Tally + ChatGPT
Build a Tally reader with ChatGPT
Prepare a grounded submission review briefing
Use ChatGPT to build a separate read-only Tally assistant with Agent200. Ground the submission review briefing in returned source data.
On this page
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 ChatGPT.
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.
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
- Works with
- ChatGPT · Your own agent code
- Authentication
- Your Agent200 API key
- You need
- An Agent200 API key
- Tools
- 5 tools
- Model in examples
openai/gpt-5.6-sol
Before you start
- An Agent200 API key. Create one on the API keys page 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 ChatGPT
-
1
Step 1: Create your Agent200 API key
Create a key on the API keys page and store it securely.
.envConceptual exampleStore the Agent200 API key as an environment variable # Keep the key out of your code, prompts and chats. export AGENT200_API_KEY="paste-your-key-here" -
2
Step 2: Inspect the real tool definitions
Confirm the actual Tally read operations and input schemas in your runtime.
-
3
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.
-
4
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.
run.jsConceptual exampleRun a request with the connector's tools 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);
Test your connection
Run one request to check everything is wired up.
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.
Get your API key
Create a key in the Agent200 dashboard. It reaches Tally and every other connector enabled for your project.
Instructions for AI agents
Using a coding agent? Paste this brief into it, or give it the address of this page. It lists what to do, in order, to connect Tally to ChatGPT.
Goal: connect Tally to ChatGPT with Agent200. Guide: https://www.agent200.com/connectors/tally/framework/chatgpt/ 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/
The whole guide is also available as Markdown, for agents and LLMs: /connectors/tally/framework/chatgpt.md
Tally tools ChatGPT can call
-
List forms
Readtally_list_formsFind forms visible to the API token.
-
Read a form
Readtally_get_formRetrieve one identified form.
-
List questions
Readtally_list_questionsRead question definitions for a selected form.
-
List submissions
Readtally_list_submissionsFind submissions with supported filters and pagination.
-
Read a submission
Readtally_get_submissionRetrieve one identified submission.
No tool matches that search.
How it works
-
01
Your app sends the request
It calls Agent200 with the model, instructions, the input and the Tally tools.
-
02
The model picks a tool
The model decides whether a Tally tool is needed, and with which arguments.
-
03
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.
-
04
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 ChatGPT; it does not install a connector into the ChatGPT app.
