# Build a ServiceM8 reader with OpenAI Dots Prepare a grounded field-service job briefing

> Use OpenAI Dots to build a separate read-only ServiceM8 assistant with Agent200. Ground the field-service job briefing in returned source data.

- Page: https://www.agent200.com/connectors/servicem8/framework/openai-dots/
- Connector: [ServiceM8](https://www.agent200.com/connectors/servicem8.md)
- Framework: OpenAI Dots
- Updated: 2026-11-17

## Instructions for AI agents

Goal: connect ServiceM8 to OpenAI Dots with Agent200.
Guide: https://www.agent200.com/connectors/servicem8/framework/openai-dots/

1. Get an Agent200 API key. If the developer has none, send them to https://agent200.com/platform/apikeys/ and ask them to choose "Create an API key". Read the key from the AGENT200_API_KEY environment variable. Never ask for it in chat, and never write it into code, prompts or logs.
2. Make sure ServiceM8 is enabled for the project in the Agent200 dashboard (Connectors), with the endpoints and scopes the task needs.
3. Add the Agent200 SDK to the project and create a client with that key.
4. Give every request a stable id for the end user. Agent200 uses only that user's own connections.
5. Connect the user's ServiceM8 account through Agent200. If Agent200 returns an authorization link, show it to the user and continue once they have approved access on ServiceM8.
6. Run requests through Agent200 with a model (for example openai/gpt-5.6-sol) and "servicem8" in the tools. The model decides when a ServiceM8 tool is needed; Agent200 executes the call.
7. Check it works with this request: "Read the ServiceM8 job I identify. Include its returned status, client and scheduled activities. Cite the specific records and disclose missing fields. Do not edit jobs or message anyone."
   What should come back:
   - The selected job is identified.
   - Only returned job status, client identity and scheduled activity details actually returned are reported.
   - Access gaps and missing context are explicit; no source data is changed.
8. If a tool is missing or a call is refused, check the project's Connectors settings in the dashboard and the access the user granted in ServiceM8, then retry.

The code on the guide page is a conceptual example of the SDK. SDK reference: https://docs.igpt.ai/

## Overview

Build a separate field-service job briefing application with Agent200. Use the runtime’s real schemas and preserve the authenticated user. This is an architecture guide, not a native installation in OpenAI Dots.

Start with one identified job. Preserve returned job status, client identity and scheduled activity details actually returned; report missing data and keep the workflow read-only.

Provider reference: [ServiceM8 API](https://developer.servicem8.com/reference/listjobs).

- **Connector:** [ServiceM8](https://www.agent200.com/connectors/servicem8/)
- **Works with:** OpenAI Dots · Your own agent code
- **Authentication:** Managed OAuth, per end user
- **You need:** [An Agent200 API key](https://agent200.com/platform/apikeys/)
- **Tools:** [6 tools](https://www.agent200.com/connectors/servicem8/framework/openai-dots/#tools)
- **Model in examples:** `openai/gpt-5.6-sol`

## Before you start

- **An Agent200 API key.** Create one on the [API keys page](https://agent200.com/platform/apikeys/) of the dashboard.
- **ServiceM8 enabled for your project.** In the dashboard's Connectors settings, with the endpoints and scopes your agent needs.
- **An end user with a ServiceM8 account.** They approve access once, on ServiceM8's own page.
- **A model for your agent.** The examples use openai/gpt-5.6-sol, through the same Agent200 API key.

## Connect ServiceM8 to OpenAI Dots

### Step 1: Create your Agent200 API key

Create a key on the [API keys page](https://agent200.com/platform/apikeys/) and store it securely.

File `.env`:

```bash
# Keep the key out of your code, prompts and chats.
export AGENT200_API_KEY="paste-your-key-here"
```

(Conceptual example of the Agent200 SDK.)

### Step 2: Inspect the real tool definitions

Confirm the actual ServiceM8 read operations and input schemas in your runtime.

### Step 3: Connect the user’s ServiceM8 account

Preserve the same stable user identity during authorization and later requests.

File `connect.js`:

```js
// Each end user authorizes their own ServiceM8 account, once.
const connection = await agent200
  .user("user_123")
  .connect("servicem8");

if (connection.authorizationUrl) {
  // Show this link to your user; Agent200 handles the rest.
  console.log(connection.authorizationUrl);
}
```

(Conceptual example of the Agent200 SDK.)

### Step 4: Build and test the read-only answer

Prepare the field-service job briefing only from returned source data. The code example illustrates a sequence, not an SDK installation contract.

File `run.js`:

```js
const result = await agent200
  .user("user_123")
  .run({
    model: "openai/gpt-5.6-sol",
    input: "List the open jobs for Hamilton Plumbing",
    tools: ["servicem8"],
  });

console.log(result.output);
```

(Conceptual example of the Agent200 SDK.)

## Test your connection

Ask: "Read the ServiceM8 job I identify. Include its returned status, client and scheduled activities. Cite the specific records and disclose missing fields. Do not edit jobs or message anyone."

What should come back:

- The selected job is identified.
- Only returned job status, client identity and scheduled activity details actually returned are reported.
- Access gaps and missing context are explicit; no source data is changed.

Check the job and client UUIDs, connected account, OAuth read scopes and schedule window. Report missing or inaccessible records without assuming that no work is scheduled.

## ServiceM8 tools OpenAI Dots can call

- **List jobs** (`servicem8_list_jobs`, read): Find accessible jobs and their returned status and client references.
- **Read a job** (`servicem8_get_job`, read): Retrieve details of one identified job.
- **List clients** (`servicem8_list_clients`, read): Find client records available to the connected account.
- **Read a client** (`servicem8_get_client`, read): Retrieve one identified client record.
- **List client contacts** (`servicem8_list_client_contacts`, read): Find contacts associated with an identified client.
- **List scheduled activities** (`servicem8_list_job_activities`, read): Read scheduled job activities within the available scope.

## How it works

1. **Your app sends the request.** It calls Agent200 with the model, instructions, the input, the end user's id and the ServiceM8 tools.
2. **The model picks a tool.** The model decides whether a ServiceM8 tool is needed, and with which arguments.
3. **Agent200 runs the call.** It uses that user's own ServiceM8 connection, within the endpoints and scopes your project allows, and returns the result to the model.
4. **Your app gets the result.** Agent200 returns the completed result. Your app decides when the agent runs and what happens next.

**Each user's own connection.** Connections belong to individual end users. A request for one user never reaches another user's ServiceM8 account.

**Permissions at every level.** Your project settings decide what the agent may request, the end user decides what they authorize, and ServiceM8 enforces what its API grants.

## Troubleshooting

### The source cannot be read

Check the job and client UUIDs, connected account, OAuth read scopes and schedule window. Report missing or inaccessible records without assuming that no work is scheduled.

## FAQ

### How do I verify this result?

Compare the named job and returned job status, client identity and scheduled activity details actually returned with the source. Treat missing information as missing, not as a fact.

### Is this a native product integration?

This describes a separate application built with Agent200 and OpenAI Dots; it does not install a connector into the OpenAI Dots app.

## Use ServiceM8 with another framework

- [ServiceM8 + Claude](https://www.agent200.com/connectors/servicem8/framework/claude.md)
- [ServiceM8 + ChatGPT](https://www.agent200.com/connectors/servicem8/framework/chatgpt.md)
- [ServiceM8 + Claude Code](https://www.agent200.com/connectors/servicem8/framework/claude-code.md)
- [ServiceM8 + Muse](https://www.agent200.com/connectors/servicem8/framework/muse.md)
- [ServiceM8 + Grok Bot](https://www.agent200.com/connectors/servicem8/framework/grok-bot.md)
- [ServiceM8 + Claude Duet](https://www.agent200.com/connectors/servicem8/framework/claude-duet.md)
- [ServiceM8 + Hermes Agent](https://www.agent200.com/connectors/servicem8/framework/hermes-agent.md)
- [ServiceM8 + OpenClaw](https://www.agent200.com/connectors/servicem8/framework/openclaw.md)

---

Agent200: https://www.agent200.com/ · API keys: https://agent200.com/platform/apikeys/ · Docs: https://docs.igpt.ai/
