Weng Jialin's personal website — software engineer building AI infrastructure and developer platforms.https://wengjialin.com/https://wengjialin.com/blog/cloud-agents-api-architecture/https://wengjialin.com/blog/cloud-agents-api-architecture/How we built a company-wide cloud Agents API: the agent loop runs in the cloud on DeepSeek Harness, its state is durably persisted, and tools run through an executor built on Codex exec-server.Sun, 18 Oct 2026 00:00:00 GMThttps://wengjialin.com/blog/desktop-agent-sandbox-boundaries/https://wengjialin.com/blog/desktop-agent-sandbox-boundaries/How desktop agents implement sandboxing, how enterprises can set practical boundaries for non-technical workflows, and where FDEs add value.Fri, 07 Aug 2026 00:00:00 GMThttps://wengjialin.com/blog/agent-harness-performance-takehome/https://wengjialin.com/blog/agent-harness-performance-takehome/A performance-optimization case study showing how prompt contracts, multi-agent research, trace tooling, experimental memory, and validation turn an agent harness into a working environment for capable models.Sun, 12 Jul 2026 00:00:00 GMThttps://wengjialin.com/blog/pe-text-ai-misdiagnosis/https://wengjialin.com/blog/pe-text-ai-misdiagnosis/A CI/CD infrastructure case study on why raw PE .text changes can be caused by relocation-covered address values rather than code logic changes, and why AI analysis still needs engineering validation.Mon, 29 Jun 2026 00:00:00 GMThttps://wengjialin.com/blog/agent-token-management/https://wengjialin.com/blog/agent-token-management/Token management in AI agents is not a single compression trick. It is a system design problem around admission control, compression, retrieval, cache protection, output shaping, and overflow recovery.Sun, 21 Jun 2026 00:00:00 GMThttps://wengjialin.com/blog/agent-observability/https://wengjialin.com/blog/agent-observability/Why agent observability needs to connect semantic traces, system-level facts, agent gateways, OpenTelemetry, evaluation, and policy into one governable trust chain.Sun, 24 May 2026 00:00:00 GMThttps://wengjialin.com/blog/formal-methods-ai-coding/https://wengjialin.com/blog/formal-methods-ai-coding/Why AI coding's prompt-level specs organize work but do not verify complex system design, and where system-level formal methods like TLA+, P, and runtime conformance checking fit.Sun, 03 May 2026 00:00:00 GMThttps://wengjialin.com/blog/harness-ai-agent/https://wengjialin.com/blog/harness-ai-agent/A comparative analysis of seven AI Agent projects, examining the Harness design space across loops, tools, sub-agents, context management, permissions, and enterprise adoption.Sun, 12 Apr 2026 00:00:00 GMThttps://wengjialin.com/blog/ai-code-review-shared-intelligence-layer/https://wengjialin.com/blog/ai-code-review-shared-intelligence-layer/Why AI code review succeeds or fails less on comment generation and more on context supply, trust, and the shared intelligence layer between developers and agents.Sun, 29 Mar 2026 00:00:00 GMThttps://wengjialin.com/blog/agent-sandbox/https://wengjialin.com/blog/agent-sandbox/A systematic overview of AI Agent Sandbox — covering architecture patterns, isolation technologies, industry solutions, and our enterprise deployment experience.Sun, 15 Mar 2026 00:00:00 GMThttps://wengjialin.com/blog/claude-code-tool-search/https://wengjialin.com/blog/claude-code-tool-search/A deep dive into Claude Code's Tool Search mechanism — how it manages tool discovery and loading through a two-layer catalog-execution architecture.Mon, 09 Mar 2026 00:00:00 GMT