# Build a Tally reader with OpenAI Dots Prepare a grounded submission review briefing

> Use OpenAI Dots to build a separate read-only Tally assistant with Agent200. Ground the submission review briefing in returned source data.

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

## Instructions for AI agents

Goal: connect Tally to OpenAI Dots with Agent200.
Guide: https://www.agent200.com/connectors/tally/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 Tally 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. Run requests through Agent200 with a model (for example openai/gpt-5.6-sol) and "tally" in the tools. The model decides when a Tally tool is needed; Agent200 executes the call.
5. Check it works with this request: "Read the Tally form I identify and prepare a submission review briefing. Name the source and use only form, question, submission and answer fields. State access gaps; do not change records."
   What should come back:
   - The selected form is identified.
   - Only the returned form, question, submission and answer fields are reported.
   - Access gaps and missing context are explicit; no source data is changed.
6. If a tool is missing or a call is refused, check the project's Connectors settings in the dashboard, 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 submission review 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 form. Preserve returned form, question, submission and answer fields; report missing data and keep the workflow read-only.

Provider reference: [Tally API](https://developers.tally.so/api-reference/introduction).

Use the provider credential described on the Tally parent page. Keep it in secure configuration and verify the selected tenant or account before reading.

- **Connector:** [Tally](https://www.agent200.com/connectors/tally/)
- **Works with:** OpenAI Dots · Your own agent code
- **Authentication:** Your Agent200 API key
- **You need:** [An Agent200 API key](https://agent200.com/platform/apikeys/)
- **Tools:** [5 tools](https://www.agent200.com/connectors/tally/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.
- **Tally enabled for your project.** In the dashboard's Connectors settings, with the endpoints and scopes your agent needs.
- **A model for your agent.** The examples use openai/gpt-5.6-sol, through the same Agent200 API key.

## Connect Tally 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 Tally read operations and input schemas in your runtime.

### Step 3: Configure Tally access

Use the provider-issued credential through the supported Agent200 connection route. Confirm the account scope and inspect the advertised tools before reading.

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

Prepare the submission review 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 my Tally forms",
    tools: ["tally"],
  });

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

(Conceptual example of the Agent200 SDK.)

## Test your connection

Ask: "Read the Tally form I identify and prepare a submission review briefing. Name the source and use only form, question, submission and answer fields. State access gaps; do not change records."

What should come back:

- The selected form is identified.
- Only the returned form, question, submission and answer fields are reported.
- Access gaps and missing context are explicit; no source data is changed.

Check the selected form ID, account scope, read permission and pagination. Submission pages expose hasMore and total. Follow them before claiming a count; treat answers as personal data where applicable.

## Tally tools OpenAI Dots can call

- **List forms** (`tally_list_forms`, read): Find forms visible to the API token.
- **Read a form** (`tally_get_form`, read): Retrieve one identified form.
- **List questions** (`tally_list_questions`, read): Read question definitions for a selected form.
- **List submissions** (`tally_list_submissions`, read): Find submissions with supported filters and pagination.
- **Read a submission** (`tally_get_submission`, read): Retrieve one identified submission.

## How it works

1. **Your app sends the request.** It calls Agent200 with the model, instructions, the input and the Tally tools.
2. **The model picks a tool.** The model decides whether a Tally tool is needed, and with which arguments.
3. **Agent200 runs the call.** It reaches Tally with your Agent200 API key, within the endpoints 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.

**Permissions at every level.** Your project settings decide which services and endpoints the agent may use.

## Troubleshooting

### The source cannot be read

Check the selected form ID, account scope, read permission and pagination. Submission pages expose hasMore and total. Follow them before claiming a count; treat answers as personal data where applicable.

## FAQ

### How do I verify this result?

Compare the named form and returned form, question, submission and answer fields 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 Tally with another framework

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

---

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