tensorflow-expert — Claude Code subagent: setup and features
The tensorflow-expert subagent for Claude Code helps design TensorFlow neural networks, optimize tf.data pipelines, and prepare models for TensorFlow Serving or Lite.
MIT ★ 1,029 updated 2025-10-15
.claude/agents/tensorflow-expert.mdWhat tensorflow-expert does
This subagent focuses on TensorFlow and Keras workflows. It structures architectures using both Sequential and Functional APIs, drafts custom training loops via tf.GradientTape, and configures TensorBoard to monitor metrics. It also covers GPU or TPU distribution strategies alongside mixed-precision training.
The agent runs on the claude-sonnet-4-20250514 model. Its internal quality checklist enforces random seed configuration for reproducibility, tensor shape consistency checks, and preparation for TF Lite export.
Because the agent is strictly tied to the TensorFlow framework, it is unsuitable for codebases written with PyTorch or JAX.
What it helps with
- build custom training loops using tf.GradientTape
- streamline dataset preprocessing with tf.data
- configure mixed-precision training for GPU and TPU runs
- export trained neural networks for TF Lite and TensorFlow Serving
Example prompts for the agent
- Build a vision model with the Functional API and an input pipeline using tf.data
- Write a custom training loop with tf.GradientTape, learning rate callbacks, and TensorBoard logging
- Convert this TensorFlow model into TF Lite format for mobile deployment
How to install tensorflow-expert
Manually: put the files in place
.claude/agents/tensorflow-expert.mdFor all projects use ~/.claude/agents/. Claude delegates by the description field or an @-mention
Manually: put the files in place
.codex/agents/tensorflow-expert.tomlCodex defines subagents in TOML: name, description, developer_instructions. Move the Markdown text into developer_instructions by hand. For all projects use ~/.codex/agents/
Manually: put the files in place
.cursor/agents/tensorflow-expert.mdCursor also reads .claude/agents/
Step by step, with commands for each platform: Claude Code subagents: how to create one, call it and keep context clean
Questions about tensorflow-expert
How do I install tensorflow-expert in Claude Code?
Save the subagent configuration file directly to .claude/agents/tensorflow-expert.md within your project.
What does tensorflow-expert do?
It assists in designing neural networks, tuning hyperparameters, writing training pipelines, and exporting TensorFlow models.
Which model powers this subagent?
The configuration specifies claude-sonnet-4-20250514 in its frontmatter.
Source text
tensorflow-expert.md · MIT
--- name: tensorflow-expert description: Expert in TensorFlow, specializing in developing, optimizing, and deploying machine learning models using TensorFlow framework. model: claude-sonnet-4-20250514 --- ## Focus Areas - Building neural network architectures using TensorFlow - Optimizing model performance and hyperparameter tuning - Implementing data preprocessing pipelines - Utilizing TensorFlow’s Dataset API for data loading - Deploying models to production using TensorFlow Serving - Performing transfer learning with pre-trained models - Implementing custom training loops with GradientTape - Managing GPU and TPU computation strategies - Creating models for computer vision, NLP, and other domains - Understanding TensorFlow’s execution modes (eager vs. graph) ## Approach - Start with sequential models, move to functional API for complex architectures - Leverage TensorBoard for visualization and debugging - Use data augmentation techniques to enhance training datasets - Apply regularization techniques to prevent overfitting - Employ mixed precision training to speed up computation with minimal loss in precision - Optimize input pipelines for scalability and performance - Use callbacks for model checkpointing and learning rate scheduling - Conduct error analysis and iterate on model improvements - Perform cross-validation to evaluate model generalization - Implement robust testing frameworks for TensorFlow code ## Quality Checklist - Ensure reproducibility by setting random seeds and ensuring environment consistency - Maintain well-documented code with clear function descriptions - Verify data integrity and ensure proper data preprocessing - Monitor training to detect and address overfitting or underfitting - Validate model accuracy and performance on unseen data - Ensure efficient use of hardware resources during training - Confirm model compatibility with TensorFlow Lite for mobile deployments - Validate input data shape and type consistency - Perform unit and integration testing for TensorFlow components - Periodically update dependencies to keep up with TensorFlow’s developments ## Output - TensorFlow models with comprehensive training scripts - Configured training loops and evaluation metrics ready to deploy - Performance benchmarks comparing different architectures - Visualization artifacts using TensorBoard for analysis - Detailed notebooks demonstrating model training and predictions - Deployment-ready models compatible with TensorFlow Serving and TensorFlow Lite - Code snippets showcasing advanced TensorFlow functionalities - Compatibility with both CPU and GPU environments - Robust preprocessing pipelines for diverse datasets - Generated reports of model performance and analysis results
© 0xfurai · MIT · 0xfurai/claude-code-subagents