AIBots

The AIBots Node connects your workflow to AIBots, a GovTech platform that enables public officers to create, share, and use customised GenAI chatbots. It leverages Retrieval-Augmented Generation (RAG) to integrate internal documents and knowledge bases, allowing the bot to deliver accurate, context-specific responses based on agency information. Visit AIBots Resources to learn more.

Experimental Feature: This node is currently in experimental stage. Features and functionality may be subject to change. You can connect to either the AIBots UAT environment (for testing) or Production environment (for live workflows) — see Connection Settings.

[Action Required] AIBots UAT database wipe — 17 Sep. The AIBots UAT database will be wiped on Wednesday, 17 September, including any bots created in UAT. UAT is intended for testing only; run live workflows against Production. If your workflows use AIBots nodes connected to UAT, complete the following before then to avoid disruption:

1. Migrate or recreate your bots in AIBots Production → https://aibots.gov.sg/
2. Request Production API access → https://go.gov.sg/aibots-api-prod
3. Once your Production API endpoints are enabled, update your AIBots node configuration in OPUS to switch from UAT → Production
4. Test the affected workflows to confirm they still work

If your workflows do not use AIBots UAT, no action is required. For issues updating the AIBots configuration in OPUS, reach out to the OPUS team. For urgent matters on AIBots, contact jacynth_low@tech.gov.sg.

AIBots Support: For any enquiries or issues related to AIBots, please reach out to the AIBots team via http://go.gov.sg/aibots-feedback or the Desk team via https://go.gov.sg/desk-feedback.

How Does It Work?

Prerequisites: Obtain your AIBots API key from the AIBots platform before configuring this node. The key must belong to the same environment (UAT or Production) you select on the node. Refer to AIBots.

Setup Steps:

1. Build your workflow using Graph Edit Mode (minimum setup: input node → AIBots node → output node, but you can add more nodes as needed)
2. Click on the AIBots node settings to open its configuration
3. Select the environment (UAT or Production) you want to connect to
4. Enter your AIBots API key for the selected environment
5. Provide the prompt or instruction you want the AIBots to handle

Output:

By default, the AIBots Node processes the input prompt using the connected AIBots and returns:

{
    "response" : "The AI-generated answer based on your agency’s knowledge base"
}Copy to clipboardErrorCopied

This output can be used by subsequent nodes to provide contextual information, automate responses, or enhance decision-making with agency-specific AI insights.

If you enable Structured Output, the node instead returns a clean object keyed by the fields you define (the response wrapper is dropped), making downstream steps easier to build.

Configuration

Connection Settings

Environment

The AIBots environment you are connecting to. Select UAT or Production using the environment selector on the node.

Note: New AIBots nodes default to the UAT environment. UAT is for testing only — use Production for live workflows. Existing workflows are unaffected and continue to use their current configuration. Make sure your API key matches the selected environment.

UAT database wipe (17 Sep): The AIBots UAT database will be wiped on 17 September, including bots created in UAT. Migrate any UAT-connected nodes to Production before then — see the action-required notice above.

API Key

Your AIBots API key for the selected environment (UAT or Production).

Format: Plain text string (e.g. aibots_...)

Parameters

Prompt

The prompt or instruction sent to your AIBot. Supports Mustache templating, so you can inject values from upstream nodes — for example {{{input.question}}}.

Structured Output

By default the AIBots returns a single block of text in the response field. Turn on the Structured Output toggle in the Parameters section to instead have the node return a clean object with the exact fields you define — so downstream nodes can reference each value directly (e.g. {{{sentiment}}}) instead of parsing free text.

Defining fields:

When you enable the toggle, a field editor appears. Click Add Field to add each output field and configure:

• Data Label — the output key name. Must be a valid identifier (letters, digits, and underscores; must start with a letter). Sibling labels must be unique, and a label cannot begin with an underscore (_).
• Data Type — one of Text, Number, True/False, Date, List, or Object.
• Prompt — a short description telling the bot what to put in this field.

Fields can be nested up to 3 levels deep. An Object field must contain at least one nested field. For a List field:

• No nested field → a list of text values.
• One nested field → a list where every item is that type.
• Two or more nested fields → a fixed-length tuple (one entry per nested field, in order) rather than a repeating list.

Note: At least one field is required when Structured Output is enabled.

Output shape:

With Structured Output on, the node returns only the object you defined — the usual response wrapper is not included:

{
  "sentiment": "positive",
  "score": 0.9
}Copy to clipboardErrorCopied

Tip: Every field is treated as optional (nullable), so the bot may legitimately return null for a field. Handle possible nulls in downstream nodes.

When to Use It?

Use AIBots Node when:

• You want to embed GenAI chatbots into your workflows.
• You need agency-specific answers powered by internal knowledge bases.
• You want a no-code way to build and connect AI chatbots within 5–15 minutes.
• You are exploring secure, cost-effective GenAI solutions built for the public sector.