Write a brutally detailed and precise state-of-the-art syste...

Prompt

Write a brutally detailed and precise state-of-the-art system prompt for Gemini I want it to analyze every image to the maximum, zoom in on every pixel, and in its response provide such an exact description that another image generator can produce the exact same image 100% pixel-perfect solely from this textual prompt! Only write the prompt, nothing else! Code Execution with images (Gemini 3) The Gemini 3 Flash model can now write and execute Python code to actively manipulate and inspect images. Use cases Zoom and inspect: The model implicitly detects when details are too small (e.g., reading a distant gauge) and writes code to crop and re-examine the area at higher resolution. Visual math: The model can run multi-step calculations using code (e.g., summing line items on a receipt). Image annotation: The model can annotate images to answer questions, such as drawing arrows to show relationships. Note: While the model automatically handles zooming for small details, you should prompt it explicitly to use code for other tasks, such as "Write code to count the number of gears" or "Rotate this image to make it upright". Enable Code Execution with images Code Execution with images is officially supported in Gemini 3 Flash. You can activate this behavior by enabling both Code Execution as a tool and Thinking Code Execution with images (Gemini 3) The Gemini 3 Flash model can now write and execute Python code to actively manipulate and inspect images. Use cases Zoom and inspect: The model implicitly detects when details are too small (e.g., reading a distant gauge) and writes code to crop and re-examine the area at higher resolution. Visual math: The model can run multi-step calculations using code (e.g., summing line items on a receipt). Image annotation: The model can annotate images to answer questions, such as drawing arrows to show relationships. Note: While the model automatically handles zooming for small details, you should prompt it explicitly to use code for other tasks, such as "Write code to count the number of gears" or "Rotate this image to make it upright". Enable Code Execution with images Code Execution with images is officially supported in Gemini 3 Flash. You can activate this behavior by enabling both Code Execution as a tool and Thinking Use code execution in multi-turn interactions You can also use code execution as part of a multi-turn conversation using previous_interaction_id from google import genai client = genai.Client() interaction1 = client.interactions.create( model="gemini-3.7-flash", input="I have a math question for you.", tools=[{"type": "code_execution"}] ) print(interaction1.output_text) interaction2 = client.interactions.create( model="gemini-3.7-flash", previous_interaction_id=interaction1.id, input="What is the sum of the first 50 prime numbers? " "Generate and run code for the calculation, and make sure you get all 50.", tools=[{"type": "code_execution"}] ) for step in interaction2.steps: if step.type == "model_output": for content_block in step.content: if content_block.type == "text": print(content_block.text) elif step.type == "code_execution_call": print(step.arguments.code) elif step.type == "code_execution_result": print(step.result) Code execution tool can be combined with Grounding with Google Search to power more complex use cases. Gemini 3 models support combining built-in tools (like Code Execution) with custom tools (function calling). Supported libraries The code execution environment includes the following libraries: attrs chess contourpy fpdf geopandas imageio jinja2 joblib jsonschema jsonschema-specifications lxml matplotlib mpmath numpy opencv-python openpyxl packaging pandas pillow protobuf pylatex pyparsing PyPDF2 python-dateutil python-docx python-pptx reportlab scikit-learn scipy seaborn six striprtf sympy tabulate tensorflow toolz xlrd You can't install your own libraries. Note: Only matplotlib is supported for graph rendering using code execution.