ChatGPT as a trading agent: dividends, tested

Follow this worked strategy

I connected ChatGPT to the NexusTrade trading API and had it research S&P 500 dividend growers and test a five-company allocation across two recorded periods. The agent operated this workflow through NexusTrade's MCP server; it did not build the integration. The 2025 test returned 44.80% against SPY at 33.99%, while the long 2014 run trailed SPY 340.90% to 419.23%. These are development tests on examined dates. Judge frozen rules on dates you have not used yet.

Follow the full journey

Step 1 of 6

Connect ChatGPT

https://nexustrade.io/api/mcp

Connect ChatGPT in the intended environment

On ChatGPT web, open Plugins → Add → Add custom MCP server. Name it NexusTrade, enter https://nexustrade.io/api/mcp and choose OAuth. Review the notice, select I understand and want to continue, then Create as a plugin. Finish NexusTrade sign-in. Open the plugin’s details and choose Try in chat.

What you should see

The result identifies Apple's company filing, filing date and source URL. The connection check makes no account changes.

Inspect the request

Use NexusTrade’s sec_edgar tool with action list_filings, ticker AAPL and limit 1. Report the company, filing form, filing date and source URL from the result. Use only this public read. Do not access portfolios, ingest filings, create resources or make changes. If the tool is unavailable, say so.

Step 2 of 6

Research the dividend-grower universe

Inspect which S&P 500 companies satisfy ten years of annual dividend increases, then rank qualifying companies by market cap. The eligible universe and actual holdings are separate records.

What you should see

A dated brief names the instrument, original sources and assumptions that matter to this strategy.

Inspect the request

Research the S&P 500 dividend-grower universe for the saved DynamicRebalance rule. Explain annual dividend-growth coverage, market-cap dates and missing values. Distinguish eligible companies from the actual selected five and historical membership assumptions. Keep the universe dynamic.

The dividend strategy's universe, filter, ranking, equal weights and rebalance trigger in NexusTrade — NexusTrade's strategy display renders the exact saved dividend rules used by this recorded simulation.

Step 3 of 6

Preview the five-company allocation

Filter the S&P 500 universe for ten annual dividend increases, select the five largest qualifying companies by market cap and target equal weights. Review the saved elapsed-time trigger.

Allocation trigger: Review allocations when portfolio value equals its initial value OR at least 30 days have passed since a filled buy. This is not an exact monthly schedule.
Equal weights: Each selected company has the same weight: five qualifying companies would target 20% each before execution effects.
Execution assumptions: Fractional shares and reinvested dividends; the original stock fee was 0.1% per transaction.

What you should see

The DynamicRebalance preview retains the universe, filter, ranking, weights and filled-buy timing trigger.

Inspect the request

Use build_portfolio to preview this exact Five dividend growers configuration. Show the entry, sizing, exits, valid and issues. After I approve the rules, use create_portfolio once to save a new draft, then read it back and retain its returned ID. Keep this candidate separate from published research portfolios. Stop before submitting a paid test or deploying.

{
  "initialValue": 10000,
  "supportsFractionalShares": true,
  "dividendPolicy": "reinvest",
  "strategies": [
    {
      "active": true,
      "condition": {
        "lhs": null,
        "rhs": null,
        "comparison": null,
        "type": "Or",
        "conditions": [
          {
            "lhs": {
              "compound": false,
              "targetAssets": [],
              "type": "PortfolioValue"
            },
            "rhs": {
              "compound": false,
              "targetAssets": [],
              "type": "InitialValue"
            },
            "comparison": "equal",
            "type": "Base"
          },
          {
            "lhs": {
              "compound": false,
              "targetAssets": [],
              "side": "Buy",
              "type": "DaysSinceOrder",
              "orderStatus": "Filled"
            },
            "rhs": {
              "compound": false,
              "targetAssets": [],
              "value": 30,
              "type": "Value"
            },
            "comparison": "greaterThanOrEqual",
            "type": "Base"
          }
        ]
      },
      "action": {
        "type": "DynamicRebalance",
        "universe": {
          "source": "SP500"
        },
        "pipeline": [
          {
            "type": "Filter",
            "condition": {
              "lhs": {
                "compound": true,
                "targetAssets": [],
                "type": "ConsecutiveIncrease",
                "maxLength": 1,
                "period": "Year",
                "lookback": 10,
                "indicators": [
                  {
                    "compound": false,
                    "targetAsset": {
                      "type": "",
                      "symbol": ""
                    },
                    "targetAssets": [],
                    "type": "LastDividend"
                  }
                ]
              },
              "rhs": {
                "compound": false,
                "targetAssets": [],
                "value": 10,
                "type": "Value"
              },
              "comparison": "greaterThanOrEqual",
              "type": "Base"
            }
          },
          {
            "type": "SelectTop",
            "metric": {
              "compound": false,
              "targetAsset": {
                "type": "",
                "symbol": ""
              },
              "targetAssets": [],
              "type": "Fundamental",
              "metric": "marketCap"
            },
            "limit": 5,
            "direction": "Highest"
          }
        ],
        "weightIndicator": {
          "compound": false,
          "targetAssets": [],
          "value": 1,
          "type": "Value"
        },
        "deploymentPercent": {
          "compound": false,
          "targetAssets": [],
          "value": 100,
          "type": "Value"
        }
      },
      "orderExecution": {
        "type": "Market"
      },
      "automaticOrderApproval": false
    }
  ]
}

Portfolio value (USD)

Five dividend growers 2026-10-07: $14,479.88
SPY buy and hold 2026-10-07: $13,399.03

Five dividend growers: 22.41% largest decline in plotted observations. 2025-02-13 ($10,415.39) to 2025-04-08 ($8,081.82).

Five dividend growersSPY buy and holdHistorical simulation

Recorded 2025-01-02 through 2026-10-07 dividend-grower simulation; $10,000 initial capital.

Step 4 of 6

Inspect the completed dividend tests

The recorded January 2, 2025 through October 7, 2026 test uses fractional shares, reinvested dividends and a 0.1% stock fee. Inspect the longer period below before choosing a new test window.

Strategy return: 44.80%
SPY return: 33.99%
Maximum drawdown: 24.33%
Strategy fees: $24.15

What you should see

The shorter simulation returned 44.80% versus SPY 33.99%. The longer period returned 340.90% versus SPY 419.23%.

Inspect the request

Prepare the matching historical test for my dividend-grower draft: 2025-01-02 through 2026-10-07, Day interval, $10,000, reinvest dividends, fractional shares, SPY baseline and 0.1% stock fee per transaction. Show the request and estimated cost before submission. Keep DynamicRebalance and the original universe. Inspect holdings after each filled rebalance, missing history and historical S&P 500 membership assumptions.

Step 5 of 6

Observe Five dividend growers in paper trading

Observe which five companies the unchanged dynamic pipeline selects now. Inspect the actual rebalance and fill history when the initial-value or 30-day-since-filled-buy trigger is satisfied.

Inspect before accepting an order: Eligible universe versus selected holdings, equal-weight targets, fractional fills, dividend reinvestment and actual trigger timing.

What you should see

Your paper portfolio has its own ID, start date, schedule and dated history. These forward observations begin with your own run.

Inspect the request

Read back the reviewed Five dividend growers draft. Prepare a separate paper-only deployment with the same rules and $10,000 starting capital. Show the plan for approval. Retain the resulting paper ID and verify its deployment type, timing, pending simulated orders and actual history. Inspect: Eligible universe versus selected holdings, equal-weight targets, fractional fills, dividend reinvestment and actual trigger timing. Keep the rules fixed and brokerage accounts unchanged.

Step 6 of 6

Review Five dividend growers for live deployment

Review the live target for fractional equity support, universe eligibility and reinvestment settings before accepting the copied dynamic allocation.

Open the live deployment walkthrough

Account and instrument review: Fractional equity support, each selected company, target weights, buying power, dividend policy and elapsed-time trigger.

What you should see

The review identifies the target account, supported instruments, rule changes and approval settings before confirmation.

Inspect the request

Prepare a live deployment review for my Five dividend growers paper portfolio. Read the actual account and broker capabilities, incoming rules and any existing rules that would be disabled. Check: Fractional equity support, each selected company, target weights, buying power, dividend policy and elapsed-time trigger. Show the plan and keep live trading unchanged until I explicitly confirm it. If an instrument or action is unsupported, report it and stop.

Follow the ChatGPT session

This guide runs on NexusTrade's MCP server. ChatGPT operated the trading workflow below, from connection to the live review. The agent's role here is operating the workflow through that server.

The table names the tool call, the approval checkpoint, and the artifact to keep at each stage. Placeholders such as a returned draft ID stand for values your own run returns. This page records no IDs from anyone else's run.

The recorded anchor is the two recorded periods below. The long 2014 run returned 340.90% against SPY at 419.23%.

Show the table · 6 rows, 4 columns

Filter rows

Scroll sideways to compare all columns. Select a heading to sort.


Connect ChatGPT	sec_edgar list_filings for AAPL with limit 1	Public read only. No portfolios, ingested filings, or changes.	Filing company, form, date, and source URL
Research the universe	S&P 500 dividend-growth coverage and market-cap ranking	Eligible companies stay separate from the selected five.	Dated universe brief
Draft the rules	build_portfolio preview, then one create_portfolio	Approve the rules before saving. Stop before paid tests.	Returned draft ID with a readback
Test history	Historical test from 2025-01-02 to 2026-10-07 at $10,000 with an SPY baseline	Show the request and estimated cost before submission.	Holdings after each filled rebalance
Trade on paper	Separate paper-only deployment at $10,000	Show the plan. Verify the portfolio is paper.	Running paper ID and dated history
Review live	Live deployment review against the actual account	Live trading stays unchanged until explicit confirmation.	Reviewed plan, or a stop report when unsupported

Where ChatGPT stops for approval

Each consequential action in this guide waits at an approval gate. The agent previews first and acts only after explicit approval.

The rules preview returns valid and issues before anything is saved. The agent resolves problems and re-previews instead of saving a candidate with open problems.

Approve the rules before the agent saves them
The agent previews the configuration with build_portfolio and shows entry, sizing, exits, valid, and issues. It saves with create_portfolio only after approval and reads the returned draft back.
Approve the test cost before the agent submits once
Historical tests are paid runs. The agent shows the exact request and estimated cost for approval before submitting once, then polls the same returned test ID until complete.
Approve the paper plan and verify it is paper
The paper deployment is a separate portfolio with its own ID. The agent shows the plan for approval, verifies the deployment type, and leaves brokerage accounts unchanged.
Confirm the live move explicitly, or nothing moves
The agent reads the actual account and broker capabilities first and keeps live trading unchanged until explicit confirmation. It reports an unsupported instrument or action and stops.

Inspect the longer recorded period

Portfolio value (USD)

Five dividend growers 2026-10-07: $44,089.69
SPY buy and hold 2026-10-07: $51,922.83

Five dividend growers: 22.80% largest decline in plotted observations. 2014-11-21 ($10,674.15) to 2015-08-25 ($8,240.24).

Five dividend growersSPY buy and holdHistorical simulation

Inspect the 2014 through 2026 curve

Strategy return: 340.90%
SPY return: 419.23%
Maximum drawdown: 24.16%
Strategy fees: $331.98

Recorded historical simulation: Jan 02, 2014 to Oct 07, 2026. Initial capital was $10,000.

These examined periods are development evidence. Historical S&P 500 membership at each date is not established by this receipt; the 2014 run is a retrospective simulation rather than proof of an investable selection.

The long-period chart pairs the allocation with SPY buy and hold on the same $10,000 starting basis. Historical S&P 500 membership at each date remains an open scope limit in the recorded receipt.

Compare the other recorded periods

Scale: 0 to 340.9 % · zero baseline

Strategy return

2025-01-0244.80%
2022-01-03134.94%
2014-01-02340.90%

Scale: 0 to 419.23 % · zero baseline

SPY baseline

2025-01-0233.99%
2022-01-0373.13%
2014-01-02419.23%

Scale: 0 to 24.33 % · zero baseline

Native max drawdown

2025-01-0224.33%
2022-01-0324.16%
2014-01-0224.16%

Scale: 0 to 422 · zero baseline

Closed trades

2025-01-0249
2022-01-03153
2014-01-02422

Scale: 0 to 331.98 USD · zero baseline

Strategy fees

2025-01-02$24.15
2022-01-03$103.47
2014-01-02$331.98

Show the table · 3 rows, 6 columns

Filter rows

Scroll sideways to compare all columns. Select a heading to sort.


2025-01-02	44.80%	33.99%	24.33%	49	$24.15
2022-01-03	134.94%	73.13%	24.16%	153	$103.47
2014-01-02	340.90%	419.23%	24.16%	422	$331.98

The same rules also have completed runs starting in 2022 and 2014. Compare the full period table before selecting a variant; the long 2014 run returned less than SPY.

Inspect the full existing strategy and configuration ↗Review the exact dividend strategy in Aurora ↗

Continue exploring

All AI clients ↗Live deployment ↗

Discussion

No comments yet.

I connected ChatGPT to a trading API and tested a dividend strategy

Follow this worked strategy

Follow the full journey

Connect ChatGPT

Connect ChatGPT in the intended environment

Research the dividend-grower universe

Preview the five-company allocation

Inspect the completed dividend tests

Observe Five dividend growers in paper trading

Review Five dividend growers for live deployment

Follow the ChatGPT session

Where ChatGPT stops for approval

Approve the rules before the agent saves them

Approve the test cost before the agent submits once

Approve the paper plan and verify it is paper

Confirm the live move explicitly, or nothing moves

Inspect the longer recorded period

Compare the other recorded periods

Strategy return

SPY baseline

Native max drawdown

Closed trades

Strategy fees

Continue exploring

Discussion

Try this in Aurora