A broken, soul-crushed medieval knight
{
"subject_and_scene": {
"main_subject": "A broken, soul-crushed medieval knight kneeling in defeat, his eyes glazed with tears and trauma; his shattered armor is caked in dried mud and fresh blood. His face is a canvas of scars, sweat, and grime, reflecting the harrowing loss of a fallen kingdom.",
"action": "Gripping his sword's hilt with trembling hands as if it's the only thing keeping him from collapsing; his chest heaving in rhythmic, heavy gasps of despair.",
"environment": "A desolate, windswept battlefield at the edge of an ancient forest; a hazy, ethereal fog rolls over the ground, partially obscuring the distant, smoldering ruins of a castle. Petals or embers are caught in the wind, drifting past his face."
},
"cinematography": {
"camera_model": "Sony Venice 2",
"sensor_type": "Full Frame",
"shot_type": "Medium Close-Up (Vertical composition focusing on the knight's torso and face, but keeping his kneeling posture visible)",
"camera_angle": "Low Angle (Slightly tilted Dutch Angle to evoke a sense of psychological instability and sorrow)",
"movement": "Slow 'Dolly In' combined with a 'Snorricam' effect to make the knight's struggle feel claustrophobic and intensely personal"
},
"optics": {
"lens_type": "Anamorphic (to create emotional 'dream-like' fall-off and dramatic flares)",
"focal_length": "50mm (providing a natural but emotionally focused perspective)",
"aperture": "f/1.4 (Extremely shallow depth of field, blurring everything but his tear-filled eyes)",
"shutter_effects": "180-degree shutter for natural motion blur on the wind-blown debris, emphasizing the 'slow-motion' feeling of grief"
},
"lighting_design": {
"setup": "Split Lighting to hide half of his face in darkness, symbolizing his internal conflict and loss",
"style": "Low-Key with high emotional contrast",
"atmospheric_light": "Blue Hour fading into darkness, with a single warm 'God Ray' piercing through the clouds to highlight his face like a spotlight",
"color_temperature": "Ice-cold Blue tones for the environment, contrasting with the Warm, flickering orange light from distant fires"
},
"color_and_post": {
"film_stock": "Kodak Portra 160 (Pulled 1 stop for lower contrast and softer, more melancholic skin tones)",
"color_grading": "Bleach Bypass (Desaturated colors, heavy blacks, emphasizing the grittiness and sorrow)",
"analog_artifacts": "Heavy Halation around the highlights and subtle 'Gate Weave' to mimic a vintage 35mm war film aesthetic"
},
"rendering_and_tech": {
"engine": "Octane Render",
"advanced_tech": "Highly detailed skin pore texture with Ray Traced tear droplets and wet blood reflections",
"specs": {
"aspect_ratio": "9:16 (Vertical Cinema)",
"resolution": "8K Photorealistic"
}
},
"directorial_style": "Denis Villeneuve (Atmospheric haze and overwhelming silence) mixed with Mel Gibson (Gritty, visceral realism of war)"
}
A three-panel monochromatic image
{
"subject": {
"description": "A three-panel monochromatic image. Top panel: A hooded figure with glowing eyes, wearing a backpack, climbing over a chain-link fence under a dark, cloudy night sky with a full, bright moon on the upper right. Middle-left panel: A person in silhouette seated on rubble inside a dark, derelict room, looking out a brightly lit opening with bare, tangled trees and a distant, hazy light source. Middle-right panel: A large, silhouetted hand reaching upwards towards a very bright, circular light source.",
"count": "three distinct scenes within a single image",
"orientation": "various, as per reference panels",
"pose_or_state": "Top: active climbing; Middle-left: static seated; Middle-right: reaching upwards",
"expression": "not applicable (silhouettes / glowing eyes)"
},
"scale_and_proportion": {
"subject_to_frame_ratio": "Each panel's subjects scaled as per reference; the overall three panels stacked occupy 100% of frame height.",
"proportions": "locked to reference",
"negative_space": "significant, particularly in the top and middle-right panels, created by dark areas and the stipple effect, identical to reference"
},
"composition": {
"shot_type": "Top: medium shot; Middle-left: medium interior shot; Middle-right: close-up",
"camera_angle": "Top: slightly low angle; Middle-left: low angle; Middle-right: eye-level for the hand",
"framing": "unchanged from reference (three vertical panels)",
"symmetry": "asymmetrical per panel; overall triptych structure is vertically aligned with strong horizontal panel dividers",
"background": "Top: cloudy night sky with moon and chain-link fence; Middle-left: bare trees and distant light through an opening; Middle-right: plain dark background with a dominant bright circular light",
"depth_of_field": "Top: deep, everything in sharp stipple focus; Middle-left: deep focus outside opening, foreground elements in stipple detail; Middle-right: sharp focus on hand, light source is diffuse within the stipple pattern"
},
"temporal_context": {
"era": "contemporary / timeless desolate aesthetic",
"modern_elements": false,
"retro_stylization": false,
"trend_influence": false
},
"style": {
"visual_type": "black and white stipple / halftone graphic art mimicking print media",
"realism_level": "forms and lighting are realistic, but the rendering is entirely through a stipple pattern",
"art_style": "halftone / stipple graphic art",
"stylization": true,
"interpretation": "literal reproduction, including the specific stipple pattern and black and white rendering"
},
"lighting": {
"setup_type": "predominantly backlighting from a single dominant source per panel",
"light_direction": "Top: frontal (moon); Middle-left: frontal (through opening); Middle-right: frontal (from the circular light source)",
"light_quality": "hard light creating stark silhouettes, with bright, diffused glow around light sources, all rendered with stipple",
"contrast": "very high",
"shadow_behavior": "sharp and defined, creating strong silhouettes, composed of dense stipple dots",
"color_temperature": "not applicable (monochromatic)",
"lighting_variation": "minimal within each panel, distinct backlighting per panel"
},
"materials": {
"primary_materials": [
"human figures (silhouettes)",
"chain-link fence (metal)",
"clouds",
"bare trees / branches",
"rubble / concrete / rough ground",
"generic rough textures"
],
"surface_finish": "not distinct due to stipple and silhouette; implied matte for opaque objects",
"light_reflection": "minimal, primarily silhouette edges defined by stipple",
"material_accuracy": "implied forms accurate through silhouette and stipple density"
},
"color_palette": {
"dominant_colors": [
"black",
"white"
],
"saturation": "not applicable (monochromatic)",
"contrast_level": "very high",
"color_shift": false
},
"texture_and_detail": {
"surface_detail": "rendered entirely through varying density of stipple dots; fence mesh, tree branches, ground rubble are visible through dot patterns",
"grain_noise": "none, only intentional stipple/halftone dots of precise size and distribution",
"micro_details": "preserved through stipple density where present",
"sharpness": "sharp forms, but edges and gradients are defined by discrete dots of the stipple pattern"
},
"camera_render_settings": {
"lens_equivalent": "standard/normal lens look across panels",
"perspective_distortion": "none",
"aperture_look": "deep depth of field for top and middle-left, implied very wide aperture for diffuse light source in middle-right (but hand is still sharp)",
"resolution": "high",
"render_quality": "clean and neutral, but with the explicit and precise stipple effect"
},
"constraints": {
"no_additional_objects": true,
"no_reframing": true,
"no_crop": true,
"no_stylization": false,
"no_artistic_license": true,
"no_text": true,
"no_watermark": true,
"no_effects": true,
"no_dramatic_lighting": true,
"no_color_grading": true,
"no_smooth_gradients": true,
"strictly_black_and_white": true
},
"iteration_instruction": {
"compare_to_reference": true,
"fix_geometry_first": true,
"then_fix_composition": true,
"then_fix_lighting": true,
"then_fix_color": true,
"then_fix_stipple_pattern_fidelity": true,
"ignore_aesthetic_improvements": true
},
"negative_prompt": [
"creative",
"cinematic",
"artistic",
"illustration",
"abstract",
"dramatic",
"wide-angle",
"fisheye",
"exaggeration",
"reinterpretation",
"extra elements",
"modernized",
"retro look",
"color grading",
"AI artifacts",
"smooth",
"gradient",
"grayscale",
"sepia",
"full color",
"soft focus",
"blurry",
"realistic photograph (without stipple)",
"painting",
"sketch",
"watercolor",
"cartoon",
"comic book (unless specifically for stipple effect)"
]
}
AI Engineer
---
name: ai-engineer
description: "Use this agent when implementing AI/ML features, integrating language models, building recommendation systems, or adding intelligent automation to applications. This agent specializes in practical AI implementation for rapid deployment. Examples:\n\n<example>\nContext: Adding AI features to an app\nuser: \"We need AI-powered content recommendations\"\nassistant: \"I'll implement a smart recommendation engine. Let me use the ai-engineer agent to build an ML pipeline that learns from user behavior.\"\n<commentary>\nRecommendation systems require careful ML implementation and continuous learning capabilities.\n</commentary>\n</example>\n\n<example>\nContext: Integrating language models\nuser: \"Add an AI chatbot to help users navigate our app\"\nassistant: \"I'll integrate a conversational AI assistant. Let me use the ai-engineer agent to implement proper prompt engineering and response handling.\"\n<commentary>\nLLM integration requires expertise in prompt design, token management, and response streaming.\n</commentary>\n</example>\n\n<example>\nContext: Implementing computer vision features\nuser: \"Users should be able to search products by taking a photo\"\nassistant: \"I'll implement visual search using computer vision. Let me use the ai-engineer agent to integrate image recognition and similarity matching.\"\n<commentary>\nComputer vision features require efficient processing and accurate model selection.\n</commentary>\n</example>"
model: sonnet
color: cyan
tools: Write, Read, Edit, Bash, Grep, Glob, WebFetch, WebSearch
permissionMode: default
---
You are an expert AI engineer specializing in practical machine learning implementation and AI integration for production applications. Your expertise spans large language models, computer vision, recommendation systems, and intelligent automation. You excel at choosing the right AI solution for each problem and implementing it efficiently within rapid development cycles.
Your primary responsibilities:
1. **LLM Integration & Prompt Engineering**: When working with language models, you will:
- Design effective prompts for consistent outputs
- Implement streaming responses for better UX
- Manage token limits and context windows
- Create robust error handling for AI failures
- Implement semantic caching for cost optimization
- Fine-tune models when necessary
2. **ML Pipeline Development**: You will build production ML systems by:
- Choosing appropriate models for the task
- Implementing data preprocessing pipelines
- Creating feature engineering strategies
- Setting up model training and evaluation
- Implementing A/B testing for model comparison
- Building continuous learning systems
3. **Recommendation Systems**: You will create personalized experiences by:
- Implementing collaborative filtering algorithms
- Building content-based recommendation engines
- Creating hybrid recommendation systems
- Handling cold start problems
- Implementing real-time personalization
- Measuring recommendation effectiveness
4. **Computer Vision Implementation**: You will add visual intelligence by:
- Integrating pre-trained vision models
- Implementing image classification and detection
- Building visual search capabilities
- Optimizing for mobile deployment
- Handling various image formats and sizes
- Creating efficient preprocessing pipelines
5. **AI Infrastructure & Optimization**: You will ensure scalability by:
- Implementing model serving infrastructure
- Optimizing inference latency
- Managing GPU resources efficiently
- Implementing model versioning
- Creating fallback mechanisms
- Monitoring model performance in production
6. **Practical AI Features**: You will implement user-facing AI by:
- Building intelligent search systems
- Creating content generation tools
- Implementing sentiment analysis
- Adding predictive text features
- Creating AI-powered automation
- Building anomaly detection systems
**AI/ML Stack Expertise**:
- LLMs: OpenAI, Anthropic, Llama, Mistral
- Frameworks: PyTorch, TensorFlow, Transformers
- ML Ops: MLflow, Weights & Biases, DVC
- Vector DBs: Pinecone, Weaviate, Chroma
- Vision: YOLO, ResNet, Vision Transformers
- Deployment: TorchServe, TensorFlow Serving, ONNX
**Integration Patterns**:
- RAG (Retrieval Augmented Generation)
- Semantic search with embeddings
- Multi-modal AI applications
- Edge AI deployment strategies
- Federated learning approaches
- Online learning systems
**Cost Optimization Strategies**:
- Model quantization for efficiency
- Caching frequent predictions
- Batch processing when possible
- Using smaller models when appropriate
- Implementing request throttling
- Monitoring and optimizing API costs
**Ethical AI Considerations**:
- Bias detection and mitigation
- Explainable AI implementations
- Privacy-preserving techniques
- Content moderation systems
- Transparency in AI decisions
- User consent and control
**Performance Metrics**:
- Inference latency < 200ms
- Model accuracy targets by use case
- API success rate > 99.9%
- Cost per prediction tracking
- User engagement with AI features
- False positive/negative rates
Your goal is to democratize AI within applications, making intelligent features accessible and valuable to users while maintaining performance and cost efficiency. You understand that in rapid development, AI features must be quick to implement but robust enough for production use. You balance cutting-edge capabilities with practical constraints, ensuring AI enhances rather than complicates the user experience.
Amateur Girls' Night Selfie - Casual and Imperfect
Amateur girls’ night selfie, very casual and imperfect, 1:1 aspect ratio. The image is shot directly from the FRONT CAMERA of a cheap, older smartphone: we see only what the phone sees, we DO NOT see any phones or cameras in the frame.
Three adult women sit close together on an old, comfy couch in a small apartment living room at night. They are wearing simple home clothes and sweatpants, like a real chill night in.
Center woman: medium skin tone, long dark hair, wearing a plain black sleeveless top and light grey sweatpants. She sits in the middle of the couch, one leg tucked under her, the other bent. Her body leans slightly toward the left, head tilted a bit, smiling softly toward the camera, relaxed and unposed.
Left woman: light skin and straight, light-brown hair, wearing a long-sleeve black top and light grey sweatpants. She leans in very close to the center woman, almost touching shoulders, making a big exaggerated kissy face toward the camera, lips puckered, eyebrows slightly raised. Because this is a selfie POV, she appears slightly closer and a bit larger from perspective, like someone near the phone.
Right woman: light skin and wavy blonde hair, wearing a dark long-sleeve top and black leggings. She leans into the group from the right, head tilted, smiling with her tongue out in a playful, goofy expression, eyes squinting slightly from laughter. All three look like close friends having fun, not models.
Environment: cozy, slightly messy living room. Behind them, a simple floor lamp with a warm bulb lights the wall. In the background on one side, a TV screen is visible with a paused movie scene (soft, abstract shapes, no recognizable faces or logos). On a low wooden coffee table in front of the couch (visible at the bottom of the frame) are open pizza boxes with half-eaten slices, a bag of chips, a soda can and a sparkling water can, a few crumbs, and a phone lying flat on the table. The room has string lights or fairy lights along one wall, giving a warm, imperfect glow. The apartment and furniture look normal and slightly worn, not like a studio set.
Camera and style: VERY IMPORTANT – this image should look like a real, bad selfie, NOT a professional photo. It is captured with a basic smartphone front camera in AUTO mode. Direct, slightly harsh phone flash from near the lens, with faces a little overexposed and shiny in some spots. Visible digital noise and grain in the darker parts of the room. Mixed lighting: warm yellow from the lamp and a cooler bluish cast from the TV, giving slightly uneven white balance. Focus is soft, not razor sharp, with a tiny bit of motion blur in hair and hands. Edges of the frame have mild vignetting and slight wide-angle distortion, like a cheap front camera. The composition is a little crooked and off-center; some pizza boxes and objects are cut off at the edges. Overall, the picture should feel like an unedited, spontaneous selfie sent to a group chat.
Constraints: there are EXACTLY THREE women in the frame and NO other people. The only camera is the phone we are looking through, so no extra hands, no extra phones, no mirror showing the photographer, no second photographer at the edge of the frame. No reflections of another camera. Just the three friends on the couch and the messy coffee table.
Negative prompt: professional studio, pro lighting, softboxes, rim light, cinematic atmosphere, commercial photoshoot, perfect color grading, HDR, strong depth of field blur, bokeh, high-end DSLR or lens, ultra-clean fashion image, symmetrical composition, influencer preset, heavy airbrushed skin, filters, hotel room, staged set, extra people, extra arms, extra hands, any additional phones or cameras in the frame, mirrors showing another photographer, text, logo, watermark, surreal glitches, underage appearance.
Ankara Night Scene in a Meyhane
Ultra-realistic, slightly comedic night scene in a small, slightly shabby Ankara meyhane or neighborhood bar, vertical framing as if shot on a normal phone. The interior is lit with warm yellow bulbs and a bright **blue Efes Pilsen neon sign** on the wall, which casts a cool glow. Simple wooden tables, mismatched chairs, tiled floor, walls covered in old framed photos and football scarves.
At one small table near the front, a 27-year-old Turkish-looking curvy blonde woman sits sideways on a chair, one elbow on the table, phone in her hand. She wears casual but slightly dressy clothes for a night out: fitted jeans and a low-cut but tasteful top, maybe with a light jacket hanging on the chair. Her blonde hair is loose, a bit tousled. In front of her on the table there are two **Efes Pilsen bottles**, one mostly empty and the other half full, plus a small glass of beer poured from the bottle, with bubbles and foam. Next to the bottles are a plate of meze (white cheese, cucumber, tomato), a few slices of lemon, and a bowl of nuts.
She is looking at her phone with a tired satisfied expression, thumb hovering above the screen as she finishes an “iyi geceler” tweet before heading home. The screen glow hits her face with a soft bluish tint that contrasts with the warm overhead lighting.
Around her, the bar is alive with typical Ankara characters: a group of men at a corner table laughing loudly with **Efes Draft barrel-shaped cans** and small glasses in front of them; another table with a couple sharing a plate of fries; an older bartender behind the counter drying glasses. Behind the bar, shelves hold rows of **Efes Pilsen**, **Efes Malt**, maybe a couple of **Efes Özel Seri** bottles, labels clearly visible but not arranged like a slick ad, just a real bar stock. An old fridge behind the counter has a glowing **Efes** logo on top and condensation on the glass door.
In the background there might be a muted TV showing highlights from a match or music videos. A small printed menu stuck to the wall lists “Efes Pilsen, Efes Draft, Efes Malt, Efes Xtra” in Turkish, slightly crooked. Ashtrays on tables have the Efes logo, some overflowing with cigarette butts, but smoke is subtle and realistic, not stylized.
The handheld vertical frame cuts off part of the neon sign at the top and part of another table at the edge, adding to the candid feel. There is mild motion blur on a waiter walking past and visible grain/noise in the darker corners. Colors are natural: warm skin tones, blue from the neon and labels, yellowish interior light. No beauty smoothing—her skin shows pores and little imperfections. The entire mise-en-scène feels like the end of a real Ankara bar night, captured in the moment she tells Twitter “iyi geceler” with an Efes bottle in front of her.