Recent Blog Posts
Insights on AI Agents, Modern Web, and the Future of Engineering.
Anatomy of an Agentic Loop: The ORAE Cycle
Explore the fundamental Observe-Reason-Act-Evaluate cycle that powers modern autonomous AI agents, state persistence, and termination strategies.
Build a Custom Autonomous Coding Agent from Scratch
Build a production-ready autonomous coding agent loop in Python implementing the ORAE cycle, tool registries, safety gates, and budget guards.
Context Window Engineering for Long-Running Loops
Master context drift, context rot, memory compaction, Git worktree isolation, and token budgeting for reliable long-running AI agent loops.
Maker-Checker & Multi-Agent Orchestration Patterns
Learn advanced multi-agent patterns including Maker/Checker separation, fan-out/fan-in sub-agent orchestration, background scheduled loops, and autonomous goal-seeking systems.
Building an Approval & Refund Graph Workflow with ADK 2.0
Step-by-step tutorial for constructing an auditable, graph-based refund processing workflow using ADK 2.0 and Python conditional routing.
End-to-End OpenTelemetry Tracing for ADK Agents
Instrument Google ADK agent harnesses with OpenTelemetry to capture full-trajectory execution traces, tool latencies, and token metrics.
Getting Started with ADK 2.0 Graph Workflows
Explore ADK 2.0 Graph Workflows to combine LLM reasoning with deterministic Python routing for complex, auditable enterprise AI agent architectures.
Implementing Human-in-the-Loop Approval Gates in ADK
Safeguard high-value actions in Google ADK using Human-in-the-Loop (HITL) interrupt gates and before-tool callbacks.
Safety Guardrails & Token Budgeting for ADK Agents
Implement multi-layered safety guardrails, PII redaction, token budgets, and error-rate circuit breakers in Google ADK agent harnesses.
Automated CI/CD Regression Evaluation for ADK Agents
Implement an automated Python quality gate for ADK agents in CI/CD pipelines to prevent trajectory regressions and enforce pass-rate thresholds before deployment.
Building a Dispatcher Agent with Specialized Subagents
Implement dynamic triage and intent-based routing using Google ADK dispatcher agents and specialized subagents for billing, tech support, and beyond.
Building an Eval Test Suite for ADK Agents
Move from vibes-based testing to structured evaluation for ADK agents, tracking tool call accuracy, trajectory efficiency, and LLM-as-a-judge quality scoring.