One PC — open source projects, AI workflows, products, and daily thoughts.https://www.peak-lake.com/en-UShttps://www.peak-lake.com/en/blog/mtw5k47k/https://www.peak-lake.com/en/blog/mtw5k47k/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.Thu, 10 Sep 2026 00:00:00 GMThttps://www.peak-lake.com/en/blog/mtw61el1/https://www.peak-lake.com/en/blog/mtw61el1/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.Thu, 10 Sep 2026 00:00:00 GMThttps://www.peak-lake.com/en/blog/agent-memory-system/https://www.peak-lake.com/en/blog/agent-memory-system/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.Mon, 07 Sep 2026 00:00:00 GMThttps://www.peak-lake.com/en/blog/intent-recognition-system/https://www.peak-lake.com/en/blog/intent-recognition-system/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).Mon, 07 Sep 2026 00:00:00 GMThttps://www.peak-lake.com/en/blog/llm-agent-exit-validation/https://www.peak-lake.com/en/blog/llm-agent-exit-validation/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.Mon, 07 Sep 2026 00:00:00 GMThttps://www.peak-lake.com/en/blog/personal-site-traffic/https://www.peak-lake.com/en/blog/personal-site-traffic/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.Mon, 07 Sep 2026 00:00:00 GMThttps://www.peak-lake.com/en/blog/chinese-time-parsing/https://www.peak-lake.com/en/blog/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?Sun, 06 Sep 2026 00:00:00 GMThttps://www.peak-lake.com/en/blog/mthdnlaj/https://www.peak-lake.com/en/blog/mthdnlaj/After many rounds of intent recognition, I finally understand how it should be done.Mon, 31 Aug 2026 00:00:00 GMThttps://www.peak-lake.com/en/blog/mtengvhn/https://www.peak-lake.com/en/blog/mtengvhn/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.Sat, 29 Aug 2026 00:00:00 GMThttps://www.peak-lake.com/en/blog/mt5oz4db/https://www.peak-lake.com/en/blog/mt5oz4db/In the AI era, if you can finish something by 'talking', don't fall back into the old 'build a system' mindset.Sun, 23 Aug 2026 00:00:00 GMThttps://www.peak-lake.com/en/blog/mt61rdis/https://www.peak-lake.com/en/blog/mt61rdis/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.Sun, 23 Aug 2026 00:00:00 GMThttps://www.peak-lake.com/en/blog/mslj4f6g/https://www.peak-lake.com/en/blog/mslj4f6g/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.Sun, 09 Aug 2026 00:00:00 GMThttps://www.peak-lake.com/en/blog/ai-gateway-01/https://www.peak-lake.com/en/blog/ai-gateway-01/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.Thu, 07 May 2026 00:00:00 GMThttps://www.peak-lake.com/en/blog/ai-rnd-prod-01/https://www.peak-lake.com/en/blog/ai-rnd-prod-01/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.Thu, 07 May 2026 00:00:00 GMThttps://www.peak-lake.com/en/blog/todo-app-sync-01/https://www.peak-lake.com/en/blog/todo-app-sync-01/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.Thu, 07 May 2026 00:00:00 GMT