Skip to content
Nappai Documentation

Simple Agent

Simple Agent is an AI agent that answers messages and uses the tools you connect when it needs them. It works like Agent, but without the advanced features switch: it has the essentials for an assistant and is easier to set up.

Use it when you want an assistant or an automatic task powered by AI and you don’t need usage limits or the rest of Agent’s advanced features. It can still use backup models by turning on Use Fallback Models and stop to wait for an approval with the Request Approval tool.

When to use it

  • A frequently asked questions assistant on your company website.
  • Drafting replies to customer emails from their message.
  • Querying a tool (calendar, CRM, search engine) and summarising the result.
  • Processing a list of texts one by one, for example to classify reviews.

Configuration

ConnectionWhat to connect
Model (required)An AI model component, for example OpenAI.
ToolsThe tools the agent can use. You can connect several.
Fallback ModelsAppears when you turn on Use Fallback Models in the advanced options. One or more backup models. If the main model fails (the provider does not answer, a usage limit is exceeded, it takes too long or returns an error), the agent repeats that step with the first one and, if that also fails, with the next, in order. The conversation and what the tools already did are kept. A model from a different provider works best.
FieldWhat it does
Agent NameThe agent’s name when another agent uses it as a tool or subagent. Default: Agent.
Agent DescriptionWhat the agent does. Another agent reads it to decide when to turn to it.
User PromptThe template of the message the agent receives. Default: {input}. Each variable in curly braces becomes a field with that name, which you can fill in or connect.
InputThe message the agent processes, usually from Chat Input. It is the field of the {input} variable.
System PromptThe agent’s behaviour instructions. Write them or connect a Prompt component. Default: You are a helpful AI assistant.

Advanced options

FieldWhat it does
Recursion LimitThe maximum number of internal steps in one answer. When it is reached, the agent stops. Default: 1000.
StreamThe answer appears in the chat as it is generated. Turning it on shows Stream Thinking, which also shows the model’s reasoning.
Include State in responseAdds the agent’s internal run data to the answer.
Use memoryThe agent remembers the conversation. Turning it on shows the Memory connection and, in the Context and Memory tab, Memory Strategy: Trim (default; the model only receives the latest messages set in Memory Limit, -1 for all), Delete Oldest (deletes the oldest messages) or Summarize (summarises older messages when the conversation exceeds Max Tokens and keeps the ones set in Messages to Keep).

In Memory you can connect a component such as Postgres Memory or Redis Memory to keep the conversation in your own service. If you connect nothing, NappAI keeps it for you.

Guardrails

In the Advanced tab, Guardrails gives the agent rules it never breaks: every request, and every action before a tool is used, is checked. See Guardrails, with an example video.

Using it as an agent tool

You can connect this component to an agent’s Tools input. In the Tool tab, Tool Name and Tool Description are the name and explanation the agent uses to recognise the tool and decide when to call it: write a clear description of what it does.

Batch processing

With the Batch Mode switch on, the component runs once for each item of the list you connect to Batch Input and returns all the results together as a list. Parallel Executions sets how many items are processed at the same time (1 to 5). Skip if Empty Batch Input skips the component when the list arrives empty, and Skip Branch if Empty Output stops the following components when the result is empty. More in Key concepts.

Output

  • Response: the agent’s answer as a message. Connect it to Chat Output or to any component that takes text.
  • Agent: the configured agent, to connect it to another agent that delegates to it (for example, to Worker Agents on Supervisor Agent).
  • Tool: the agent turned into a tool, for another agent’s Tools input.

Example

The language school Lingua Norte wants to answer questions about timetables and enrolment on its website. It connects Chat Input to Input, an AI model to Model and writes in System Prompt: “You are the Lingua Norte assistant. You answer questions about timetables, levels and enrolment fees. If you don’t know something, offer the office phone number.” It turns on Use memory so the assistant remembers what the student has already asked, and connects Response to Chat Output.