph when branches, dependencies, or recovery paths are worth making explicit. Use an agent graph when delegating decisions across agents has a concrete advantage over one agent or a fixed process.
Start with retrieval or a sequential workflow when it already meets the task. Draw exits, errors, retries, and handoffs as well as the happy path.
Last reviewed 09/20/2026. Pages unreviewed for 90 days are flagged for another pass.