Collect financial data on 100 independent schools
My Hands-On Experiment with OpenAI’s Operator. Task: My Hands-On Experiment with OpenAI’s Operator If you feel like AI news has been on a rollercoaster lately, you’re not alone. We’ve been riding an AI hype cycle that has everyone talking – and educators are no exception. A new buzzword in this cycle is agentic AI: not just chatbots answering questions, but AI that takes action on our behalf. Think of software that can browse, click, and type for you, almost like a virtual intern. It sounds like science fiction, and to be fair, the technology is still finding its footing. Analysts note that agentic AI is in its early stages and is still immature in many ways. Yet, it’s advancing at breakneck speed. In fact, we’re already seeing rapid progress from simple email helpers to more autonomous calendar scheduling agents, all of which are now offered through email clients like Superhuman and Shortwave. OpenAI recently released an experimental agent called Operator, which they claim can handle simple browser-based tasks, like ordering groceries for pickup or delivery. The pace of development is dizzying – new capabilities seem to emerge every month – and it’s not too soon to start paying attention. Fullstack Educator is a reader-supported publication. To receive new posts and support my work, consider becoming a free or paid subscriber. So, with equal parts skepticism and curiosity, I decided to put Operator to the test. Would it live up to the hype and actually help with a real-world task, or would it reveal the cracks beneath the buzz? To find out, I gave Operator a challenge that many of us in education and research can appreciate: a tedious data-gathering project that I really didn’t want to do by hand. Here’s how that experiment unfolded. Experiment Setup For my test drive of Operator, I chose a task that was both practical and a bit ambitious: gathering financial data for 100 independent schools. Why this task? In the world of independent (private) schools, strategic decisions often rely on understanding finances – budgets, fundraising, endowments, expenditures - the financial strength of peer institutions. Much of that information is publicly available through IRS filings (Form 990) since most independent schools are nonprofit organizations. ProPublica is an organization and website that hosts this information in a handy web database called Nonprofit Explorer, which includes summary financial data from those tax returns. In other words, the data was out there on the web, but collecting it into one place would normally mean a lot of repetitive clicking and copy-pasting – exactly the kind of drudgery we hope AI might handle. The plan was straightforward on paper: have Operator pull key financial metrics from ProPublica’s Nonprofit Explorer for 100 schools and record them in a Google Sheet. I prepared a blank Google Sheet with nothing but a list of the schools’ names (which I got from an o3-mini-high query). Operator would need to: Search for each school on ProPublica’s Nonprofit Explorer site. Search for each school on ProPublica’s Nonprofit Explorer site. Click on the school’s entry to find the summary financial data (like total revenue and assets for the latest year). Click on the school’s entry to find the summary financial data (like total revenue and assets for the latest year). Copy those numbers and paste them into the Google Sheet in the row for that school. Copy those numbers and paste them into the Google Sheet in the row for that school. It’s the kind of rote web-based task that could eat up hours of my time – perfect for an AI agent if it actually works. The rationale was that this experiment would simulate an actual strategic analysis prep: before you can analyze or compare schools’ financials, you need to gather the data. Usually, I might write a custom script if I felt like coding. But here, I wanted to see if a no-code AI agent could serve as my data collector in the background while I focused on other work (or maybe just sipped my coffee). With the stage set—Google Sheet ready, a list of 100 school names in hand, and Operator at my command—I kicked off the experiment. How Operator Performed; tools: Operator. Human role: The original post does not say how a person stayed involved.; limitations: Operator is not 100% reliable and requires extensive human supervision for accuracy. The process is significantly slower than manual entry or scripted scraping for large datasets. Rounding inconsistencies and entity misidentification limit its utility for precise financial comparison without post-processing..
Tools
Published on Agent Work Atlas:
Overview
My Hands-On Experiment with OpenAI’s Operator
Workflow
My Hands-On Experiment with OpenAI’s Operator If you feel like AI news has been on a rollercoaster lately, you’re not alone. We’ve been riding an AI hype cycle that has everyone talking – and educators are no exception. A new buzzword in this cycle is agentic AI: not just chatbots answering questions, but AI that takes action on our behalf. Think of software that can browse, click, and type for you, almost like a virtual intern. It sounds like science fiction, and to be fair, the technology is still finding its footing. Analysts note that agentic AI is in its early stages and is still immature in many ways. Yet, it’s advancing at breakneck speed. In fact, we’re already seeing rapid progress from simple email helpers to more autonomous calendar scheduling agents, all of which are now offered through email clients like Superhuman and Shortwave. OpenAI recently released an experimental agent called Operator, which they claim can handle simple browser-based tasks, like ordering groceries for pickup or delivery. The pace of development is dizzying – new capabilities seem to emerge every month – and it’s not too soon to start paying attention. Fullstack Educator is a reader-supported publication. To receive new posts and support my work, consider becoming a free or paid subscriber. So, with equal parts skepticism and curiosity, I decided to put Operator to the test. Would it live up to the hype and actually help with a real-world task, or would it reveal the cracks beneath the buzz? To find out, I gave Operator a challenge that many of us in education and research can appreciate: a tedious data-gathering project that I really didn’t want to do by hand. Here’s how that experiment unfolded. Experiment Setup For my test drive of Operator, I chose a task that was both practical and a bit ambitious: gathering financial data for 100 independent schools. Why this task? In the world of independent (private) schools, strategic decisions often rely on understanding finances – budgets, fundraising, endowments, expenditures - the financial strength of peer institutions. Much of that information is publicly available through IRS filings (Form 990) since most independent schools are nonprofit organizations. ProPublica is an organization and website that hosts this information in a handy web database called Nonprofit Explorer, which includes summary financial data from those tax returns. In other words, the data was out there on the web, but collecting it into one place would normally mean a lot of repetitive clicking and copy-pasting – exactly the kind of drudgery we hope AI might handle. The plan was straightforward on paper: have Operator pull key financial metrics from ProPublica’s Nonprofit Explorer for 100 schools and record them in a Google Sheet. I prepared a blank Google Sheet with nothing but a list of the schools’ names (which I got from an o3-mini-high query). Operator would need to: Search for each school on ProPublica’s Nonprofit Explorer site. Search for each school on ProPublica’s Nonprofit Explorer site. Click on the school’s entry to find the summary financial data (like total revenue and assets for the latest year). Click on the school’s entry to find the summary financial data (like total revenue and assets for the latest year). Copy those numbers and paste them into the Google Sheet in the row for that school. Copy those numbers and paste them into the Google Sheet in the row for that school. It’s the kind of rote web-based task that could eat up hours of my time – perfect for an AI agent if it actually works. The rationale was that this experiment would simulate an actual strategic analysis prep: before you can analyze or compare schools’ financials, you need to gather the data. Usually, I might write a custom script if I felt like coding. But here, I wanted to see if a no-code AI agent could serve as my data collector in the background while I focused on other work (or maybe just sipped my coffee). With the stage set—Google Sheet ready, a list of 100 school names in hand, and Operator at my command—I kicked off the experiment. How Operator Performed
Reported result
The experiment was partially successful but unreliable. Operator stopped after collecting data for only about 25 schools due to excessive slowness. It introduced rounding errors and misidentified organizations with similar names, requiring the author to supervise closely and correct mistakes.
Human role
The original post does not say how a person stayed involved.
Limitations
Operator is not 100% reliable and requires extensive human supervision for accuracy. The process is significantly slower than manual entry or scripted scraping for large datasets. Rounding inconsistencies and entity misidentification limit its utility for precise financial comparison without post-processing.
Try it
Act as a data collection agent using OpenAI Operator. I need to gather financial metrics (total revenue, assets) for [replaceable list of 10 nonprofit school names] from ProPublica Nonprofit Explorer and log them into [replaceable Google Sheet URL]. Steps: 1. Search for each school name on the site. 2. Click the correct entry (verify EIN or location if ambiguous). 3. Extract exact numbers without rounding. 4. Paste into the corresponding row in the Google Sheet. Constraints: - Process only 3 schools as a dry run first. - Stop and ask for confirmation if a school name is ambiguous. - Do not round numbers; preserve exact figures. - Report any errors or misidentifications immediately. Output: - A completed Google Sheet with verified data for the sample. - A summary of any issues encountered during the dry run. Measure success by: 100% accuracy in the sample data and correct entity identification. If the sample fails, do not proceed to the full list.
Source reports are not independently verified. Publication date is the catalog publication date, not the original article date.