~/categories/ agent-engineering

Agent Engineering

Categories · 8

2026-10-06
Agents That Check Their Own Work and Tidy Their Own Memory
Outcomes has an independent grader, blind to the writer's reasoning, check the work criterion by criterion and send it back until it passes; Dreaming reads an old memory store and past sessions between runs and writes a separate, reorganized store while leaving the original untouched. Both are Claude Managed Agents APIs on the Claude Developer Platform, and Claude Code does not have them. Following the official docs, this article explains why both are needed and how they work, then identifies their closest relatives in Claude Code (/goal and the unreleased auto-dream), runs /goal 12 times on the same task, and translates the design into two contracts you can rebuild on any Agent stack.
Agent Architecture Deep Dives #Claude #Claude Code #Managed Agents #AI Agent
2026-08-02
Five Codex Harness Designs Worth Copying
A source-grounded analysis of selective parallelism, Unified Exec, ExecCell, progressive Skills, persistent Goal continuation, and embedding the runtime through App Server.
Agent Architecture Deep Dives #Codex #OpenAI #AI Agent #Agent Harness
2026-06-20
One File Path Eliminated 84% of Tool Calls
OpenClaw's daily-ai-news cron job kept timing out. The root cause wasn't a weak model, bloated prompt, or upstream API failure — it was a missing absolute path in the SKILL.md, causing the Agent to spend 15 exec calls searching for a tool's location every run. Message count ballooned from 54 to 165, tool results from 204KB to 1.1MB. This is the full debugging story.
OpenClaw Production Notes #OpenClaw #AI Agent #Cron Job #SKILL.md
2026-06-20
OpenClaw Memory in Practice
OpenClaw's vector retrieval silently failed — but BM25 text search kept the memory system running for two weeks unnoticed. When you discover 'it works without embeddings,' should you even bother fixing it? Here's how I used NVIDIA's free embedding API to complete the picture, and what I learned about when vector search actually matters.
OpenClaw Production Notes #OpenClaw #AI Agent #Memory System #Embedding
2026-06-13
Claude's Tool Calling Paradigm Shift
Anthropic's Programmatic Tool Calling and Dynamic Filtering aren't just feature additions — they represent a paradigm shift in Agent architecture: from natural language orchestration to code-driven orchestration, from full context injection to on-demand filtering. Synthesizing multiple non-AI-written deep-dive articles, this post covers architecture, benchmarks, and production patterns.
Agent Architecture Deep Dives #Claude #AI Agent #Agent Architecture #Tool Calling
2026-05-27
OpenClaw in Production
A full-chain production battle log: from startup failures and Feishu message silent drops to production stability — compaction safeguard, five-layer debugging, model-harness fit, and memory system comparison.
OpenClaw Production Notes #OpenClaw #AI Agent #Feishu #Memory System
2026-05-16
Why We Moved from Celery to Temporal
Agent pipelines are not ordinary async tasks — they have state, they get stuck, they need replay debugging, and one failure must not sink the entire batch. We hit every one of these walls with Celery before understanding that Temporal solves a fundamentally different problem.
#Agent Engineering #Temporal #Celery #Workflow Engine
2026-05-11
RAG vs LLM Wiki vs Plain Text
Cost, latency, accuracy, and maintainability trade-offs across three Agent memory approaches: RAG, structured knowledge bases, and plain-text context memory. Includes decision tree.
#AI Agent #Memory #RAG #Context Engineering