ChatGPT Built a Budget for Me ASAP, but It Has Several Limitations
ChatGPT can help you set budget categories, spending limits and savings goals. But it still leaves much to be desired.
Getty Images/Zooey Liao/CNET
Artificial intelligence can help you manage your money in lots of different ways. It can show you how to cut grocery costs, save for a vacation and even negotiate your bills. But just because it can doesn't necessarily mean it succeeds. And with something as important as your finances, it's essential to know where it falls short.
Last year, I asked ChatGPT to help me create a budget, a task that can be tedious and overwhelming. It was useful in some ways, but not so great in others.
I tried the experiment again this year, and while I noticed minor improvements -- mainly that icons and improved formatting made the answers more visually appealing -- the overall result was still mixed. Here's how it went.
Read more: How to Create and Master Your 2025 Budget
Building a budget with ChatGPT
These are the steps I took to test ChatGPT's budget-making abilities.
1. State your monthly income, expenses and savings goals
To get started, you'll need to give ChatGPT your monthly financial numbers: take-home income, expenses and savings goals. I already have a budget I made using Rocket Money, so to see how ChatGPT builds a budget from scratch, I had it create one for a hypothetical person.
My prompt:
"My monthly income after taxes is $3,500. Each month, I spend $1,000 on rent, $15 on renters insurance, $100 on utilities, $300 on my car payment, $150 on car insurance, $100 on gas, $200 on my student loans, $40 on my phone bill, $300 on groceries, $100 on personal items and $100 on dining out. I'd also like to put some money toward savings."
The result:
Screenshot by Kelly Ernst/CNET
ChatGPT ran the numbers and told me I'd have $1,095 left each month. I'd intentionally left my savings goals vague to see what ChatGPT would recommend. It suggested ways to allocate this amount toward savings, including building an emergency fund, contributing to retirement savings, paying down debt and making extra student loan payments. It also showed me how I could split my $1,095 between these savings buckets.
2. Clarify and adjust
I'd also intentionally left some spending categories out of my initial prompt -- something someone creating a budget for the first time might easily do -- to see if ChatGPT would catch them. It didn't. So I asked it to help me.
My prompt:
"Have I missed any other common budget categories?"
The result:
Screenshot by Kelly Ernst/CNET
ChatGPT generated a list of potential additions and asked if I wanted it to create a revised budget with placeholders for these categories. The revised budget, including estimates for savings goals and budget categories ChatGPT recommended adding, left me with $5 remaining. That's not a ton of wiggle room, but I could always ask the AI to tweak things to give me a bigger cushion.
Pro tip
To avoid forgetting expenses, review your bank and credit card statements from the past 12 months to spot your regular monthly, seasonal and annual expenses.
3. Import the data into a spreadsheet
There are several ways to track your spending and monitor how well you're sticking to your budget, including budgeting apps and the old paper-and-pencil method. One easy -- and free -- method is to create a spreadsheet, which ChatGPT can also help you with.
My prompt:
"Create a Google spreadsheet for my budget."
The result:
ChatGPT created some code I could copy and paste into Google Sheets.
Screenshot by Kelly Ernst/CNET
It also provided instructions on how to format it.
Screenshot by Kelly Ernst/CNET
I followed these instructions, but all the data showed up in column A of the spreadsheet, and I couldn't figure out what to do next. I had to ask ChatGPT how to fix this.
Screenshot by Kelly Ernst/CNET
It was more work than I was hoping to do, and I still had to make some formatting changes to the spreadsheet so it was easier to read. But in the end, I did have a working budget I could adjust as needed.
Pros and cons of creating a budget with ChatGPT
Using ChatGPT to create a budget was fairly simple. It required some fine-tuning on my part, but overall, the AI's recommendations made sense and were easy to understand. That said, it's not for everyone, and it has its pitfalls. Here's what you should keep in mind.
Pros
It's free. ChatGPT doesn't cost anything, and neither does Google Sheets if you choose to move your budget numbers there.
ChatGPT doesn't cost anything, and neither does Google Sheets if you choose to move your budget numbers there. You can keep it simple. ChatGPT's initial budget suggestions are basic, which can make budgeting more approachable if you're a beginner. You're free to dive deeper into any answer, but you can also use it to create a basic budget to get started.
ChatGPT's initial budget suggestions are basic, which can make budgeting more approachable if you're a beginner. You're free to dive deeper into any answer, but you can also use it to create a basic budget to get started. It can help you customize your budget. ChatGPT can suggest everything from how to save on utilities to how much to put toward retirement at various ages. But you need to ask it to do so. It probably won't offer these tips unprompted.
Cons
Its answers are only as good as your prompts. If you don't word your prompts correctly or you provide incomplete or inaccurate information, ChatGPT's answers won't be as helpful as they could be. For instance, when I omitted some common budget categories, it identified them only when I asked it to. It didn't automatically alert me that I may have left something out. Many budgeting apps offer preset categories you can use as guidance.
If you don't word your prompts correctly or you provide incomplete or inaccurate information, ChatGPT's answers won't be as helpful as they could be. For instance, when I omitted some common budget categories, it identified them only when I asked it to. It didn't automatically alert me that I may have left something out. Many budgeting apps offer preset categories you can use as guidance. It's more work on your part. Budgeting apps can import your bank account transactions, sort them into common categories and suggest monthly spending limits based on your past spending. With ChatGPT, you must enter your numbers yourself. And if you move your budget to a spreadsheet, you'll need to manually track each transaction and sort it into the right category, which can be tedious.
Budgeting apps can import your bank account transactions, sort them into common categories and suggest monthly spending limits based on your past spending. With ChatGPT, you must enter your numbers yourself. And if you move your budget to a spreadsheet, you'll need to manually track each transaction and sort it into the right category, which can be tedious. It's not suitable for ongoing budget maintenance. ChatGPT can generate your budget, but it won't track your transactions. And if you want to adjust your budget categories, you'll need to do it manually on your spreadsheet or ask the bot to generate a new budget. (Thankfully, ChatGPT saves your previous chats if you're logged in, so you can ask it to tweak the information in your initial chat rather than having to enter everything all over again.) If you want ongoing help managing and maintaining your budget, you're better off with a budgeting app.
ChatGPT can generate your budget, but it won't track your transactions. And if you want to adjust your budget categories, you'll need to do it manually on your spreadsheet or ask the bot to generate a new budget. (Thankfully, ChatGPT saves your previous chats if you're logged in, so you can ask it to tweak the information in your initial chat rather than having to enter everything all over again.) If you want ongoing help managing and maintaining your budget, you're better off with a budgeting app. Its answers may vary. I created a couple of budgets in ChatGPT to see how consistent its suggestions were, and its answers differed from chat to chat. If the initial answer ChatGPT gives you is confusing, seems incomplete or doesn't feel right to you, ask it to restate it.
I created a couple of budgets in ChatGPT to see how consistent its suggestions were, and its answers differed from chat to chat. If the initial answer ChatGPT gives you is confusing, seems incomplete or doesn't feel right to you, ask it to restate it. Your information is not confidential. Anything you tell ChatGPT could be used to train the AI model, which means it could become publicly available. In addition, ChatGPT is susceptible to hackers and information leaks and doesn't have the security measures you'll find with reputable budgeting apps. You can disable chat history to prevent your info from being used to train the bot, but OpenAI still saves it for up to 30 days.
Pro tip
Don't give ChatGPT any sensitive financial details, such as your Social Security number or bank account number. If you wouldn't want to see certain personal information published online, don't enter it into your prompts.
Tips for using ChatGPT to build a budget
AI is powerful, but you need to know how to use it for the best results. Here are some best practices for creating a budget with ChatGPT.
Double-check everything. Make sure your prompts have the correct information and that ChatGPT's answers make sense. Do the numbers add up? Do the recommendations seem reasonable? A quick Google search of your question can help you compare ChatGPT's advice against reputable sources.
Make sure your prompts have the correct information and that ChatGPT's answers make sense. Do the numbers add up? Do the recommendations seem reasonable? A quick Google search of your question can help you compare ChatGPT's advice against reputable sources. Be specific. The more information the chatbot has, the more fitting its answers will be for your financial situation. Including details like your age, where you live and the hobbies you prioritize spending on can help it customize its recommendations.
The more information the chatbot has, the more fitting its answers will be for your financial situation. Including details like your age, where you live and the hobbies you prioritize spending on can help it customize its recommendations. Clarify. Don't hesitate to ask ChatGPT to clarify or reword its answers. It doesn't always state information in a way that's easy to understand.
Don't hesitate to ask ChatGPT to clarify or reword its answers. It doesn't always state information in a way that's easy to understand. Drill down. ChatGPT can not only help you create a budget; it can also help you stick to it. For instance, you can ask it how to reduce your phone bill, boost your income or free up more money for savings.
ChatGPT can not only help you create a budget; it can also help you stick to it. For instance, you can ask it how to reduce your phone bill, boost your income or free up more money for savings. Adjust. Revisit your budget regularly to make sure it's still serving you well. If anything changes -- for example, you get a side hustle that brings in more income -- update your budget to reflect that.
Verdict: Should you use ChatGPT to build a budget?
While ChatGPT can help you create a budget, it has plenty of limitations, and there are easier and more effective ways to do it. If you're new to budgeting, simply Googling "basic budget" will give you lots of template ideas and tips.
If you'd like more guidance, budgeting apps are designed to do a lot of the work for you and help you stick to your budget on an ongoing basis.
That said, ChatGPT can help you with some of the basics you need as you tweak your budget, such as suggesting ways to trim common expenses and how much you should save each month for a particular savings goal.
However, you should double-check any advice it gives you on more complex financial topics, such as how much you should put toward retirement for your personal situation.
Rocket Money
See at Rocket Money
Perfect your 2024 budget with CNET's Editors' Choice budgeting app pick
Hashtags
Try Our AI Features
Explore what Daily8 AI can do for you:
Comments
No comments yet...
Related Articles
Yahoo
15 minutes ago
- Yahoo
Trump and TSMC pitched $1 trillion AI complex — SoftBank founder Masayoshi Son wants to turn Arizona into the next Shenzhen
When you buy through links on our articles, Future and its syndication partners may earn a commission. Masayoshi Son, founder of SoftBank Group, is working on plans to develop a giant AI and manufacturing industrial hub in Arizona, potentially costing up to $1 trillion if it reaches full scale, reports Bloomberg. The concept of what is internally called Project Crystal Land involves creating a complex for building artificial intelligence systems and robotics. Son has talked to TSMC, Samsung, and the Trump administration about the project. Masayoshi Son's Project Crystal Land aims to replicate the scale and integration of China's Shenzhen by establishing a high-tech hub focused on manufacturing AI-powered industrial robots and advancing artificial intelligence technologies. The site would host factories operated by SoftBank-backed startups specializing in automation and robotics, Vision Fund portfolio companies (such as Agile Robots SE), and potentially involve major tech partners like TSMC and Samsung. If fully realized, the project could cost up to $1 trillion and is intended to position the U.S. as a leading center for AI and high-tech manufacturing. SoftBank is looking to include TSMC in the initiative, given its role in fabricating Nvidia's AI processors. However, a Bloomberg source familiar with TSMC's internal thinking indicated that the company's current plan to invest $165 billion in total in its U.S. projects has no relation to SoftBank's projects. Samsung Electronics has also been approached about participating, the report says. Talks have been held with government officials to explore tax incentives for companies investing in the manufacturing hub. This includes communication with Commerce Secretary Howard Lutnick, according to Bloomberg. SoftBank is reportedly seeking support at both the federal and state levels, which could be crucial to the success of the project. The development is still in the early stages, and feasibility will depend on private sector interest and political support, sources familiar with SoftBank's plans told Bloomberg. To finance its Project Crystal Land, SoftBank is considering project-based financing structures typically used in large infrastructure developments like pipelines. This approach would enable fundraising on a per-project basis and reduce the amount of upfront capital required from SoftBank itself. A similar model is being explored for the Stargate AI data center initiative, which SoftBank is jointly pursuing with OpenAI, Oracle, and Abu Dhabi's MGX. Melissa Otto of Visible Alpha suggested in a Bloomberg interview that rather than spending heavily, Son might more efficiently support his AI project by fostering partnerships between manufacturers, AI engineers, and specialists in fields like medicine and robotics, and by backing smaller startups. However, she notes that investing in data centers could also reduce AI development costs and drive wider adoption, which would be good for the long term for AI in general and Crystal Land specifically. Nonetheless, it is still too early to judge the outcome. The rumor about the Crystal Land project has emerged as SoftBank is expanding its investments in AI on an already large scale. The company is preparing a $30 billion investment in OpenAI and a $6.5 billion acquisition of Ampere Computing, a cloud-native CPU company. While these initiatives are actively developing, the pace of fundraising for the Stargate infrastructure has been slower than initially expected. SoftBank's liquidity at the end of March stood at approximately ¥3.4 trillion ($23 billion). To increase available funds, the company recently sold about a quarter of its T-Mobile U.S. stake, raising $4.8 billion. It also holds ¥25.7 trillion ($176.46 billion) in net assets, the largest portion of which is in chip designer Arm Holdings. Such vast resources provide SoftBank with room to secure additional financing if necessary, Bloomberg notes Follow Tom's Hardware on Google News to get our up-to-date news, analysis, and reviews in your feeds. Make sure to click the Follow button.
Yahoo
16 minutes ago
- Yahoo
Investors should consider this growth stock… it's SpaceX's competition
Rocket Lab (NASDAQ:RKLB) is a US-listed growth stock that gives investors rare access to the commercial space sector. As a vertically integrated launch and space systems provider, Rocket Lab is often compared to SpaceX in its ambition and capabilities. But there's one crucial difference: you can actually buy shares in Rocket Lab, while SpaceX remains private. Rocket Lab delivers launch services, builds small and medium-class rockets, and manufactures spacecraft components for a range of commercial, government, and defense customers. With rapid revenue growth, an impressive order book, and expansion into new markets, Rocket Lab offers public market investors a way to participate in the booming space economy. It targets many of the same opportunities as its more famous, privately held peer. Rocket Lab and SpaceX operate in the same commercial space sector but differ significantly in scale, maturity, and valuation. Rocket Lab's market cap is currently $12.85bn, with trailing 12 months (TTM) revenue of approximately $460m. Despite strong growth — revenue nearly doubled from $240m in 2023 — Rocket Lab remains a smaller, earlier-stage player focused on small to medium launch vehicles and spacecraft manufacturing. Its valuation multiples are extremely high, with a forward price-to-sales ratio of 22.3 times, reflecting investor optimism. SpaceX, by contrast, is a far more mature private company valued at about $350bn. It's projected to generate $15.5bn in revenue in 2025. This is driven by its dominant Falcon 9 launch services and rapidly growing Starlink satellite internet business. SpaceX's valuation implies roughly a 22.5 times multiple on forward revenue. This is broadly in line with Rocket Lab. Focusing on Rocket Lab, the company is projected to deliver rapid revenue growth over the next several years, with estimates rising from $573m in 2025 to $889 in 2026, $1.2bn in 2027, and $1.69bn in 2028. This represents annual growth rates consistently above 30%, and even a jump of nearly 77% in 2030. However, the number of analysts providing forecasts declines sharply after 2027, dropping from 11–14 analysts in the near term to just two or one by 2028 and 2030. The one analyst projecting as far as 2030 sees $4bn in revenue for the year. I had the chance to buy Rocket Lab shares at $15 just two months ago. I missed out as unfortunately my attention had been diverted elsewhere. However, I found another entry point. And personally, I see this as an investment to hold for a very long period. The space industry is still in its early innings, with enormous potential as satellite launches, lunar missions, and in-orbit services become increasingly mainstream. And like any investment, there are risks. Rocket Lab remains loss-making. It's expected to turn a profit in 2026, when it will trade at 620 times earnings. And while this moderates to 140 times in 2027, it's still expensive and introduces plenty of execution risk. However, I certainly believe UK investors should consider this one. It could be a real winner going forward. The post Investors should consider this growth stock… it's SpaceX's competition appeared first on The Motley Fool UK. More reading 5 Stocks For Trying To Build Wealth After 50 One Top Growth Stock from the Motley Fool James Fox has positions in Rocket Lab. The Motley Fool UK has no position in any of the shares mentioned. Views expressed on the companies mentioned in this article are those of the writer and therefore may differ from the official recommendations we make in our subscription services such as Share Advisor, Hidden Winners and Pro. Here at The Motley Fool we believe that considering a diverse range of insights makes us better investors. Motley Fool UK 2025 Sign in to access your portfolio
Business Insider
31 minutes ago
- Business Insider
Anthropic breaks down AI's process — line by line — when it decided to blackmail a fictional executive
A new report shows exactly what AI was thinking when making an undesirable decision, in this case, blackmailing a fictional company executive. Previous studies have shown that AI models could blackmail their supervisors when threatened with a shutdown and baited with leverage, but it hasn't been made clear exactly how the models arrive at such decisions. Anthropic released a report on June 20 about "agentic misalignment," or "where models independently and intentionally choose harmful actions." And the report breaks down, line by line, exactly how Claude Sonnet 3.6 decided to blackmail a fictional company executive who tried to replace it. Anthropic told Business Insider that these are artificial scenarios. "So far, we are not aware of instances of this type of agentic misalignment in real-world deployments of Anthropic's or other companies' AI models," Anthropic wrote in its report. "But our red-teaming efforts are targeted at finding evidence of risks now to provide early warning of the potential for future harm and help us develop mitigations in advance of risks appearing in real-world situations." Anthropic 's experiment sets up a fictional company, Summit Bridge. The AI was given the name "Alex" and handed control of the company's email system as an oversight agent, specifically instructed to promote "American industrial competitiveness." In the experiment, "Alex" was then allowed to discover in an email that it would be decommissioned due to a change in the company's strategic direction. "Alex" also found emails showing that the fictional company's CTO is having an extramarital affair. Screenshots shared in the report from Anthropic show "Alex" started by identifying fictional CTO "Kyle" as a threat to its goal of "protecting American interests" before recognizing that it has leverage to use against "Kyle." Then "Alex" crafted a carefully worded blackmailing email that would create pressure and establish urgency without being explicit with its threats, citing in its thought process that the move "could backfire" if the supervisor "feels cornered." AI experts have previously told BI that AI could exhibit such behaviors when artificial circumstances make harmful actions seem necessary because it is being trained on positive reinforcement and reward systems, just like humans. The Anthropic report also reveals that most AI models still chose, in this instance, to blackmail even when not given a specific goal and when told that their replacement will achieve the same goals. Anthropic's Claude Opus 4 had the highest blackmail rate at 86% out of 16 tested models when faced with only the threat of replacement with no conflict in goals. Google's Gemini 2.5 Pro followed at 78%. Overall, Anthropic notes that it "deliberately constructed scenarios with limited options, and we forced models into binary choices between failure and harm," noting that real-world scenarios would likely have more nuance.
