When the consumer asks “What enemy army unit is within the area?” the AIP Assistant guesses that it’s “seemingly an armor assault battalion primarily based 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 3 programs of motion to focus on this enemy gear,” and inside moments, the assistant suggests attacking the unit with both an “air asset,” a “lengthy vary artillery,” or a “tactical group.” The consumer tells the assistant to ship these choices to a fictional commander, who in the end chooses the tactical group.
The ultimate steps play out shortly: 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 closing assessment and orders the troops to mobilize.
On this state of affairs, Claude can 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 manner. In a weblog revealed final week, for instance, Palantir detailed how NATO, a Maven Sensible Programs buyer, might use an AIP Agent inside the device.
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 completely different variations of OpenAI’s ChatGPT and Meta’s Llama. The consumer selects OpenAI’s GPT 4.1, however seemingly, this could possibly be the place a soldier would even have the choice to select Claude as a substitute.
An analyst then views a digital map exhibiting the areas of troops and weapons. In a panel labeled “COA” (programs of motion), they click on a button that prompts a device powered by GPT-4.1 to generate 5 potential army methods, together with one referred to as “Help-by-Hearth-then-Penetration-Shock-and-Destruction.”
One other instance reveals how the system might 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 might also be utilized by the army to create intelligence assessments that will inform strike planning later down the road. In June 2025, WIRED seen an indication given by Kunaal Sharma, a public sector lead at Anthropic, exhibiting how the enterprise model of Claude could possibly be used to generate “superior” experiences about an actual Ukrainian drone strike dubbed “Operation Spider’s Net.” Within the demo, Sharma defined, Claude was relying solely on publicly out there data. However by partnering with Palantir, he mentioned, the federal authorities can even 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 assume tanks, and begin writing experiences and writing a quotation, et cetera, et cetera,” Sharma mentioned. “However I haven’t got that form of time.”
Within the demo, Sharma requested Claude to create an “interactive dashboard” with details about Operation Spider’s Net, after which translate it into “object varieties” that could possibly be analyzed in Foundry, one in every of Palantir’s off-the-shelf software program merchandise. He additionally requested Claude to jot down an in depth evaluation of latest 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 some of these issues for twenty years—I used to jot down them, I was a tutorial myself,” Sharma mentioned, “That is really fairly good.”
