PANews contributor Biteye tested Binance’s newly launched Binance Intelligence suite, with the main focus on Binance AI Pro, the version designed for more advanced users.
As described in the article, Binance Intelligence has three layers. Binance AI is positioned for general users and can generate briefs covering crypto, U.S. equities, and macro markets, while adjusting content based on a user’s behavior, preferences, and holdings. Binance AI Pro is built for users who want to describe trading ideas in natural language and convert them into automated workflows. Agent OS is aimed at developers who want external AI agents to connect to Binance data and trading capabilities.
How Binance presented AI Pro
According to the article’s account of the launch event, Binance CEO Richard Teng and Vice President of Product Jeff Li said users only need to describe a trading idea in a single sentence, and AI Pro can organize that input into a workflow. The user can revise it, simulate it, and decide afterward whether to deploy it in live trading.
The article says “workflow” was one of the most frequently repeated terms during the presentation. Users can tell the AI when to open a position, which indicators to watch, and how to manage position sizing. AI Pro then breaks those conditions into a strategy framework. After generation, the strategy can still be edited, tested in paper trading, and then either kept in simulation or moved into live execution. Binance summarized the process as “Prompt, Test, Trade.”
The event also showed non-trading use cases, including automatic market daily reports and persistent BTC monitoring with alerts at key price levels.
Test case one: using AI Pro to choose Binance Earn products
Biteye wrote that this review did not repeat basic market and data queries that earlier Binance AI versions and the ChatGPT plugin had already handled. Instead, the first test focused on a more practical scenario. Since the new AI Pro is connected to Binance Earn, the author asked:
“I have 50 BTC and want to put it into Binance Earn to generate yield, but I do not want to take principal loss risk. How would you allocate it? Please prioritize options with relatively high current yield and relatively low risk.”
According to the article, AI Pro directly called current Binance Earn product data and could also read the author’s real account balance. Because the account actually held only a small amount of BTC, the system proactively responded: “You currently do not have 50 BTC in your spot account. If you really want to execute this, you would first need to transfer BTC into the account.”
On product selection, AI Pro understood the core constraint and excluded products such as dual investment that could change the BTC amount held. It prioritized BTC flexible and fixed-term products instead. The article says it found a BTC flexible product with an APR of about 0.26%, along with a special 5-day fixed-term promotional product with up to 20% APR. Biteye wrote that this was broadly consistent with what later appeared on the Earn page.
Test case two: building a BTCUSDT perpetual long strategy
The second round centered on what the author called AI Pro’s core feature: strategy creation. Instead of using a simple “buy the breakout” instruction, Biteye combined several conditions typically used in perpetual futures trading to see whether the system could still parse the logic cleanly once the setup became more complex.
The prompt used in the test was:
“Help me create a BTCUSDT perpetual long strategy: 1h and 4h are both above MA20; 15m reclaims MA20 and trading volume is above 1.3x the average of the past 20 candles; open a position when 1h OI growth exceeds 5%, aggressive buy-sell ratio is greater than 1, and funding rate is below 0.01%. Position size 10%, 2x leverage, stop-loss 1.5%, take-profit 3%. Generate the strategy first, not for live trading.”
The author said the result was better than expected. AI Pro broke the logic into a fairly complete structure: 1h and 4h were used to determine the broader trend, 15m was used for entry timing, turnover confirmed expansion in activity, OI and the aggressive buy-sell ratio were used to judge whether capital participation was moving in the same direction, and funding was used to filter out overheated conditions.
The article also says the system handled execution details well. For example, when the prompt specified a “10% position,” AI Pro proactively clarified whether that referred to notional exposure or margin allocation. Parameters not explicitly stated in the prompt, such as isolated margin, one-way position mode, and checking frequency, were also surfaced for confirmation before the strategy moved forward.
Once confirmed, the strategy could be placed into paper trading. Biteye said the BTCUSDT setup was sent into simulated trading so the system could keep checking market conditions against the strategy in real time. That made it possible to observe whether triggers would fire as intended and whether any logic or parameter issues appeared before live use. At the time of writing, the article says the strategy was already running in simulation, with any move to live trading left for later if performance stayed stable and the trigger behavior matched expectations.
The author’s overall takeaway
In the closing section, Biteye wrote that the two tests left a better impression than expected.
The author said that, after looking into AI trading earlier, one conclusion had become clearer: AI is well suited to tasks such as monitoring markets around the clock, checking data, waiting for conditions, and executing strategies. People get tired and distracted, the article says, while AI does not. It also notes that more trading tools have recently started moving in the direction of AI agents.
The piece adds that Binance has a clear advantage here because of its market depth, large user base, and large amount of first-hand trading data. Many third-party AI products still need to connect data feeds, user accounts, and trading interfaces on their own. Binance, by contrast, can place AI directly inside an existing trading system.
Biteye’s final conclusion was: “AI has started to truly enter the trading era.”