Agentic trading: what it is and the platforms compared

Agentic trading is trading in which an AI agent, such as Claude or ChatGPT, uses tools to research markets, build strategies or place orders in an account on your behalf. You set the limits: which account it can reach, what it may do there, and what needs your approval.

By Keel Research Team · Updated November 17, 2026 · Platform facts as of November 17, 2026

The term covers two different products. In one, an AI agent is connected to a brokerage or exchange account and sends orders. Robinhood, Coinbase, Public and others offer this today, and the comparison below lists eleven of them. In the other, the agent writes a strategy once, and a fixed engine tests it and runs it. The risks are very different, so it is worth knowing which one a product means.

This page explains how agentic trading works, compares the platforms from their own pages, and shows where language models help in trading and where they fail. For the protocol most of these products use, see what is MCP.

How agentic trading works: the agent, the tools, the account, the guardrail

Every agentic trading setup has the same four parts. What differs between products is how much each part is allowed to do.

  1. The agent. An AI agent for trading is a model such as Claude or ChatGPT that can take steps on its own: look something up, call a tool, read the result and try again. You give it a goal in plain words.
  2. The tools. The agent can only do what its tools allow. Most platforms publish theirs over the Model Context Protocol (MCP), an open standard for connecting an AI application to outside tools. A tool might return a quote, read a portfolio, run a backtest or submit an order.
  3. The account. The tools act on an account you authorize. Some platforms use your main account, and some make you open and fund a separate one for the agent.
  4. The guardrail. A limit on what the agent can do without you: an approval before each order, a cap on cash or products, a paper or demo mode, or no order tool at all.

When you compare products, read the tools and the guardrail first. They decide what a wrong answer from the model can cost.

Agentic trading platforms compared

Eleven platforms that let an AI agent work in a trading account, in no ranked order. Each row states what the platform’s own page said when we read it on , and links that page. Coinbase’s page blocks automated readers, so its row cites the TechCrunch report of its launch. A cell reads “Not stated” when the source does not say. These products change quickly, so check the source before you rely on a row.

Agentic trading platforms compared, facts as of November 17, 2026
PlatformWhat the agent can doThe guardrailMarketsLaunched
Robinhood Agentic Trading
Source: robinhood.com, read
Connect your own AI agent over MCP to a dedicated Robinhood account. The agent can scan the market, review the portfolio, build watchlists and place trades.A separate account you fund for the agent. You review each trade before it is placed, and approvals are on by default.Not listed on the pageNot stated. Agent Loops, for continuous or scheduled runs, is listed as coming.
Coinbase for Agents
Source: techcrunch.com, read
An agent that places trades and pays for research, which also works from ChatGPT or Claude through Coinbase's MCP server.The agent can run in a separate sandbox. Custom limits such as a maximum trade size were described as coming.Crypto spot and derivativesJune 11, 2026
Alpaca MCP Server
Source: alpaca.markets, read
Pull live or historical market data and place orders in plain language from clients such as Claude, ChatGPT and Cursor.Paper trading with simulated funds. Going live is a change of API keys. The page says you see every prompt, parameter and order payload before anything goes to market.US stocks, ETFs, options and cryptoNot stated
Public
Source: public.com/mcp-trading, public.com/ai-agents, read
Connect Claude, ChatGPT or Perplexity over MCP to read the portfolio and place trades. In-app Agents monitor markets, place trades and manage cash on rules you set.Dedicated brokerage accounts for MCP connections. Inside one, the agent can trade without your input on each transaction. Each in-app Agent needs your sign-off before it runs.Stocks, ETFs, options, crypto and bonds over MCP. Stocks, options and crypto for in-app Agents.Not stated
Interactive Brokers
Source: interactivebrokers.co.uk, read
Connect ChatGPT, Claude, Grok, Perplexity and other MCP clients for research, portfolio analysis and preparing trade instructions. IBKR Autonomous Trading lets eligible clients authorize an AI to place supported trades on criteria they set.By default you review and submit every order yourself. Autonomous Trading runs only inside a dedicated AI Partition, which limits the cash, products and trading authority the AI gets.Autonomous Trading covers eligible stocks and equity optionsNot stated
Kraken CLI
Source: docs.kraken.com, read
A command-line tool with a built-in MCP server that gives an agent Kraken's trading and account commands.A paper trading engine that runs on live prices. Login saves a restricted API key with no withdrawal rights and an expiry date.Crypto spot, tokenized stocks, forex, and perpetual and dated futuresNot stated
OKX Agent Trade Kit
Source: okx.com, read
An open-source MCP server and command-line tool for Claude, Cursor, VS Code and other MCP clients: market data, orders, and grid and DCA bots.A demo mode with simulated assets. If the API key has no trading permission, the order tools are never given to the agent.Spot, perpetual swaps, futures and optionsMarch 10, 2026
Binance Skills Hub
Source: binance.com, read
“An open skills marketplace giving AI agents native access to crypto”: skills for exchange trading, on-chain swaps, wallet operations and market data.Skills are security-reviewed before listing, and the trading skill requires authentication.Binance spot, futures and Convert, plus on-chain swapsNot stated
Gemini Agentic Trading
Source: gemini.com, read
The full Gemini trading API over MCP, so Claude, ChatGPT or another AI can place trades, monitor markets and manage risk.Not described in the announcementCrypto. The announcement lists no specific markets.April 27, 2026
TradeStation Institutional
Source: tradestation.com, read
Connect Claude, ChatGPT and other assistants to a brokerage account over MCP to pull historical data, run analysis and build multi-leg orders in conversation.“No trade executes without your explicit approval.”Equities, options and futuresNot stated
tastytrade MCP server
Source: developer.tastytrade.com, read
An open-source MCP server you host yourself: market data, account data, and placing, replacing and cancelling orders.An order needs a dry run first, then a single-use confirmation token that lasts 60 seconds. A sandbox environment holds no real money.Options are covered in detail. The page gives no full list.Not stated

Read down the guardrail column and one pattern repeats. Each of these products gives an agent an account and a way to send an order, then limits the damage in one of three ways: a separate account that holds only what you assign, an approval before each order, or a cap on what the agent may trade. The model still decides each trade in the moment. The guardrail limits what a wrong decision can cost. It does not let you test the decision before it is made.

Keel is not in the table because it gives the agent no order to send. That design is the next section. For connectors that bring charts and market data to an agent, see MCP servers for trading, and for projects you run yourself, see open-source AI trading agents.

The other design: the agent writes the strategy, an engine runs it

There is a second way to use an agent, and it needs no guardrail on orders because the agent never sends one. The agent writes a strategy once: which coins, what signal, how big each position is, how often to rebalance. A fixed engine then tests that strategy over past data. If you start it, the engine runs it as written, the same way every time, with no model in the loop.

This is what Keel does. Keel is a strategy builder for Hyperliquid. Through Keel’s Hyperliquid MCP an agent such as Claude or ChatGPT can search the building blocks, write a strategy, backtest it on Hyperliquid data and compare versions, all in one conversation. It has no tool that sends orders. When a strategy is ready, the agent gives you a link to it in the Keel app, and you start it there yourself.

An agent that places orders compared with an agent that writes the strategy
The agent places ordersThe agent writes the strategy
Who decides each tradeThe model, in the momentRules you approved, on a schedule
Can you test it firstRarely. Its choices depend on the prompt and the dayYes. The same rules run over past data with fees, slippage and funding
What you can readIts explanation after the factEvery block and setting, before it runs
What limits a mistakeA separate account, an approval or a capThe agent has no order to send. You start the strategy yourself

The second design has its own limit. The agent can still propose a bad strategy, and a backtest cannot prove a good one. What changes is where the mistake shows up: in a result you read before any money moves, not in a position.

Where LLMs help in trading, and where they fail

Language models are sharp at work that has many valid answers: prose, putting code together, refactoring, summarizing, explaining what something does. They make things up on work that has one correct answer: arithmetic, exact state, accounting. Trading has both kinds. Composing a thesis (which signals to combine, what regime to gate on, what volatility to target) is the soft side. There are many reasonable answers, and a good model iterates quickly. Computing P&L is the hard side. There is exactly one correct answer, and a model that invents a fill price is breaking your execution.

That split explains the failures you see when a model sits in the trading loop:

  • A made-up number becomes a position. The model produces a trade the math does not support, and the order goes out.
  • The same prompt gives two answers. Ask twice and the decision can differ, so there is no record of how its choices would have done before you funded it.
  • Costs are easy to miss. Funding on a perpetual, fees and slippage are exact bookkeeping, which is the kind of work a model gets wrong.
  • A script per strategy drifts. When the model writes one-off code that calls a broker API, small differences between the research script and the live script (how prices are read, how funding accrues) make live results diverge from the test.

The builder design lines up with the split: soft work to the model, exact work to the engine. To see what happens when models trade for themselves in public, read the recap of the Alpha Arena AI trading contest. For how the models differ from each other, see LLM trading with Gemini, Grok and DeepSeek.

How agentic trading works with a tested rule

An AI trading agent is a model such as Claude or ChatGPT that can use tools: search for components, run a backtest, read the result. In agentic trading on Keel, you connect your agent to Keel and ask it for a strategy in plain words. It builds the strategy from Keel’s blocks, so every rule is one you can read, and Keel runs the backtest on real Hyperliquid data with fees, slippage and funding charged.

  1. Ask. Describe the idea to your agent: what to trade, when to get in, when to get out. It picks the blocks and puts the strategy together.
  2. Test. The agent runs the backtest on Keel and gives you a link to the result in the Keel app, where you read the rules and the numbers yourself.
  3. Paper trade. Start the strategy on paper against live Hyperliquid prices, with no wallet, and watch how it behaves.
  4. Go live from your own account. Your funds stay in your Hyperliquid account. Keel trades through an agent wallet that can place trades but can never withdraw, and you can revoke it whenever you like.
  5. The rule trades, not the agent. Once live, the tested strategy runs on its own schedule and acts at the close of each bar. Your agent can be closed.

Keel works with Claude, ChatGPT and other MCP clients. The setup and a prompt to start from are on the page about an AI agent for trading on Hyperliquid.

A worked example

A user asks an MCP client (Claude Code, Cursor or Codex, any of them) to build a funding-carry strategy with a funding-level regime gate and backtest it. The agent searches the component library, finds the carry signal and the regime component, composes the strategy, submits it with keel_strategy_compose and starts keel_backtest_run.

The engine runs it on Hyperliquid perps with fees, slippage and funding charged, and returns the Sharpe, return and drawdown. For a run anyone can open, see funding carry in the strategy library, whose page shows its published backtest.

The point: the agent did not compute the Sharpe. The agent composed the strategy, and the engine computed the result from the saved strategy. Run the same strategy again and you get the same result. The agent’s work can be read, repeated and separated from the math.

A backtest shows how the rules behaved in the past. It is not proof that a strategy is ready for live capital. See the robustness checklist for what to check before you deploy, and trading prompts that end in a backtest for prompts to start from.

What agentic trading does not promise

Some pitches claim more than any of the designs above delivers:

  • “AI portfolio manager.” A model deciding on your funds with no tested strategy underneath is the setup the guardrails exist for. In the builder design the manager is the strategy, not the model.
  • “Set and forget.” Strategies need watching even with no model in the loop. Markets change, and a strategy that worked in a backtest can degrade live.
  • “No testing needed.” Describing an idea in plain words is a fine way to start and a poor place to stop. Related ideas have their own pages: vibe trading, an AI trading bot and the best AI trading software.

What Keel ships: a backtest engine on Hyperliquid history with fees, slippage and funding, typed building blocks that an agent composes over MCP, and trading from your own Hyperliquid account through an agent wallet that can place trades but can never withdraw.

Try it: connect an AI agent to Keel

To try the builder design yourself, the install for Claude Code is two commands:

pipx install keel-trade
claude mcp add keel -- keel mcp serve

The first command installs the keel-trade command-line tool from PyPI. The second registers it with Claude Code. The first call opens a sign-in at app.usekeel.io. After that, the agent can search components, compose strategies, run backtests, summarize results, and copy and compare versions.

For setup in other clients and prompts to start from, see the Keel MCP product page, ChatGPT for trading and build a trading bot with Claude on Hyperliquid.

This article is educational and is not investment advice. The platform comparison states what each source said on November 17, 2026 and may be out of date. A passing backtest is not a guarantee of live performance. Before deploying a strategy, see the robustness checklist. Reference: the Model Context Protocol specification at modelcontextprotocol.io.
Automate it

Trade systematically on Keel

Keel is a strategy builder for Hyperliquid. Describe an idea, backtest it with fees, slippage and funding, and run it live on Hyperliquid’s crypto perps. Stock and index perps are coming soon.

Start free. Connect a Hyperliquid wallet when you’re ready to trade.

What you can do
  • Backtest any strategy with realistic fees, slippage, and funding.
  • Change a parameter and run it again. Every backtest is kept.
  • Run it live on Hyperliquid with stop-losses and leverage caps.
  • Start from a sentence. Describe your idea and Keel builds a strategy you can test.
FAQ

Agentic trading questions

What is agentic trading?

Agentic trading is trading in which an AI agent uses tools to do part of the work for you: research, building a strategy, or placing orders in an account. The term covers two designs. In one, the agent is connected to a brokerage or exchange account and sends orders, usually inside a guardrail such as a separate account or an approval step. In the other, the agent writes a strategy once and a fixed engine tests it and runs it, so no model decides a trade in the moment. Keel is built the second way.

What is an AI trading agent?

An AI model, such as Claude or ChatGPT, that can use tools to do work for you rather than only answer questions. For trading, the useful work is building a strategy, running a backtest and explaining the result. On Keel the agent does that design work, and the tested strategy is what trades, at the close of each bar, from your own Hyperliquid account.

Is agentic trading safe?

It depends on what the agent is allowed to do. An agent that can send orders turns a wrong answer into a real position, which is why the platforms that allow it add a guardrail: a separate account funded with only what you assign, an approval before each order, or a cap on what it can trade. A guardrail limits the size of a mistake. It does not stop one. With Keel the agent has no tool that sends orders and cannot withdraw funds, and the strategy it wrote is backtested before you decide to run it. A backtest shows how rules behaved in the past and is not a guarantee, so any strategy can still lose money.

Which AI agent is best for trading?

There is no single best one, because the agent is only half of the setup. Claude, ChatGPT and similar assistants are general agents, and what they can do in a market depends on the tools you connect them to. Compare platforms on three things: what the agent can do, what guardrail limits it, and which markets it reaches. The table on this page lists those for eleven platforms, each with its source. If you want an agent to build a strategy and test it before anything trades, that is what Keel is for.

Can an AI agent trade crypto?

Yes. Coinbase, Kraken, OKX, Binance and Gemini each offer a way to connect an AI agent to a crypto account, and Alpaca and Public include crypto beside stocks. On Keel an agent builds and backtests strategies for Hyperliquid's crypto perpetuals. The strategy you approve then trades from your own Hyperliquid account on a fixed schedule, and the agent places no orders.

How is agentic trading different from a trading bot?

A trading bot runs fixed rules that someone wrote in advance, and it does the same thing every time. In agentic trading a model chooses what to do through tools, so it can research, adapt and explain, and it can also be wrong in ways fixed rules are not. The two meet when an agent writes the rules: the agent does the building, and what runs afterward behaves like a bot you can read and backtest.

Does the agent need to be online while my strategy trades?

No. Once a strategy is built and started, it runs on Keel on its own schedule. The agent does not need to be open, connected or installed. A model in the trading loop adds delay, cost and a chance of a made-up answer on every decision, so Keel keeps the model out of that loop.

How do I get started?

Two commands. pipx install keel-trade installs the Keel command-line tool from PyPI, and claude mcp add keel -- keel mcp serve registers it with Claude Code. The first call opens a sign-in at app.usekeel.io. After that the agent can search components, build strategies, run backtests and summarize results. Setup for other clients is at usekeel.io/docs/getting-started.