> For the complete documentation index, see [llms.txt](https://vibemx.gitbook.io/neuronai-studio/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://vibemx.gitbook.io/neuronai-studio/agents/overview.md).

# Overview

Agents are the core building blocks of NeuronAI Studio. Each agent definition stores a provider, model, system instructions, and optional tool/MCP bindings.

## What is an agent?

An agent is a configured LLM assistant that can:

* Follow a system prompt (instructions)
* Call bound tools during conversation
* Access MCP server tools when configured
* Run standalone in the Playground or inside workflow graphs

```mermaid
flowchart TB
    Definition[AgentDefinition in DB] --> Runner[AgentRunner]
    Runner --> DynamicAgent[DynamicAgent]
    DynamicAgent --> Provider[Neuron LLM Provider]
    DynamicAgent --> Tools[Bound Tools + MCP Tools]
    Provider --> Response[Streaming Response]
    Tools --> Response
```

## Agent lifecycle

| Stage           | Where                              | Guide                                                                      |
| --------------- | ---------------------------------- | -------------------------------------------------------------------------- |
| Create / edit   | Agent form                         | [Creating Agents](/neuronai-studio/agents/creating-agents.md)              |
| Test            | Playground                         | [Playground & Threads](/neuronai-studio/agents/playground-and-threads.md)  |
| Evaluate        | Evals UI or CLI                    | [Evaluations](/neuronai-studio/agents/evaluations.md)                      |
| Use in workflow | Agent node                         | [AI Nodes](/neuronai-studio/workflows/ai-nodes.md)                         |
| Export          | Studio UI, CLI, or codegen preview | [Export & Production](/neuronai-studio/workflows/export-and-production.md) |

## Studio routes

| Route                                     | Purpose                  |
| ----------------------------------------- | ------------------------ |
| `/neuronai-studio/agents`                 | List all agents          |
| `/neuronai-studio/agents/create`          | Create new agent         |
| `/neuronai-studio/agents/{id}/edit`       | Edit agent               |
| `/neuronai-studio/agents/{id}/playground` | Test agent in chat       |
| `/neuronai-studio/agents/{id}/evals`      | Manage evaluation suites |

> **Screenshot pending:** Agent list with Create Agent button.
>
> Asset path: `docs/assets/screenshots/agents-index.png` Capture: `/neuronai-studio/agents` — dark theme, 1440×900

## Database model

Agents are stored in the `agent_definitions` table (always prefixed, e.g. `neuronai_studio_agent_definitions`). Key fields:

* `name`, `slug` — display name and unique identifier
* `provider`, `model` — LLM configuration
* `instructions` — system prompt
* `tools` — JSON array of tool binding references
* `memory_config` — per-agent memory envelope (context window, history driver, summarization / compaction). Null inherits the global `chat_history_context_window` default.

## Knowledge Bases

Knowledge bases store embedded document chunks for retrieval in workflows and RAG tools.

| Route                                        | Purpose                                         |
| -------------------------------------------- | ----------------------------------------------- |
| `/neuronai-studio/knowledge-bases`           | List knowledge bases                            |
| `/neuronai-studio/knowledge-bases/create`    | Create knowledge base                           |
| `/neuronai-studio/knowledge-bases/{id}/edit` | Edit metadata, ingest documents, preview search |

Full guide: [Knowledge Bases](/neuronai-studio/knowledge-bases/overview.md).

Each knowledge base configures embeddings, a [vector store driver](/neuronai-studio/knowledge-bases/vector-stores.md), and retrieval defaults (`top_k`, `threshold`).

Connect to agents via a **RAG tool** or a workflow **RAG node** — see [Agent binding](/neuronai-studio/knowledge-bases/agent-binding.md).

## Next steps

* [Creating Agents](/neuronai-studio/agents/creating-agents.md)
* [Playground & Threads](/neuronai-studio/agents/playground-and-threads.md)
* [Evaluations](/neuronai-studio/agents/evaluations.md)
* [Tools Overview](/neuronai-studio/tools/overview.md)


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://vibemx.gitbook.io/neuronai-studio/agents/overview.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.