Archive
All posts by category, 15 in total.
Engineering
Enterprise AI Transformation: From Dev Efficiency to a Self-Evolving AI Organization
What are the stages of enterprise AI Native adoption? From AI-ready infrastructure, enterprise knowledge engineering, and SkillOps, to Multi-Agent and AI Organization — this post lays out the full evolution path and best practices.
One Person Can Ship a Product Too: My OPC Software Development Practice
How can a solo developer ship a product alone? Using "Arrange Life" as the case, this is how I turn real pain points into a complete software production system — from requirements, design, dev, and test to release and operations — with AI, coding agents, and Skills.
Sync Architecture for a Todo App: Client and Desktop
The hard part of a todo app isn't the UI, it's multi-device sync and conflict handling. Get the design right and sync feels as natural as local. This post covers the key designs and the traps that break them.
AI
Agent Long-Term Memory: A Complete Design from Async Extraction to Hybrid Retrieval
A complete agent memory system has three mainlines: the write path (outbox async extraction that never slows chat), the read path (dense + lexical hybrid retrieval with RRF), and governance (four-state decision + bitemporal invalidation). This post lays out the whole thing.
Intent Recognition System Design: Unbounded Problems to the Model, Bounded Problems to Code
Intent recognition isn't a classification problem — it's an observable, verifiable execution chain that's allowed to admit uncertainty. One principle: give unbounded problems to the model (understanding), bounded problems to code (compute and guard).
How to Stop an LLM Agent from Faking "Created": Exit Validation That Checks Facts, Not Wording
The model claimed "schedule created" without calling any write tool. Blocking phrases like "created" fails because the model rewords endlessly. Use an exit invariant: only a real database write counts as success.
Slot Extraction in Intent Recognition: The Pitfalls of Chinese Time Parsing
Intent recognition isn't just classifying intent — you still have to extract slots like time. Chinese time is the easiest slot to get wrong: is "7点半" 7:30 AM or 7:30 PM?
Why We Deleted 530 Lines of Intent Regex: A Calendar Agent's Architecture Rewrite
Rebuilding a calendar agent from real user feedback: from 530 lines of intent regex to a single large-model call, keeping the safety boundary with a state machine, tool constraints, exit validation, and real-model evaluation.
I Gave Up the Ops Workbench and Generated a Thousand Calendar Images with a Few Sentences
In the AI era, if you can finish something by 'talking', don't fall back into the old 'build a system' mindset.
Agent Intent Recognition: From Classifier to Executable Control System
How to design an agent's intent recognition. The core: intent recognition isn't labeling a sentence — it's a control system deciding whether to call tools, which tool, whether side effects are allowed, and whether the last sentence can be trusted.
Why I Built an AI Gateway
For indie developers, an AI gateway isn't showing off — it's the smallest engineering unit that unifies model access, cost, and stability. This post covers the five capabilities a production gateway needs, and the traps behind each.
What Separates AI Development from Demo to Production
The real gap isn't model quality, it's engineering: observability, regression, cost, permission, and failure recovery. This post walks through the five things you must add to go from demo to production, and the trap each one hides.
Thoughts
How to Get Traffic to a Personal Site: SEO, GEO, Content Engineering, and Bilingual
Traffic to a personal site isn't "post and wait for indexing" — it's four layers: technical foundation (sitemap/rss/structured data, so content is findable), content engineering (topic + writing pipeline, so content is worth searching), GEO (llms.txt + citable content, so AI engines cite you), and bilingual (to reach a bigger market). This is my full record.
Thinking About Intent Recognition: Plan + Tool Design
After many rounds of intent recognition, I finally understand how it should be done.
Loop Engineering Has No Silver Bullet: Vertical Skills + spec/TDD
Chasing one big "fully autonomous" loop doesn't work. After half a year of intensive coding-agent development, my conclusion: the right carrier for Loop Engineering is per-vertical Skills, with spec + TDD at the core.