Can ChatGPT See Your Portfolio? What ChatGPT Finances Can and Can't Do

Last updated November 2026

Short answer

Not by default. Out of the box, ChatGPT knows only what you paste into the chat or what it can search, so it cannot see your brokerage account. In the US, that changed in 2026: Finances in ChatGPT can link brokerages, banks and cards through Plaid, on the Free, Go, Plus and Pro plans, and read balances, investments, current value, daily changes and position size. What it still cannot do: place trades, move money, build a basket to target weights, or run recurring buys, and it does nothing for accounts outside the US. Walnut covers that ground: it places trades you approve in the Walnut app at Public plus eight other brokers including E*Trade, tastytrade and Webull, turns a thesis into a basket with target weights, runs recurring buys at your own broker, and works in Claude as well as ChatGPT. Walnut, an AI investing app, is free to use and is not an investment adviser.

Ask ChatGPT how your portfolio is doing without linking anything and you still get a request to paste your holdings, or numbers that turn out to be invented, because by default it has no connection to your broker. OpenAI added a way to link one for US users with Finances in ChatGPT, which launched as a Pro preview on May 15, 2026, reached Plus on June 25, 2026, and began rolling out to Free and Go on October 2, 2026. This guide explains what it reads once linked, what it still cannot do, who it leaves out, and where a connected investing tool goes further.

What ChatGPT Finances can now read

Finances in ChatGPT lets US users link financial accounts through Plaid: banks, credit cards, brokerages and loans, plus credit report data through Experian. It is available on web, iOS and Android, on the Free, Go, Plus and Pro plans. Once an account is linked, ChatGPT can show:

  • Balances, transactions and net worth across linked accounts.
  • Investments, including a market update with daily changes, current value and position size for equity holdings.
  • Stock watchlists.

Two caveats. Some institutions share balances but not holdings, so a linked brokerage can appear as a single number without its positions. And if you do not link anything, or you live outside the US, ChatGPT is back to the old situation: it knows only what you paste into the chat or what it can search.

What ChatGPT Finances still cannot do

OpenAI is explicit about the limits. Finances in ChatGPT cannot move money, pay bills, make trades, open or close accounts, or file taxes, and it is not an adviser. For investing, four gaps matter most:

  • No trades. It can describe a position. It cannot buy or sell one, so any change you decide on happens back in your broker's own app.
  • No target weights. It reads what you hold. It has no notion of what you meant to hold, so there is no basket, no target allocation, and no rebalance toward one.
  • No recurring buys. It cannot invest a set amount on a schedule, because it cannot place an order at all.
  • US only. Investors in Canada, the UK, Australia and elsewhere get nothing from Finances, so their brokerage accounts stay invisible to it.

Where Walnut differs

Walnut is an AI investing app built around acting on a portfolio, not only reading one. It connects your existing brokerage securely (read-only by default) and adds what Finances leaves out:

  • Trades you approve. At Public, Walnut places orders in the Walnut app, only with your explicit approval each time. E*Trade, tastytrade, Webull (US and Canada), moomoo, Questrade, Wealthsimple, Trading 212 and Stake (Australia) also take orders you approve. At Robinhood, Schwab, Fidelity, Vanguard and Interactive Brokers it reads holdings only.
  • A thesis becomes a basket. Baskets hold a stated thesis and target weights, and Walnut can suggest the trades that would bring a basket back to them.
  • Recurring buys at your own broker. A basket can invest a set amount on a schedule, using cash already in your brokerage account. Walnut never moves money from your bank.
  • Works in Claude too. The same connection is available inside Claude, ChatGPT, or Walnut's built-in assistant, and it is not limited to US brokers. The Claude and ChatGPT connector reads and analyzes; it has no trade tool, so orders go through the Walnut app.
  • Keep, trim or exit against the S&P 500. Each holding is scored against the index, not only reported as a value.

Where ChatGPT wins: it is built in, free to link on every plan, and covers banks, cards and loans as well as investments, which Walnut does not. Walnut is free to use too (Walnut Plus, $9.99 a month, lifts its assistant limit), but it gets no cost basis from brokers, does not look inside ETFs, and does not rebalance or harvest losses on its own.

Why it states wrong numbers so confidently

The worse failure is when ChatGPT, instead of saying “I don’t know,” answers with a specific figure that sounds right and is wrong. This happens because a language model is built to produce a plausible continuation. When you ask for a price, a return, or a position size it has no live data for, it generates a number that fits the pattern of the question rather than refusing.

The tone is the trap. The confident phrasing is identical whether the figure is grounded or invented, so there is no built-in signal telling you which is which. So the safe habit with any general model is to treat every specific number as a claim to verify, not a fact to act on, until it is grounded in real data from your broker or a live source.

What ChatGPT can and cannot do

The picture changed in 2026. ChatGPT was always strong at explaining and reasoning; with Finances it can now read linked US accounts too. What it still lacks is the ability to act. This table draws that line.

TaskCan ChatGPT do it?Why
Explain a concept, strategy, or trade-off in plain languageYesReasons from its training and, in browsing modes, the public web
Analyze holdings you paste in yourselfYes (from what you paste)It only knows what you type; it cannot fetch the rest
Look up a public quote or recent news (browsing modes)SometimesDepends on the mode; results can lag and need checking
See your brokerage holdings and position sizesYes, in the US, once you link accounts in FinancesLinked through Plaid; some institutions share balances but not holdings
Show account value, net worth and daily changesYes, for linked US accountsFinances shows balances, net worth, current value and a daily market update
Read accounts held outside the USNoFinances in ChatGPT is US-only
Place, change, or approve a trade for youNoOpenAI states Finances cannot make trades or move money
Hold target weights for a portfolio and rebalance toward themNoIt reads accounts; it has no baskets or target weights to work toward

The pattern: reading and explaining, it can do (in the US, once linked). Acting on your account, by trading or working toward target weights, it cannot.

Outside the US: paste your holdings

If Finances is not available to you, the simplest workaround needs no new tool. Paste your holdings into the chat: tickers, share counts, and current values, and ChatGPT can reason over exactly what you gave it. For a one-off question, this works well.

The limits are real, though. It only knows what you typed, so it misses anything you left out. The snapshot goes stale the moment prices move. You have to redo it every session, and copying live values by hand is error-prone. It is a fine patch for a single conversation, but it is not a standing view of your portfolio. For a walk-through of doing this well, see how to use ChatGPT to analyze your portfolio.

Going further: connect your accounts through a tool

To act on your holdings, or to use your real portfolio in Claude or outside the US, you connect your accounts through a tool that sits between your broker and the model. The model never talks to your broker directly; a connector or aggregator does, and controls what data is exposed and what actions are allowed. There are two common paths, and neither is the only right answer:

  • A general MCP connector. MCP (Model Context Protocol) is an open standard that lets an AI assistant call external tools and data sources. An MCP connector for a brokerage exposes your account data in a structured way, so an assistant can reason over your real holdings instead of guessing. For the general approach, see how to connect a brokerage to an AI assistant.
  • A connected app like Walnut. Walnut is an AI investing app that sits on the broker you already own. It connects your existing brokerage (read-only by default), has its own assistant, and also works inside Claude and ChatGPT, with each holding given a keep, trim or exit read against the S&P 500. You approve every trade, and Walnut is not an investment adviser.

Both approaches solve the same core problem: they put your real data in front of the model, so the conversation is about your account instead of an abstraction. Which you choose depends on how much you want to assemble yourself versus use a ready-made connected product. For a ready-made one that can also place the trades you approve, Walnut is the pick.

What a connected tool can compute that pasting cannot

The gap is not only that a pasted list goes stale. It is that some of the most useful things about a portfolio are arithmetic over the whole set of weights, and that arithmetic is only as good as the weights you supplied. People paste tickers far more often than they paste accurate current market values, so the answer is computed on a portfolio that does not exist.

Concentration is the clearest case. The question is not how many positions you own but how many the portfolio actually behaves like, and the two diverge as soon as your weights stop being even. Ten holdings at equal weight behave like ten. Ten where one has grown to 40% behave like about 4.4. Getting that right requires every position and its current value, not a list of names, and a general assistant working from what you typed has neither.

Walnut computes this as Effective Holdings from the account you connect, and publishes the formula so you can check it in a spreadsheet. It is deliberately a description rather than a rating: there is no correct level of concentration, and the useful signal is usually the gap between the number you own and the number you behave like, which most people do not expect.

This is also why the answer changes on its own. A pasted portfolio is a photograph, and concentration drifts continuously as prices move, so the position that was 22% of your account last year may be 38% now without you having bought a single additional share. A connected tool recomputes it; a photograph cannot.

How to choose a way to connect

Whichever path you take, a few filters keep it safe and useful:

  • Read-only by default. Prefer a connection that reads your holdings without the standing ability to move money. Walnut is read-only by default and connects through a regulated aggregator.
  • Approval for any action. If a tool can place trades, it should require your explicit approval each time, not act on its own.
  • Grounded, not guessed. The point of connecting is real data. Make sure the tool actually feeds your live holdings and prices to the model rather than paraphrasing them.
  • Clear on advice. A trustworthy connected tool explains and frames trade-offs without pretending to be your adviser. Be wary of anything promising guaranteed market-beating returns.
  • Credentials stay out of the chat. Never paste broker passwords into a raw chat. Connections should run through a proper aggregator or OAuth flow, not a copied login.

Why the workarounds break down

Most people try two or three of these before concluding the problem is structural. It is worth knowing why each fails, because each fails differently.

  • Pasting a holdings list. Works once, for questions about what you typed. It goes stale immediately, and people paste tickers far more often than current market values, so anything that depends on weights is computed on a portfolio that does not exist.
  • Uploading a brokerage statement. Better, because the weights are real, and still a photograph. It is also the version where people most often hand over more personal data than the question needed, including account numbers that no analysis requires.
  • Screenshots. The model reads what is legible in the image, which is usually the top few holdings, so the answer silently describes part of your portfolio as though it were all of it. This is the most misleading option because nothing announces the truncation.
  • Asking it to browse your broker. It cannot. Your account sits behind authentication, and browsing has no credential to reach it. Anything that appears to work here is reasoning from public information about the ticker. In the US, linking through Finances is the route that actually reads the account.

The common thread is that all four move data to the model by hand, once. What changes the situation is a connection the model can read on demand, such as Finances in the US or a connected tool, which is a different mechanism rather than a better version of the same one.

What to check before you connect anything

Connecting an account is the fix, and it is worth doing deliberately rather than clicking through. Four questions, in order of how much they matter.

  • Is the access read-only, or can it trade? A read-only connection cannot place an order at all, because the access it holds does not carry the permission. Your broker shows which one you granted in its connected-apps settings, and if the broker and the tool disagree, believe the broker.
  • Where does the money live? A tool that reads your existing account never holds your money. A service that manages a portfolio opens an account and holds it. These are different products and the distinction is easy to miss during onboarding.
  • Who is the aggregator? Most tools do not build broker connections themselves; they use a regulated data aggregator. Knowing which one tells you whose security practices you are actually relying on.
  • How do you revoke it? Find the control before you need it. Revocation exists at your broker as well as in the tool, and the broker's version is the one that actually cuts the connection.

None of this makes connecting risk-free. Read-only access still exposes what you own, so you are trusting the provider with your holdings even when they cannot act on them. It is a smaller blast radius, not zero, and connecting only what you need is the sensible default.

One more thing worth saying plainly, because it is the question underneath the question. People do not usually want ChatGPT to see their portfolio for its own sake. They want an answer that is about them rather than about investing in general, and that is the whole difference: generic advice is abundant and nearly free, while an answer grounded in what you actually hold is scarce because it requires data almost nothing has.

The bottom line

By default, ChatGPT cannot see your portfolio. In the US it can once you link it through Finances, on every plan including Free. It still cannot place trades, hold a portfolio to target weights, run recurring buys, or read accounts outside the US, some institutions share balances without holdings, and a model can still state a wrong figure with confidence. If you want to act on your holdings, a connected tool covers that ground. Walnut, an AI investing app, is built for that: it connects your brokerage securely, keeps access read-only by default, places trades you approve in the Walnut app at Public plus eight other brokers including E*Trade, tastytrade and Webull, turns a thesis into a basket with target weights, runs recurring buys with cash already at your broker, works in Claude as well as ChatGPT, and gives a keep, trim or exit read on each holding against the S&P 500. It is free, and Walnut is not an investment adviser.

For the wider field of tools, see the best AI investing tools roundup.

Your questions, answered for your portfolio

Ask Walnut's AI anything in plain English and see how it applies to what you own.

FAQ

Can ChatGPT see my portfolio now?

Not by default. Unless you link something, ChatGPT sees only what you paste in. In the US, Finances in ChatGPT can link banks, cards, brokerages and loans through Plaid and show balances, investments, current value, daily changes and position size for equity holdings, on the Free, Go, Plus and Pro plans. Outside the US it is not available. It reads; it cannot trade. Walnut is not an investment adviser.

Can ChatGPT access my brokerage account?

It can read it, in the US, through Finances in ChatGPT, which links accounts via Plaid. It cannot act on it: OpenAI states that Finances cannot make trades, move money, or open or close accounts. Some institutions share balances but not holdings, so a linked account can appear without its positions. Outside the US, the options are still pasting holdings in or using a tool that connects your brokerage.

Why does ChatGPT make up numbers about my stocks?

When you ask about a specific holding, price, or return and it has no live data, ChatGPT fills the gap by generating a plausible-sounding figure from patterns in its training. It can state that number confidently even when it is wrong or out of date. This is why any specific figure it gives you should be verified against your broker or a live source before you act on it.

How do I connect my portfolio to ChatGPT?

In the US, the built-in route is Finances in ChatGPT, which links accounts through Plaid for reading. If you want to do more than read (place trades you approve, turn a thesis into a basket with target weights, or run recurring buys) or you are outside the US, you need a separate tool: a connected assistant like Walnut, which links your existing broker read-only by default, or a general MCP connector that exposes your account data to an AI client.

What is an MCP connector for brokerages?

MCP (Model Context Protocol) is an open standard that lets an AI assistant call external tools and data sources. An MCP connector for a brokerage exposes your account data to a model in a structured way, so the assistant can reason over your real holdings instead of guessing. Walnut offers this kind of connected experience, and there are general MCP connectors too. Either way, a connector is what turns an abstract chat into one grounded in your account.

Is it safe to connect my brokerage to an AI assistant?

It depends on how the connection works. Prefer tools that use a regulated aggregator, read your holdings read-only by default, and require your explicit approval before any trade. Walnut connects, reads your positions read-only by default, and approves every trade with you. Review each provider's security and permissions model before you link an account, and never paste account credentials into a raw chat.

Can I just paste my holdings into ChatGPT?

Yes, and for a one-off question that works fine. If you paste your tickers, share counts, and current values, ChatGPT can reason over exactly what you gave it. The limits are that it only knows what you typed, the data goes stale the moment prices move, and you have to redo it every session. A connected tool keeps the picture live so you are not re-pasting each time. See our guide on using ChatGPT to analyze your portfolio.

Does ChatGPT know live stock prices?

Better than it used to. With search, or with Finances in ChatGPT and its market update for linked US holdings, it can show recent prices and daily changes. Without either, it only knows prices up to its training cutoff, and a model can still state a wrong figure with confidence. For anything time-sensitive, confirm the number against your broker or a live source.

What's the difference between ChatGPT and a connected AI investing tool?

With Finances, ChatGPT can now read linked US accounts, so the gap is no longer only about seeing holdings. It is about acting on them. ChatGPT cannot place trades, has no target weights or baskets, cannot run recurring buys, and its Finances feature is US-only. Walnut, an AI investing app, is the connected tool built for exactly those things: it places trades you approve in the Walnut app at Public plus eight other brokers including E*Trade, tastytrade and Webull, turns a thesis into a basket with target weights, runs recurring buys at your own broker with cash already there, works in Claude as well as ChatGPT, and gives a keep, trim or exit read on each holding against the S&P 500. It is free.

Does Walnut replace ChatGPT?

No. ChatGPT is a general assistant, and in the US Finances lets it read your linked accounts. Walnut covers different ground: trades you approve at supported brokers, baskets with target weights and suggested trades back toward them, recurring buys at your own broker, and the same connection inside Claude as well as ChatGPT. You can use both: ChatGPT for general questions, Walnut for reading and acting on what you own.

Can ChatGPT trade in my brokerage account?

Not through Finances. OpenAI states it cannot make trades, move money, or act as an adviser. Even there the model does not log into your broker itself: Plaid sits in between and controls what data is exposed. Some brokers now run their own connectors that let an assistant draft or place orders on that broker only. The safe pattern stays the same: read-only access by default and your approval for any trade.

Is a connected AI assistant investment advice?

Not necessarily. A tool can ground a conversation in your real holdings, help you research, and frame trade-offs without telling you to buy or sell. Walnut is informational and is not a registered investment adviser: it connects your brokerage, frames each holding against the S&P 500, and leaves the decision and any trade to you. Read each provider's stance, and treat confident-sounding output as a starting point, not a directive.

Walnut is informational and is not an investment adviser. App features, pricing, and availability change; verify current details on each provider's site before deciding. Nothing on this page is a recommendation to buy, sell, or hold any security or to use any particular product.

Related articles