Take your AI projects to the next level with
Small Language Agents for Modern Workflows. Aaron Blake shows you how to build
interactive, multi-agent systems powered by small, on-device NLP models—fast, efficient, and secure.
Learn how to:
- Design Agentic Pipelines: Tool-routing, multi-agent orchestration, and conversational loops
- Deploy Cross-Platform: ONNX, TensorRT, TFLite, Core ML, and edge devices
- Optimize Performance: Quantization, caching, batching, and latency reduction
- Monitor & Scale: Lightweight Prometheus metrics, structured logging, and Kubernetes autoscaling
- Secure & Private AI: Run fully private agents without cloud dependencies
Packed with
hands-on tutorials, project walkthroughs, and production-ready scripts, this book equips developers to build
powerful agentic AI workflows that run anywhere—from laptops to mobile devices to embedded systems.
Ideal for ML engineers, AI developers, and tech-savvy innovators who want to deploy smart, responsive AI agents on the edge.