This guide shows you how to set up an Airtable OpenAI integration with web search to automatically fetch daily stock news. You'll build an automation that updates your base with headlines, summaries, URLs, and dates from recent news stories - no coding required.
Unlike Airtable's AI field agents which populate single fields, the OpenAI responses API can search the web and return multiple pieces of structured data - each in its own Airtable field.
What you'll learn:
This integration uses OpenAI's API with web search to find current information directly in your Airtable base. While Data Fetcher is free to start, you'll also need an OpenAI API account with billing set up.
Before connecting to the OpenAI responses API, you need to prepare your Airtable base with company names and stock tickers to search.
1. Create a table called "Companies" if you don't already have one.
2. In the Name field, enter the company names:
3. Add a new field called Ticker (Single line text field).
4. Enter the corresponding stock tickers in the Ticker field:
1. Sign up for an OpenAI API account, or log in to your existing account.
2. Add a payment method in your OpenAI API billing panel.
3. Create an API key in your OpenAI account. Save this API key - you'll need it in the next steps.
Note: OpenAI API accounts and billing are separate from ChatGPT subscriptions. You will still need to go through these steps even if you have a subscription to ChatGPT.
We'll create a request in Data Fetcher that will send queries to the OpenAI responses API to search for current stock news.
1. Add the Data Fetcher extension to your Airtable base.
2. Once you've added the extension, sign in to Data Fetcher or sign up if you don't have an account.
3. Once you're logged in to Data Fetcher, click Create your first request.
Follow these steps to configure the request:
1. Select OpenAI under Application.
2. Rename the request to "Fetch Daily Stock News".
3. Copy and paste your OpenAI API key under Authorization.
4. Under Endpoint, select Create a model response.
5. Click Save and Continue in the bottom right corner.
6. For this tutorial, we'll use the gpt-5-mini model, which provides excellent web search capabilities at lower cost.
Writing effective prompts for the OpenAI responses API requires clear instructions about what information to find and how to format it. The key is specifying the time frame, topic, and exact output structure you need.
1. Copy and paste the following text into the Input field:
Find a news story in the last 24 hours about this public company. Return only JSON with these fields: headline, url, summary, published_date. Stock ticker:
2. Click the + button on the right-hand side of the input.
3. In the dialog that opens:
4. Click Confirm to save and close the dialog.
The input prompt will now have a reference to the Ticker field, so the OpenAI responses API will search for news about each stock ticker in your table.
5. Toggle on the Enable web search option. This allows the OpenAI responses API to search the internet for current information instead of relying only on its training data.
1. Click Save & Run in the bottom right.
The request will run and the Response Field Mapping modal will open. This is where you map the fields returned by the OpenAI responses API to your Airtable table.
Data Fetcher returns several fields from the OpenAI responses API, but we only need the news data fields we specified in our JSON format. You can ignore the "Json" prefix in the field names - Data Fetcher automatically adds this because we configured the API to return JSON-formatted data.
2. Click the Message field to deselect it. We don't need the raw message, as we'll map each field separately.
3. Select and map these fields from the OpenAI responses API to your table:
4. Click Save & Run in the bottom right.
Data Fetcher will now create the new fields, and run the Airtable OpenAI responses API integration. Back in your Companies table, you'll see current news stories populated for each stock ticker, with headlines, URLs, summaries, and publication dates in separate fields.
To keep your stock news current, you can set up the OpenAI responses API to automatically fetch fresh news once per day for all companies in your table.
Note: This requires a paid Data Fetcher plan.
1. Scroll to the Schedule section in Data Fetcher and click Upgrade.
2. Choose a Data Fetcher plan based on your needs and enter your payment details.
1. After upgrading, click + Authorize.
2. A window will open where you'll authorize Airtable bases. Click + Add resources to avoid needing to authorize bases in the future.
3. Click Grant access.
1. Back in Data Fetcher, the Schedule toggle will now be turned on.
2. Select Days from the interval dropdown.
3. Enter 1 to run the integration once per day.
4. Optionally, set a specific time for the daily update (like 9:00 AM for morning news briefings).
5. Click Save at the bottom of the screen.
Your OpenAI responses API automation is now active! Every day at your scheduled time, Data Fetcher will automatically search for the latest news about each stock in your portfolio and update your Airtable base.
Using the OpenAI responses API with web search lets you automatically gather current information and organize it in your Airtable base. Here are practical ways to use this integration:
Stock Portfolio Tracking: Get daily news updates about companies you're invested in. Track earnings reports, product announcements, and market news with headlines, summaries, and source links organized in your base.
Competitor Monitoring: Keep tabs on what competitors are doing by collecting news about their product launches, partnerships, and company updates. Build a searchable archive of competitive activity over time.
Industry News Aggregation: Follow developments in your industry by searching for regulatory changes, market trends, or technology updates. Create a knowledge base that updates daily with relevant news.
Client Research: Stay informed about your key clients by tracking news about their business expansions, leadership changes, or major announcements. Use this information to prepare for meetings or identify new opportunities.
Event Monitoring: Track conference announcements, webinar schedules, or industry events related to your interests. Build a calendar of upcoming opportunities with details and registration links.
Each search can pull multiple pieces of information into separate fields - dates, titles, descriptions, URLs - giving you organized, structured data instead of unformatted text dumps.
Jul 25, 2024
Jul 18, 2024
Jul 5, 2024
Data Fetcher customers spend less time copying data and more time using it.
1 / 11
Data Fetcher is incredibly easy to use and understand. We have no API or data experience, yet our team can seamlessly integrate external data easily with Data Fetcher.
Thomas Coiner
CEO, ProU Sports