Next Steps

Explain what Aura Agent is and how it fits into the Aura Console

Describe the agent loop: interpret input, select a tool, execute a query, generate a response

Identify which of the three tool types — Cypher Template, Text2Cypher, or Similarity Search — fits each question type

Define role and scope so the agent stays focused and declines off-topic requests

Write tool descriptions that give the LLM enough context to select the correct tool

Create a Cypher Template tool with parameterized queries and descriptive parameter names

Create a Text2Cypher tool with a domain-aware description that constrains when it is used

Understand when Similarity Search applies and what graph preparation it requires

Add, edit, and delete tools, and save changes with Update agent

Use the reasoning panel to verify tool selection and inspect generated Cypher

Choose between Internal and External access modes

Enable the MCP server and retrieve the MCP endpoint

Connect your agent to an MCP client such as Cursor or Claude Desktop

Scope agents narrowly — One focused agent per task makes tool selection easier for the LLM and makes behavior more predictable. Include an instruction to decline off-topic requests.

Templates first — If you can write the complete Cypher query now with only $parameter slots for variable values, use a Cypher Template. Reserve Text2Cypher for questions whose structure changes.

Write effective Text2Cypher descriptions — State when to use the tool and when not (for example, only when no template fits). Add domain context: relevant node labels, relationships, and which properties are suitable for filtering and aggregation.

One tool per question pattern — Give each distinct question type its own tool. A single template that tries to cover unrelated questions leads to vague descriptions and wrong tool picks.

Describe parameters as instructions — Write parameter descriptions with examples, such as "The customer ID, for example ALFKI or QUICK", not just "The customer ID".

Use the reasoning panel — Always check the reasoning trace to verify which tool was selected and what Cypher was generated. Inspect Text2Cypher output before relying on it in production.

Save changes — After adding, editing, or deleting tools, click Update agent to persist the configuration.

Neo4j & GenAI Fundamentals — Understand the fundamentals of generative AI and how Neo4j integrates with LLMs

Using Neo4j with LangChain — Integrate Neo4j with LangChain for retrieval-augmented generation and agents

Developing with Neo4j MCP Tools — Learn how to use the Model Context Protocol to connect AI applications to Neo4j tools and data sources

Building GraphRAG Python MCP tools — Build your own GraphRAG MCP server with graph-backed tools using the MCP Python SDK

Building GraphRAG TypeScript MCP tools — Build your own MCP tools and server using the MCP TypeScript SDK

Introduction to Vector Indexes and Unstructured Data — Learn how to generate embeddings and build vector indexes for Similarity Search