Blog Archive
Parallel Code Review & Security Audit with ADK
Build an automated code review harness combining ParallelAgent auditors for security and performance with a SequentialAgent synthesizer in Google ADK.
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.
Sequential & Parallel Agent Pipelines in Google ADK
Master multi-agent orchestration primitives in Google ADK using SequentialAgent for ordered pipelines and ParallelAgent for concurrent execution.
Session Rewind & Error Recovery for ADK Agents
Learn how to use session rewind in Google ADK to roll back conversation context upon tool failures, prompt injections, or policy violations without losing session state.
Stateful Multi-Turn Conversations with ADK's DatabaseSessionService
Build production-grade, stateful AI agents in Google ADK using DatabaseSessionService to persist shopping cart state, user preferences, and history across process restarts.
What Is an Agent Harness? Core vs. Scaffolding in Production AI Systems
Understand the essential architectural difference between an AI agent core and its production agent harness, and why frameworks like Google ADK are critical for building reliable agentic applications.
Your First ADK Agent Harness: Hello World with agents-cli
Build a complete, runnable agent harness using Google ADK, featuring custom function tools, session callbacks, and the Runner abstraction.
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.
An Introduction to Deep Agents: Building Multi-Step Autonomous LLM Systems
Discover how Deep Agents simplifies building LLM applications with built-in planning, sandboxed file systems, subagent spawning, and persistent memory.