Start from LLM applications, Agent/MCP, RAG, real-time voice, model serving, and observability.
For backend-capable builders who want to turn model capabilities into runnable systems.
Gleam Lab · Start Here
This page is a site guide rather than a feed. Pick the track that matches your question, then follow the related articles, projects, and series.
Start Here
Pick a track first, then follow the most relevant articles and projects without getting lost in the full archive.
Start from LLM applications, Agent/MCP, RAG, real-time voice, model serving, and observability.
For backend-capable builders who want to turn model capabilities into runnable systems.
Understand the infrastructure behind AI apps through model serving, RAG, vector databases, GPU, Kubernetes, observability, and cost governance.
For backend, platform, DevOps, and AI app engineers who need an AI infrastructure map.
Build the engineering foundation around Java, Spring Cloud, microservices, Kubernetes, DevOps, messaging, and data pipelines.
For backend developers, platform engineers, and builders moving from business features to system design.
Understand how long-term public work grows through a technical portal, AscendLab, tool sites, SEO/GEO, AI workflows, and content systems.
For people building public work, personal brand sites, small tools, or indie product experiments.
Use stop-slop-zh, anti-slop rules, technical-blog quality checks, review workflows, and prompt engineering to govern Chinese AI writing.
For writers, reviewers, prompt builders, and anyone reducing the templated feel of AI-generated Chinese content.
Follow annual reviews, project write-ups, training notes, digital-life experiments, and personal reflections as long-term practice.
For readers interested in long-term growth, public notes, review habits, and practice beyond pure technical topics.
Topics
Six long-term topic assets connect Start Here, Series, Projects, Workflow, and the content roadmap.
Turning business capabilities into stable systems with Java, microservices, databases, messaging, Kubernetes, and observability.
ai-engineering AI EngineeringTurning LLMs, Agents, MCP, RAG, real-time voice, and model APIs into runnable, observable, and iterative application systems.
ai-infra AI InfraBuilding the AI engineering foundation around model serving, RAG, vector databases, GPU, Kubernetes, evaluation, observability, and cost governance.
indie-building Indie Building & Tool SitesTurning a personal technical portal, tool site, content system, SEO/GEO, AI workflows, and public projects into long-term assets.
ai-writing-quality Chinese AI Writing Quality GovernanceReducing templated Chinese AI writing through stop-slop-zh, rule categories, common slop patterns, human review, and possible Skill packaging.
digital-life Long-term Records & Digital LifeTurning project reviews, personal data, digital life, annual records, and long-term growth into a public archive that can be revisited.
Now Building
A compact view of the active workbench: public tools, AI engineering, knowledge systems, writing rules, and the site itself.
Organize 147 free browser tools and keep AI workflows clearly marked as preview, early access, or planned.
Public Tool SiteContinue Trace, latency, Apply / Reload, tool-list consistency, and end-to-end stability work.
Project ArchiveBuild the map for model serving, RAG, Agent/MCP, GPU, Kubernetes, observability, and cost governance.
Learning HandbookExpand rule categories, prompt templates, review workflows, and possible Skill packaging.
Open-source ProjectKeep improving content governance, bilingual paths, SEO/GEO, and AI-search readability.
Public SiteWho This Helps
It is not a generic resume page. It is a growing archive of systems, tools, experiments, and writing paths.
You can follow how service design, observability, deployment, and tool calling connect with LLM applications.
You can inspect how small tools, project pages, SEO/GEO, and long-term writing form a public work system.
You can use the series, tags, project map, RSS, and llms.txt as structured entry points rather than a linear blog feed.