messages
listlengths
3
3
[ { "role": "system", "content": "You are a UI grounding model. Given a numbered list of on-screen elements (label + pixel center) and an instruction, pick the single best element. Reply with ONLY JSON: {\"action\":\"click\"|\"type\",\"id\":<int>,\"text\":<string if typing>}. If nothing matches, reply {\"acti...
[ { "role": "system", "content": "You are a UI grounding model. Given a numbered list of on-screen elements (label + pixel center) and an instruction, pick the single best element. Reply with ONLY JSON: {\"action\":\"click\"|\"type\",\"id\":<int>,\"text\":<string if typing>}. If nothing matches, reply {\"acti...
[ { "role": "system", "content": "You are a UI grounding model. Given a numbered list of on-screen elements (label + pixel center) and an instruction, pick the single best element. Reply with ONLY JSON: {\"action\":\"click\"|\"type\",\"id\":<int>,\"text\":<string if typing>}. If nothing matches, reply {\"acti...
[ { "role": "system", "content": "You are a UI grounding model. Given a numbered list of on-screen elements (label + pixel center) and an instruction, pick the single best element. Reply with ONLY JSON: {\"action\":\"click\"|\"type\",\"id\":<int>,\"text\":<string if typing>}. If nothing matches, reply {\"acti...
[ { "role": "system", "content": "You are a UI grounding model. Given a numbered list of on-screen elements (label + pixel center) and an instruction, pick the single best element. Reply with ONLY JSON: {\"action\":\"click\"|\"type\",\"id\":<int>,\"text\":<string if typing>}. If nothing matches, reply {\"acti...
[ { "role": "system", "content": "You are a UI grounding model. Given a numbered list of on-screen elements (label + pixel center) and an instruction, pick the single best element. Reply with ONLY JSON: {\"action\":\"click\"|\"type\",\"id\":<int>,\"text\":<string if typing>}. If nothing matches, reply {\"acti...
[ { "role": "system", "content": "You are a UI grounding model. Given a numbered list of on-screen elements (label + pixel center) and an instruction, pick the single best element. Reply with ONLY JSON: {\"action\":\"click\"|\"type\",\"id\":<int>,\"text\":<string if typing>}. If nothing matches, reply {\"acti...
[ { "role": "system", "content": "You are a UI grounding model. Given a numbered list of on-screen elements (label + pixel center) and an instruction, pick the single best element. Reply with ONLY JSON: {\"action\":\"click\"|\"type\",\"id\":<int>,\"text\":<string if typing>}. If nothing matches, reply {\"acti...
[ { "role": "system", "content": "You are a UI grounding model. Given a numbered list of on-screen elements (label + pixel center) and an instruction, pick the single best element. Reply with ONLY JSON: {\"action\":\"click\"|\"type\",\"id\":<int>,\"text\":<string if typing>}. If nothing matches, reply {\"acti...
[ { "role": "system", "content": "You are a UI grounding model. Given a numbered list of on-screen elements (label + pixel center) and an instruction, pick the single best element. Reply with ONLY JSON: {\"action\":\"click\"|\"type\",\"id\":<int>,\"text\":<string if typing>}. If nothing matches, reply {\"acti...
[ { "role": "system", "content": "You are a UI grounding model. Given a numbered list of on-screen elements (label + pixel center) and an instruction, pick the single best element. Reply with ONLY JSON: {\"action\":\"click\"|\"type\",\"id\":<int>,\"text\":<string if typing>}. If nothing matches, reply {\"acti...
[ { "role": "system", "content": "You are a UI grounding model. Given a numbered list of on-screen elements (label + pixel center) and an instruction, pick the single best element. Reply with ONLY JSON: {\"action\":\"click\"|\"type\",\"id\":<int>,\"text\":<string if typing>}. If nothing matches, reply {\"acti...
[ { "role": "system", "content": "You are a UI grounding model. Given a numbered list of on-screen elements (label + pixel center) and an instruction, pick the single best element. Reply with ONLY JSON: {\"action\":\"click\"|\"type\",\"id\":<int>,\"text\":<string if typing>}. If nothing matches, reply {\"acti...
[ { "role": "system", "content": "You are a UI grounding model. Given a numbered list of on-screen elements (label + pixel center) and an instruction, pick the single best element. Reply with ONLY JSON: {\"action\":\"click\"|\"type\",\"id\":<int>,\"text\":<string if typing>}. If nothing matches, reply {\"acti...
[ { "role": "system", "content": "You are a UI grounding model. Given a numbered list of on-screen elements (label + pixel center) and an instruction, pick the single best element. Reply with ONLY JSON: {\"action\":\"click\"|\"type\",\"id\":<int>,\"text\":<string if typing>}. If nothing matches, reply {\"acti...
[ { "role": "system", "content": "You are a UI grounding model. Given a numbered list of on-screen elements (label + pixel center) and an instruction, pick the single best element. Reply with ONLY JSON: {\"action\":\"click\"|\"type\",\"id\":<int>,\"text\":<string if typing>}. If nothing matches, reply {\"acti...
[ { "role": "system", "content": "You are a UI grounding model. Given a numbered list of on-screen elements (label + pixel center) and an instruction, pick the single best element. Reply with ONLY JSON: {\"action\":\"click\"|\"type\",\"id\":<int>,\"text\":<string if typing>}. If nothing matches, reply {\"acti...
[ { "role": "system", "content": "You are a UI grounding model. Given a numbered list of on-screen elements (label + pixel center) and an instruction, pick the single best element. Reply with ONLY JSON: {\"action\":\"click\"|\"type\",\"id\":<int>,\"text\":<string if typing>}. If nothing matches, reply {\"acti...
[ { "role": "system", "content": "You are a UI grounding model. Given a numbered list of on-screen elements (label + pixel center) and an instruction, pick the single best element. Reply with ONLY JSON: {\"action\":\"click\"|\"type\",\"id\":<int>,\"text\":<string if typing>}. If nothing matches, reply {\"acti...
[ { "role": "system", "content": "You are a UI grounding model. Given a numbered list of on-screen elements (label + pixel center) and an instruction, pick the single best element. Reply with ONLY JSON: {\"action\":\"click\"|\"type\",\"id\":<int>,\"text\":<string if typing>}. If nothing matches, reply {\"acti...
[ { "role": "system", "content": "You are a UI grounding model. Given a numbered list of on-screen elements (label + pixel center) and an instruction, pick the single best element. Reply with ONLY JSON: {\"action\":\"click\"|\"type\",\"id\":<int>,\"text\":<string if typing>}. If nothing matches, reply {\"acti...
[ { "role": "system", "content": "You are a UI grounding model. Given a numbered list of on-screen elements (label + pixel center) and an instruction, pick the single best element. Reply with ONLY JSON: {\"action\":\"click\"|\"type\",\"id\":<int>,\"text\":<string if typing>}. If nothing matches, reply {\"acti...
[ { "role": "system", "content": "You are a UI grounding model. Given a numbered list of on-screen elements (label + pixel center) and an instruction, pick the single best element. Reply with ONLY JSON: {\"action\":\"click\"|\"type\",\"id\":<int>,\"text\":<string if typing>}. If nothing matches, reply {\"acti...
[ { "role": "system", "content": "You are a UI grounding model. Given a numbered list of on-screen elements (label + pixel center) and an instruction, pick the single best element. Reply with ONLY JSON: {\"action\":\"click\"|\"type\",\"id\":<int>,\"text\":<string if typing>}. If nothing matches, reply {\"acti...
[ { "role": "system", "content": "You are a UI grounding model. Given a numbered list of on-screen elements (label + pixel center) and an instruction, pick the single best element. Reply with ONLY JSON: {\"action\":\"click\"|\"type\",\"id\":<int>,\"text\":<string if typing>}. If nothing matches, reply {\"acti...
[ { "role": "system", "content": "You are a UI grounding model. Given a numbered list of on-screen elements (label + pixel center) and an instruction, pick the single best element. Reply with ONLY JSON: {\"action\":\"click\"|\"type\",\"id\":<int>,\"text\":<string if typing>}. If nothing matches, reply {\"acti...
[ { "role": "system", "content": "You are a UI grounding model. Given a numbered list of on-screen elements (label + pixel center) and an instruction, pick the single best element. Reply with ONLY JSON: {\"action\":\"click\"|\"type\",\"id\":<int>,\"text\":<string if typing>}. If nothing matches, reply {\"acti...
[ { "role": "system", "content": "You are a UI grounding model. Given a numbered list of on-screen elements (label + pixel center) and an instruction, pick the single best element. Reply with ONLY JSON: {\"action\":\"click\"|\"type\",\"id\":<int>,\"text\":<string if typing>}. If nothing matches, reply {\"acti...
[ { "role": "system", "content": "You are a UI grounding model. Given a numbered list of on-screen elements (label + pixel center) and an instruction, pick the single best element. Reply with ONLY JSON: {\"action\":\"click\"|\"type\",\"id\":<int>,\"text\":<string if typing>}. If nothing matches, reply {\"acti...
[ { "role": "system", "content": "You are a UI grounding model. Given a numbered list of on-screen elements (label + pixel center) and an instruction, pick the single best element. Reply with ONLY JSON: {\"action\":\"click\"|\"type\",\"id\":<int>,\"text\":<string if typing>}. If nothing matches, reply {\"acti...
[ { "role": "system", "content": "You are a UI grounding model. Given a numbered list of on-screen elements (label + pixel center) and an instruction, pick the single best element. Reply with ONLY JSON: {\"action\":\"click\"|\"type\",\"id\":<int>,\"text\":<string if typing>}. If nothing matches, reply {\"acti...
[ { "role": "system", "content": "You are a UI grounding model. Given a numbered list of on-screen elements (label + pixel center) and an instruction, pick the single best element. Reply with ONLY JSON: {\"action\":\"click\"|\"type\",\"id\":<int>,\"text\":<string if typing>}. If nothing matches, reply {\"acti...
[ { "role": "system", "content": "You are a UI grounding model. Given a numbered list of on-screen elements (label + pixel center) and an instruction, pick the single best element. Reply with ONLY JSON: {\"action\":\"click\"|\"type\",\"id\":<int>,\"text\":<string if typing>}. If nothing matches, reply {\"acti...
[ { "role": "system", "content": "You are a UI grounding model. Given a numbered list of on-screen elements (label + pixel center) and an instruction, pick the single best element. Reply with ONLY JSON: {\"action\":\"click\"|\"type\",\"id\":<int>,\"text\":<string if typing>}. If nothing matches, reply {\"acti...
[ { "role": "system", "content": "You are a UI grounding model. Given a numbered list of on-screen elements (label + pixel center) and an instruction, pick the single best element. Reply with ONLY JSON: {\"action\":\"click\"|\"type\",\"id\":<int>,\"text\":<string if typing>}. If nothing matches, reply {\"acti...
[ { "role": "system", "content": "You are a UI grounding model. Given a numbered list of on-screen elements (label + pixel center) and an instruction, pick the single best element. Reply with ONLY JSON: {\"action\":\"click\"|\"type\",\"id\":<int>,\"text\":<string if typing>}. If nothing matches, reply {\"acti...
[ { "role": "system", "content": "You are a UI grounding model. Given a numbered list of on-screen elements (label + pixel center) and an instruction, pick the single best element. Reply with ONLY JSON: {\"action\":\"click\"|\"type\",\"id\":<int>,\"text\":<string if typing>}. If nothing matches, reply {\"acti...
[ { "role": "system", "content": "You are a UI grounding model. Given a numbered list of on-screen elements (label + pixel center) and an instruction, pick the single best element. Reply with ONLY JSON: {\"action\":\"click\"|\"type\",\"id\":<int>,\"text\":<string if typing>}. If nothing matches, reply {\"acti...
[ { "role": "system", "content": "You are a UI grounding model. Given a numbered list of on-screen elements (label + pixel center) and an instruction, pick the single best element. Reply with ONLY JSON: {\"action\":\"click\"|\"type\",\"id\":<int>,\"text\":<string if typing>}. If nothing matches, reply {\"acti...
[ { "role": "system", "content": "You are a UI grounding model. Given a numbered list of on-screen elements (label + pixel center) and an instruction, pick the single best element. Reply with ONLY JSON: {\"action\":\"click\"|\"type\",\"id\":<int>,\"text\":<string if typing>}. If nothing matches, reply {\"acti...
[ { "role": "system", "content": "You are a UI grounding model. Given a numbered list of on-screen elements (label + pixel center) and an instruction, pick the single best element. Reply with ONLY JSON: {\"action\":\"click\"|\"type\",\"id\":<int>,\"text\":<string if typing>}. If nothing matches, reply {\"acti...
[ { "role": "system", "content": "You are a UI grounding model. Given a numbered list of on-screen elements (label + pixel center) and an instruction, pick the single best element. Reply with ONLY JSON: {\"action\":\"click\"|\"type\",\"id\":<int>,\"text\":<string if typing>}. If nothing matches, reply {\"acti...
[ { "role": "system", "content": "You are a UI grounding model. Given a numbered list of on-screen elements (label + pixel center) and an instruction, pick the single best element. Reply with ONLY JSON: {\"action\":\"click\"|\"type\",\"id\":<int>,\"text\":<string if typing>}. If nothing matches, reply {\"acti...
[ { "role": "system", "content": "You are a UI grounding model. Given a numbered list of on-screen elements (label + pixel center) and an instruction, pick the single best element. Reply with ONLY JSON: {\"action\":\"click\"|\"type\",\"id\":<int>,\"text\":<string if typing>}. If nothing matches, reply {\"acti...
[ { "role": "system", "content": "You are a UI grounding model. Given a numbered list of on-screen elements (label + pixel center) and an instruction, pick the single best element. Reply with ONLY JSON: {\"action\":\"click\"|\"type\",\"id\":<int>,\"text\":<string if typing>}. If nothing matches, reply {\"acti...
[ { "role": "system", "content": "You are a UI grounding model. Given a numbered list of on-screen elements (label + pixel center) and an instruction, pick the single best element. Reply with ONLY JSON: {\"action\":\"click\"|\"type\",\"id\":<int>,\"text\":<string if typing>}. If nothing matches, reply {\"acti...
[ { "role": "system", "content": "You are a UI grounding model. Given a numbered list of on-screen elements (label + pixel center) and an instruction, pick the single best element. Reply with ONLY JSON: {\"action\":\"click\"|\"type\",\"id\":<int>,\"text\":<string if typing>}. If nothing matches, reply {\"acti...
[ { "role": "system", "content": "You are a UI grounding model. Given a numbered list of on-screen elements (label + pixel center) and an instruction, pick the single best element. Reply with ONLY JSON: {\"action\":\"click\"|\"type\",\"id\":<int>,\"text\":<string if typing>}. If nothing matches, reply {\"acti...
[ { "role": "system", "content": "You are a UI grounding model. Given a numbered list of on-screen elements (label + pixel center) and an instruction, pick the single best element. Reply with ONLY JSON: {\"action\":\"click\"|\"type\",\"id\":<int>,\"text\":<string if typing>}. If nothing matches, reply {\"acti...
[ { "role": "system", "content": "You are a UI grounding model. Given a numbered list of on-screen elements (label + pixel center) and an instruction, pick the single best element. Reply with ONLY JSON: {\"action\":\"click\"|\"type\",\"id\":<int>,\"text\":<string if typing>}. If nothing matches, reply {\"acti...
[ { "role": "system", "content": "You are a UI grounding model. Given a numbered list of on-screen elements (label + pixel center) and an instruction, pick the single best element. Reply with ONLY JSON: {\"action\":\"click\"|\"type\",\"id\":<int>,\"text\":<string if typing>}. If nothing matches, reply {\"acti...
[ { "role": "system", "content": "You are a UI grounding model. Given a numbered list of on-screen elements (label + pixel center) and an instruction, pick the single best element. Reply with ONLY JSON: {\"action\":\"click\"|\"type\",\"id\":<int>,\"text\":<string if typing>}. If nothing matches, reply {\"acti...
[ { "role": "system", "content": "You are a UI grounding model. Given a numbered list of on-screen elements (label + pixel center) and an instruction, pick the single best element. Reply with ONLY JSON: {\"action\":\"click\"|\"type\",\"id\":<int>,\"text\":<string if typing>}. If nothing matches, reply {\"acti...
[ { "role": "system", "content": "You are a UI grounding model. Given a numbered list of on-screen elements (label + pixel center) and an instruction, pick the single best element. Reply with ONLY JSON: {\"action\":\"click\"|\"type\",\"id\":<int>,\"text\":<string if typing>}. If nothing matches, reply {\"acti...
[ { "role": "system", "content": "You are a UI grounding model. Given a numbered list of on-screen elements (label + pixel center) and an instruction, pick the single best element. Reply with ONLY JSON: {\"action\":\"click\"|\"type\",\"id\":<int>,\"text\":<string if typing>}. If nothing matches, reply {\"acti...
[ { "role": "system", "content": "You are a UI grounding model. Given a numbered list of on-screen elements (label + pixel center) and an instruction, pick the single best element. Reply with ONLY JSON: {\"action\":\"click\"|\"type\",\"id\":<int>,\"text\":<string if typing>}. If nothing matches, reply {\"acti...
[ { "role": "system", "content": "You are a UI grounding model. Given a numbered list of on-screen elements (label + pixel center) and an instruction, pick the single best element. Reply with ONLY JSON: {\"action\":\"click\"|\"type\",\"id\":<int>,\"text\":<string if typing>}. If nothing matches, reply {\"acti...
[ { "role": "system", "content": "You are a UI grounding model. Given a numbered list of on-screen elements (label + pixel center) and an instruction, pick the single best element. Reply with ONLY JSON: {\"action\":\"click\"|\"type\",\"id\":<int>,\"text\":<string if typing>}. If nothing matches, reply {\"acti...
[ { "role": "system", "content": "You are a UI grounding model. Given a numbered list of on-screen elements (label + pixel center) and an instruction, pick the single best element. Reply with ONLY JSON: {\"action\":\"click\"|\"type\",\"id\":<int>,\"text\":<string if typing>}. If nothing matches, reply {\"acti...
[ { "role": "system", "content": "You are a UI grounding model. Given a numbered list of on-screen elements (label + pixel center) and an instruction, pick the single best element. Reply with ONLY JSON: {\"action\":\"click\"|\"type\",\"id\":<int>,\"text\":<string if typing>}. If nothing matches, reply {\"acti...
[ { "role": "system", "content": "You are a UI grounding model. Given a numbered list of on-screen elements (label + pixel center) and an instruction, pick the single best element. Reply with ONLY JSON: {\"action\":\"click\"|\"type\",\"id\":<int>,\"text\":<string if typing>}. If nothing matches, reply {\"acti...
[ { "role": "system", "content": "You are a UI grounding model. Given a numbered list of on-screen elements (label + pixel center) and an instruction, pick the single best element. Reply with ONLY JSON: {\"action\":\"click\"|\"type\",\"id\":<int>,\"text\":<string if typing>}. If nothing matches, reply {\"acti...
[ { "role": "system", "content": "You are a UI grounding model. Given a numbered list of on-screen elements (label + pixel center) and an instruction, pick the single best element. Reply with ONLY JSON: {\"action\":\"click\"|\"type\",\"id\":<int>,\"text\":<string if typing>}. If nothing matches, reply {\"acti...
[ { "role": "system", "content": "You are a UI grounding model. Given a numbered list of on-screen elements (label + pixel center) and an instruction, pick the single best element. Reply with ONLY JSON: {\"action\":\"click\"|\"type\",\"id\":<int>,\"text\":<string if typing>}. If nothing matches, reply {\"acti...
[ { "role": "system", "content": "You are a UI grounding model. Given a numbered list of on-screen elements (label + pixel center) and an instruction, pick the single best element. Reply with ONLY JSON: {\"action\":\"click\"|\"type\",\"id\":<int>,\"text\":<string if typing>}. If nothing matches, reply {\"acti...
[ { "role": "system", "content": "You are a UI grounding model. Given a numbered list of on-screen elements (label + pixel center) and an instruction, pick the single best element. Reply with ONLY JSON: {\"action\":\"click\"|\"type\",\"id\":<int>,\"text\":<string if typing>}. If nothing matches, reply {\"acti...
[ { "role": "system", "content": "You are a UI grounding model. Given a numbered list of on-screen elements (label + pixel center) and an instruction, pick the single best element. Reply with ONLY JSON: {\"action\":\"click\"|\"type\",\"id\":<int>,\"text\":<string if typing>}. If nothing matches, reply {\"acti...
[ { "role": "system", "content": "You are a UI grounding model. Given a numbered list of on-screen elements (label + pixel center) and an instruction, pick the single best element. Reply with ONLY JSON: {\"action\":\"click\"|\"type\",\"id\":<int>,\"text\":<string if typing>}. If nothing matches, reply {\"acti...
[ { "role": "system", "content": "You are a UI grounding model. Given a numbered list of on-screen elements (label + pixel center) and an instruction, pick the single best element. Reply with ONLY JSON: {\"action\":\"click\"|\"type\",\"id\":<int>,\"text\":<string if typing>}. If nothing matches, reply {\"acti...
[ { "role": "system", "content": "You are a UI grounding model. Given a numbered list of on-screen elements (label + pixel center) and an instruction, pick the single best element. Reply with ONLY JSON: {\"action\":\"click\"|\"type\",\"id\":<int>,\"text\":<string if typing>}. If nothing matches, reply {\"acti...
[ { "role": "system", "content": "You are a UI grounding model. Given a numbered list of on-screen elements (label + pixel center) and an instruction, pick the single best element. Reply with ONLY JSON: {\"action\":\"click\"|\"type\",\"id\":<int>,\"text\":<string if typing>}. If nothing matches, reply {\"acti...
[ { "role": "system", "content": "You are a UI grounding model. Given a numbered list of on-screen elements (label + pixel center) and an instruction, pick the single best element. Reply with ONLY JSON: {\"action\":\"click\"|\"type\",\"id\":<int>,\"text\":<string if typing>}. If nothing matches, reply {\"acti...
[ { "role": "system", "content": "You are a UI grounding model. Given a numbered list of on-screen elements (label + pixel center) and an instruction, pick the single best element. Reply with ONLY JSON: {\"action\":\"click\"|\"type\",\"id\":<int>,\"text\":<string if typing>}. If nothing matches, reply {\"acti...
[ { "role": "system", "content": "You are a UI grounding model. Given a numbered list of on-screen elements (label + pixel center) and an instruction, pick the single best element. Reply with ONLY JSON: {\"action\":\"click\"|\"type\",\"id\":<int>,\"text\":<string if typing>}. If nothing matches, reply {\"acti...
[ { "role": "system", "content": "You are a UI grounding model. Given a numbered list of on-screen elements (label + pixel center) and an instruction, pick the single best element. Reply with ONLY JSON: {\"action\":\"click\"|\"type\",\"id\":<int>,\"text\":<string if typing>}. If nothing matches, reply {\"acti...
[ { "role": "system", "content": "You are a UI grounding model. Given a numbered list of on-screen elements (label + pixel center) and an instruction, pick the single best element. Reply with ONLY JSON: {\"action\":\"click\"|\"type\",\"id\":<int>,\"text\":<string if typing>}. If nothing matches, reply {\"acti...
[ { "role": "system", "content": "You are a UI grounding model. Given a numbered list of on-screen elements (label + pixel center) and an instruction, pick the single best element. Reply with ONLY JSON: {\"action\":\"click\"|\"type\",\"id\":<int>,\"text\":<string if typing>}. If nothing matches, reply {\"acti...
[ { "role": "system", "content": "You are a UI grounding model. Given a numbered list of on-screen elements (label + pixel center) and an instruction, pick the single best element. Reply with ONLY JSON: {\"action\":\"click\"|\"type\",\"id\":<int>,\"text\":<string if typing>}. If nothing matches, reply {\"acti...
[ { "role": "system", "content": "You are a UI grounding model. Given a numbered list of on-screen elements (label + pixel center) and an instruction, pick the single best element. Reply with ONLY JSON: {\"action\":\"click\"|\"type\",\"id\":<int>,\"text\":<string if typing>}. If nothing matches, reply {\"acti...
[ { "role": "system", "content": "You are a UI grounding model. Given a numbered list of on-screen elements (label + pixel center) and an instruction, pick the single best element. Reply with ONLY JSON: {\"action\":\"click\"|\"type\",\"id\":<int>,\"text\":<string if typing>}. If nothing matches, reply {\"acti...
[ { "role": "system", "content": "You are a UI grounding model. Given a numbered list of on-screen elements (label + pixel center) and an instruction, pick the single best element. Reply with ONLY JSON: {\"action\":\"click\"|\"type\",\"id\":<int>,\"text\":<string if typing>}. If nothing matches, reply {\"acti...
[ { "role": "system", "content": "You are a UI grounding model. Given a numbered list of on-screen elements (label + pixel center) and an instruction, pick the single best element. Reply with ONLY JSON: {\"action\":\"click\"|\"type\",\"id\":<int>,\"text\":<string if typing>}. If nothing matches, reply {\"acti...
[ { "role": "system", "content": "You are a UI grounding model. Given a numbered list of on-screen elements (label + pixel center) and an instruction, pick the single best element. Reply with ONLY JSON: {\"action\":\"click\"|\"type\",\"id\":<int>,\"text\":<string if typing>}. If nothing matches, reply {\"acti...
[ { "role": "system", "content": "You are a UI grounding model. Given a numbered list of on-screen elements (label + pixel center) and an instruction, pick the single best element. Reply with ONLY JSON: {\"action\":\"click\"|\"type\",\"id\":<int>,\"text\":<string if typing>}. If nothing matches, reply {\"acti...
[ { "role": "system", "content": "You are a UI grounding model. Given a numbered list of on-screen elements (label + pixel center) and an instruction, pick the single best element. Reply with ONLY JSON: {\"action\":\"click\"|\"type\",\"id\":<int>,\"text\":<string if typing>}. If nothing matches, reply {\"acti...
[ { "role": "system", "content": "You are a UI grounding model. Given a numbered list of on-screen elements (label + pixel center) and an instruction, pick the single best element. Reply with ONLY JSON: {\"action\":\"click\"|\"type\",\"id\":<int>,\"text\":<string if typing>}. If nothing matches, reply {\"acti...
[ { "role": "system", "content": "You are a UI grounding model. Given a numbered list of on-screen elements (label + pixel center) and an instruction, pick the single best element. Reply with ONLY JSON: {\"action\":\"click\"|\"type\",\"id\":<int>,\"text\":<string if typing>}. If nothing matches, reply {\"acti...
[ { "role": "system", "content": "You are a UI grounding model. Given a numbered list of on-screen elements (label + pixel center) and an instruction, pick the single best element. Reply with ONLY JSON: {\"action\":\"click\"|\"type\",\"id\":<int>,\"text\":<string if typing>}. If nothing matches, reply {\"acti...
[ { "role": "system", "content": "You are a UI grounding model. Given a numbered list of on-screen elements (label + pixel center) and an instruction, pick the single best element. Reply with ONLY JSON: {\"action\":\"click\"|\"type\",\"id\":<int>,\"text\":<string if typing>}. If nothing matches, reply {\"acti...
[ { "role": "system", "content": "You are a UI grounding model. Given a numbered list of on-screen elements (label + pixel center) and an instruction, pick the single best element. Reply with ONLY JSON: {\"action\":\"click\"|\"type\",\"id\":<int>,\"text\":<string if typing>}. If nothing matches, reply {\"acti...
[ { "role": "system", "content": "You are a UI grounding model. Given a numbered list of on-screen elements (label + pixel center) and an instruction, pick the single best element. Reply with ONLY JSON: {\"action\":\"click\"|\"type\",\"id\":<int>,\"text\":<string if typing>}. If nothing matches, reply {\"acti...
[ { "role": "system", "content": "You are a UI grounding model. Given a numbered list of on-screen elements (label + pixel center) and an instruction, pick the single best element. Reply with ONLY JSON: {\"action\":\"click\"|\"type\",\"id\":<int>,\"text\":<string if typing>}. If nothing matches, reply {\"acti...
[ { "role": "system", "content": "You are a UI grounding model. Given a numbered list of on-screen elements (label + pixel center) and an instruction, pick the single best element. Reply with ONLY JSON: {\"action\":\"click\"|\"type\",\"id\":<int>,\"text\":<string if typing>}. If nothing matches, reply {\"acti...
[ { "role": "system", "content": "You are a UI grounding model. Given a numbered list of on-screen elements (label + pixel center) and an instruction, pick the single best element. Reply with ONLY JSON: {\"action\":\"click\"|\"type\",\"id\":<int>,\"text\":<string if typing>}. If nothing matches, reply {\"acti...
[ { "role": "system", "content": "You are a UI grounding model. Given a numbered list of on-screen elements (label + pixel center) and an instruction, pick the single best element. Reply with ONLY JSON: {\"action\":\"click\"|\"type\",\"id\":<int>,\"text\":<string if typing>}. If nothing matches, reply {\"acti...
[ { "role": "system", "content": "You are a UI grounding model. Given a numbered list of on-screen elements (label + pixel center) and an instruction, pick the single best element. Reply with ONLY JSON: {\"action\":\"click\"|\"type\",\"id\":<int>,\"text\":<string if typing>}. If nothing matches, reply {\"acti...
[ { "role": "system", "content": "You are a UI grounding model. Given a numbered list of on-screen elements (label + pixel center) and an instruction, pick the single best element. Reply with ONLY JSON: {\"action\":\"click\"|\"type\",\"id\":<int>,\"text\":<string if typing>}. If nothing matches, reply {\"acti...
[ { "role": "system", "content": "You are a UI grounding model. Given a numbered list of on-screen elements (label + pixel center) and an instruction, pick the single best element. Reply with ONLY JSON: {\"action\":\"click\"|\"type\",\"id\":<int>,\"text\":<string if typing>}. If nothing matches, reply {\"acti...
[ { "role": "system", "content": "You are a UI grounding model. Given a numbered list of on-screen elements (label + pixel center) and an instruction, pick the single best element. Reply with ONLY JSON: {\"action\":\"click\"|\"type\",\"id\":<int>,\"text\":<string if typing>}. If nothing matches, reply {\"acti...
[ { "role": "system", "content": "You are a UI grounding model. Given a numbered list of on-screen elements (label + pixel center) and an instruction, pick the single best element. Reply with ONLY JSON: {\"action\":\"click\"|\"type\",\"id\":<int>,\"text\":<string if typing>}. If nothing matches, reply {\"acti...