Jamie's Blog

The curious developer's ODYSSEY, Exploring the Universe of TECH, CODE & AI.

Beyond the IDE: Running Autonomous Agentic SDLC in Isolated Containers

How I finalized the architecture for running autonomous coding agents in isolated non-root containers with '3+1' stage execution and autonomous PR review triage.

Posted by Jamie Zhang on Tuesday, November 3, 2026

Scaling Agentic SDLC: Designing an Adaptive Auto Mode for Autonomous Coding

Borrowing lessons from Anthropic's code review architecture to scale the Dual-PR model into an adaptive 'auto' mode that balances safety with developer speed.

Posted by Jamie Zhang on Monday, November 2, 2026

From AI-First + SDD to Agentic SDLC: Building a Dual-PR Governance Engine for Autonomous Coding

Why pairing AI-first coding with Spec-Driven Development (SDD) breaks down when autonomous agents enter execution loops, and how I built a Git-anchored Dual-PR SDLC engine to govern delivery.

Posted by Jamie Zhang on Sunday, November 1, 2026

Building Eval Literacy & Red-Teaming for Multi-Agent AI Code Review

How to upgrade an AI Agent from a 'working prototype' to an empirical, production-grade review system with OWASP 2026 Agentic Security defenses.

Posted by Jamie Zhang on Sunday, August 23, 2026

The Self-Declaration Principle: Why Handoffs Only Works When Agents Know Their Own Edges

Self-declaration is not an optional enhancement to Handoffs — it's what makes Handoffs a coherent pattern. A conversation with Claude uncovered the design principle that every multi-agent framework tutorial quietly skips.

Posted by Jamie Zhang on Wednesday, July 8, 2026

Observability & Trace Collection: Spring Boot & OpenTelemetry Engineering Reference

A staff-engineer-level reference on trace collection, data masking, and fallback handling using Spring Boot 4.1, Micrometer, and OpenTelemetry to Langfuse.

Posted by Jamie Zhang on Thursday, June 25, 2026

Multi-Agent Architectures: The Diagrams the Numbers Are Hiding

A companion to LangChain's 'Choosing the Right Multi-Agent Architecture' — full sequence diagrams and call-by-call token math for Skills, Handoffs, and Router, not just Subagents.

Posted by Jamie's Blog on Tuesday, June 23, 2026

The Self-Improvement Agent in Hermes: A Deep Dive

Staff-engineer-level notes on Hermes Agent's procedural self-improvement loop: how the runtime turns solved problems, user corrections, and hard-won debugging paths into durable skills without interrupting the foreground task.

Posted by Jamie Zhang on Friday, May 29, 2026

Exception Handling for LLM Calls in Production Agentic Systems

A deep dive into agent/auxiliary_client.py from Hermes Agent. Written for engineers building production agentic applications who need to go beyond 'catch Exception and retry.'

Posted by Jamie Zhang on Wednesday, May 27, 2026

Designing Context Compression for Production Agents: A Deep Dive into Hermes

Staff-engineer-level notes on agent/context_compressor.py: how Hermes preserves task continuity when a long-running agent outgrows the model context window, and what the implementation teaches about summarization, compression, and failure-tolerant agent design.

Posted by Jamie Zhang on Sunday, May 24, 2026