Public primer
Evals Primer
A practical introduction to evaluation design, judge calibration, regression testing, and production feedback loops for AI systems.
evalsqualityobservability
Books
Books
Public technical primers and longer-form drafts, available for free access and feedback.
I strongly believe books in the AI era should be continuously rewritten, much like the continual learning paradigm. These drafts are my attempt to write continual-learning books: living technical references that stay open, improve over time, and invite feedback as the field changes.
Technical primers
Technical primers
Focused, browsable guides to the systems and control surfaces behind production AI.
Public primer
AI Application Architecture
An architectural guide to composing models, orchestration, data, interfaces, and reliability into production AI applications.
architectureapplicationsreliability
Public primer
Agentic Workflows & Harness Design
A systems view of agent loops, harnesses, control boundaries, approvals, recovery, and dependable workflow execution.
agentsworkflowsharnesses
Public primer
Tools & MCP
A field guide to tool interfaces, the Model Context Protocol, permission boundaries, schemas, and reliable integration patterns.
toolsmcpintegration
Public primer
RAG & Context Engineering
A practical treatment of retrieval, ranking, evidence assembly, context construction, and grounded generation.
ragretrievalcontext
Public primer
Security, Identity & Governance
A control-oriented primer on identity, authorization, policy, auditability, and governance for AI applications and agents.
securityidentitygovernance
Long-form drafts
Long-form drafts
Living manuscripts that remain open in Google Docs for reading and feedback.
Free draft
Inference Engineering
Notes and book draft on inference architecture, serving, latency, throughput, and GPU/cloud economics.
inferenceservinggpu
Free draft
AI Agents in Production
Book draft on production agent systems, durable harnesses, memory, tool boundaries, evals, and governance.
agentsmemoryevals
Free draft
AI Data Integration Patterns
Book draft on RAG, context engineering, knowledge graphs, semantic connectors, and enterprise data-to-AI patterns.
dataragknowledge graphs
Free draft
AI Security
Book draft on security patterns for AI systems, agents, data access, tool use, and AI application risk.
securitygovernanceagents
Free draft
Fundamentals of LLMs
Book draft on modern LLMs, reasoning models, multimodal systems, and inference-time compute.
llmsreasoningmultimodal
Free draft
Reinforcement Learning in LLM Training
Book draft on reinforcement learning concepts, environments, evaluation loops, and agent training patterns.
reinforcement learningagentsevals
Free draft
AI-Assisted Software Engineering
Book draft on AI-assisted coding, agentic development workflows, code review, and software delivery loops.
ai codingdeveloper toolsagents