When the consumer asks “What enemy army unit is within the area?” the AIP Assistant guesses that it’s “seemingly an armor assault battalion based mostly on the sample of the gear.” This prompts the analyst to request a MQ-9 Reaper drone to survey the scene. They then ask the AIP Assistant to “generate three programs of motion to focus on this enemy gear,” and inside moments, the assistant suggests attacking the unit with both an “air asset,” a “long-range artillery,” or a “tactical group.” The consumer tells the assistant to ship these choices to a fictional commander, who finally chooses the tactical group.
The ultimate steps play out rapidly: The analyst asks the AIP Assistant to “analyze the battlefield,” then “generate a route” for troops to succeed in the enemy, and eventually “assign jammers” to sabotage their communications gear. Inside seconds, the analyst provides the battle plan a last evaluation and orders the troops to mobilize.
On this state of affairs, Claude could be the “voice” of the AIP Assistant, and the “reasoning” it makes use of to generate responses. Different AIP demos present customers interacting with giant language fashions in a lot the identical means. In a weblog published final week, for instance, Palantir detailed how NATO, a Maven Sensible Techniques customer, may use an AIP Agent throughout the software.
In a single graphic, Palantir reveals how a third-party protection contractor can choose from a number of of Palantir’s built-in AI fashions, together with totally different variations of OpenAI’s ChatGPT and Meta’s Llama. The consumer selects OpenAI’s GPT 4.1, however seemingly, this might be the place a soldier would even have the choice to select Claude as an alternative.
An analyst then views a digital map displaying the areas of troops and weapons. In a panel labeled “COA” (programs of motion), they click on a button that prompts a software powered by GPT-4.1 to generate 5 doable army methods, together with one referred to as Assist-by-Fireplace-Then-Penetration-Shock-and-Destruction.
One other instance reveals how the system may assist interpret satellite tv for pc imagery: The analyst selects three tanker truck detections on a map, masses them into the AIP Agent’s chat interface, and asks it to “interpret” the imagery and recommend choices for what to do subsequent.
Claude may additionally be utilized by the army to create intelligence assessments which will inform strike planning later down the road. In June 2025, WIRED considered an illustration given by Kunaal Sharma, a public sector lead at Anthropic, displaying how the enterprise model of Claude might be used to generate “superior” experiences about an actual Ukrainian drone strike dubbed Operation Spider’s Web. Within the demo, Sharma defined, Claude was relying solely on publicly obtainable info. However by partnering with Palantir, he mentioned, the federal authorities may pull from inner datasets.
“That is sometimes one thing that I’d sit for like 5 hours with a cup of espresso, and browse Google, and go into suppose tanks, and begin writing experiences and writing a quotation, and so forth.,” Sharma mentioned. “However I haven’t got that type of time.”
Within the demo, Sharma requested Claude to create an “interactive dashboard” with details about Operation Spider’s Internet, after which translate it into “object varieties” that might be analyzed in Foundry, one in every of Palantir’s off-the-shelf software program merchandise. He additionally requested Claude to put in writing an in depth evaluation of current developments in Russia’s border provinces, in addition to a 200-word synopsis of the operation’s “army and political results.”
“Frankly, I have been studying most of these issues for 20 years—I used to put in writing them, I was an educational myself,” Sharma mentioned, “That is really fairly good.”
