Skip to content PROJECT SHOWROOM / 06 RECIPES
Give your agent a real GPU project. Pick an outcome, copy one complete prompt, and paste it into your coding agent. It builds locally, asks before spending, and returns the artifact to your machine.
01 Copy a prompt model URL included 02 Approve the ceiling price + runtime 03 Get the artifact saved locally amics / run 01
❯ PNG / 512 × 512
orbital-greenhouse.png
✓ artifact returned
Build 01
Turn a sentence into an image Build a tiny text-to-image app around the official Diffusers pipeline and generate a finished PNG.
Model: Hugging Face Diffusers ↗ You get A local 512px concept-art PNG
Copy the agent prompt → amics / run 02
❯ 00:00:00,000 → 00:00:03,400
And so, my fellow Americans…
✓ jfk.srt
Build 02
Transcribe a piece of history Use OpenAI Whisper on its real JFK sample and bring back timestamped subtitles.
Model: OpenAI Whisper ↗ You get A local, timestamped SRT transcript
Copy the agent prompt → amics / run 03
❯ PLY / binary
six-wheel lunar rover
✓ mesh validated
Build 03
Make a 3D object from words Run OpenAI's official Shap-E model and turn a text prompt into a mesh you can open locally.
Model: OpenAI Shap-E ↗ You get A local textured PLY mesh
Copy the agent prompt → amics / run 04
❯ PDB / ATOM records
mean pLDDT
✓ 88.3
Validate 04
Fold a protein in 3D Give ESMFold an amino-acid sequence and get an atomic structure without a sequence database.
Model: Hugging Face ESMFold ↗ You get A local PDB structure with confidence scores
Copy the agent prompt → amics / run 05
❯ RGBA / alpha
truck-cutout.png
✓ mask verified
Build 05
Cut an object out of a photo Use Meta's SAM 2 to find an object and return a transparent cutout with no manual tracing.
Model: Meta SAM 2 ↗ You get A local transparent PNG cutout
Copy the agent prompt → amics / run 06
❯ Qwen3-0.6B + LoRA
before → after
✓ loss / time / VRAM
Optimize 06
Teach a tiny language model Fine-tune a small Qwen model with LoRA and compare its answer before and after training.
Model: Hugging Face TRL ↗ You get A measured before-and-after fine-tune
Copy the agent prompt → YOUR TURN
Start with the result you want. The prompt handles the project scaffold, model source, compute bounds, and verification.
Choose a project ↑ Build / AGENT RECIPE
Turn a sentence into an image Paste this prompt into a coding agent from any empty working directory.
Use $amics to build a small text-to-image project.
### Project
- Model and usage: https://huggingface.co/stabilityai/sdxl-turbo
- Create image-lab with only pyproject.toml, README.md, and generate.py.
- Follow Hugging Face Diffusers' official text-to-image pipeline using stabilityai/sdxl-turbo in half precision and a fixed seed.
- Generate “a quiet orbital greenhouse above the Atlantic, technical editorial photography”.
- Write only the final PNG bytes to stdout; send diagnostics to stderr.
### Remote run
- Confirm that amics is installed and quote live capacity with at least 16 GB VRAM and a realistic runtime.
- Before spending, ask me to approve explicit hourly-price and runtime ceilings.
- After approval, run one literal command with amics in default output mode and redirect stdout locally to image-lab/orbital-greenhouse.png.
- Do not use --json, create durable storage, or replay an unknown run automatically.
### Success criteria
- Verify that the local output is a valid PNG and report its dimensions. Copy prompt
Build / AGENT RECIPE
Transcribe a piece of history Paste this prompt into a coding agent from any empty working directory.
Use $amics to build a GPU transcription project.
### Project
- Model and usage: https://github.com/openai/whisper (load the turbo model)
- Create whisper-lab with pyproject.toml, README.md, and transcribe.py using the official openai-whisper package.
- Download OpenAI Whisper's tests/jfk.flac sample into the folder before the snapshot.
- Run the turbo model on CUDA and emit a valid SRT transcript to stdout; send progress to stderr.
### Remote run
- Confirm that amics is installed and quote live capacity with at least 12 GB VRAM and a realistic runtime.
- Before acquisition, ask me to approve explicit hourly-price and runtime ceilings.
- After approval, run one literal command with amics in default output mode and redirect stdout locally to whisper-lab/jfk.srt.
- Do not use --json or durable storage.
### Success criteria
- Verify that the SRT has numbered cues and timestamps, then show me the first two cues. Copy prompt
Build / AGENT RECIPE
Make a 3D object from words Paste this prompt into a coding agent from any empty working directory.
Use $amics to build a text-to-3D project.
### Project
- Models and usage: https://github.com/openai/shap-e (load text300M and transmitter)
- Create shape-lab with only pyproject.toml, README.md, and generate_mesh.py, following OpenAI's official Shap-E text-to-3D example.
- Generate “a small lunar rover with six wheels” with a fixed seed and export the decoded result as a binary PLY mesh.
- Write only the PLY bytes to stdout; send all progress to stderr.
### Remote run
- Confirm that amics is installed and quote live capacity with at least 16 GB VRAM and a realistic runtime.
- Before spending, ask me to approve explicit hourly-price and runtime ceilings.
- After approval, run exactly one amics command in default output mode and redirect stdout locally to shape-lab/lunar-rover.ply.
- Do not use --json or durable storage.
### Success criteria
- Validate the PLY header and report the local file size. Copy prompt
Validate / AGENT RECIPE
Fold a protein in 3D Paste this prompt into a coding agent from any empty working directory.
Use $amics to build a protein-folding project.
### Project
- Model and usage: https://huggingface.co/facebook/esmfold_v1
- Create protein-lab with pyproject.toml, README.md, and fold.py using Hugging Face Transformers' ESMForProteinFolding with facebook/esmfold_v1.
- Use the short example sequence from the official ESM documentation, run inference on CUDA, and convert the atom positions to PDB.
- Write only the PDB text to stdout; send the mean pLDDT confidence to stderr.
### Remote run
- Confirm that amics is installed and quote live capacity with at least 24 GB VRAM and a realistic runtime.
- Before acquisition, ask me to approve explicit hourly-price and runtime ceilings.
- After approval, run one literal amics command in default output mode and redirect stdout locally to protein-lab/result.pdb.
- Do not use --json or durable storage.
### Success criteria
- Validate that the local file contains ATOM records and report the confidence score. Copy prompt
Build / AGENT RECIPE
Cut an object out of a photo Paste this prompt into a coding agent from any empty working directory.
Use $amics to build an image-segmentation project.
### Project
- Model and usage: https://huggingface.co/facebook/sam2-hiera-large
- Create segment-lab with pyproject.toml, README.md, and segment.py, following Meta's official SAM 2 image-prediction example.
- Download the repository's notebooks/images/truck.jpg demo asset locally before the snapshot.
- Load facebook/sam2-hiera-large, use a center-point prompt on the nearest truck, and apply the best mask as alpha.
- Write only the transparent PNG bytes to stdout; send diagnostics to stderr.
### Remote run
- Confirm that amics is installed and quote live capacity with at least 16 GB VRAM and a realistic runtime.
- Before spending, ask me to approve explicit hourly-price and runtime ceilings.
- After approval, run one literal amics command in default output mode and redirect stdout locally to segment-lab/truck-cutout.png.
- Do not use --json or durable storage.
### Success criteria
- Verify that the local PNG has an alpha channel. Copy prompt
Optimize / AGENT RECIPE
Teach a tiny language model Paste this prompt into a coding agent from any empty working directory.
Use $amics to build a small language-model fine-tuning project.
### Project
- Model and usage: https://huggingface.co/Qwen/Qwen3-0.6B
- Dataset: https://huggingface.co/datasets/trl-lib/Capybara
- Create finetune-lab with pyproject.toml, README.md, and train.py, following Hugging Face TRL's official SFTTrainer and PEFT integration.
- Fine-tune Qwen/Qwen3-0.6B with LoRA on the first 500 examples of trl-lib/Capybara using a fixed seed and a held-out evaluation slice.
- In one run, print the same test prompt's response before and after training, plus initial loss, final loss, runtime, and peak VRAM.
### Remote run
- Confirm that amics is installed and quote live capacity with at least 16 GB VRAM and a realistic runtime.
- Before acquisition, ask me to approve explicit hourly-price and runtime ceilings.
- After approval, execute one literal amics command and retain its normal text output.
- Do not create durable storage unless you first quote it and I approve its ongoing cost. Never replay an unknown run automatically.
### Success criteria
- Report the before-and-after response, loss change, runtime, and peak VRAM. Copy prompt