Author

Tencent Technical Engineering

Official account of Tencent Technology. A platform for publishing and analyzing Tencent's technological innovations and cutting-edge developments.

112

Articles

Likes

379

Views

Comments

Latest from Tencent Technical Engineering

100 recent articles max

Tencent Technical Engineering

Apr 9, 2026 · Backend Development

Inside the 512K‑Line AI Agent Harness: Architecture, Performance Tricks & Hidden Easter Eggs

This article provides a comprehensive technical deep‑dive into a cutting‑edge TypeScript CLI AI coding agent, covering its massive 1,900‑file, 512 K+ line codebase, layered startup, tool system design, async query engine, multi‑agent orchestration, performance optimisations, the emerging Harness Engineering paradigm, and a suite of hidden features such as a virtual pet, AutoDream memory consolidation, and playful commands.

0 likes · 57 min read

Inside the 512K‑Line AI Agent Harness: Architecture, Performance Tricks & Hidden Easter Eggs

Tencent Technical Engineering

Mar 30, 2026 · Artificial Intelligence

How Agentic Engineering Turns AI into a Full‑Stack Development Partner

This article explores Agentic Engineering, a methodology that transforms AI agents from simple code‑generation tools into coordinated, context‑aware collaborators capable of handling the full software development lifecycle—from requirement analysis and design to coding, testing, and knowledge retention—while addressing challenges like context scarcity, hallucinations, and token efficiency.

0 likes · 105 min read

How Agentic Engineering Turns AI into a Full‑Stack Development Partner

Tencent Technical Engineering

Mar 27, 2026 · Artificial Intelligence

How AI Coding Transformed Kuikly’s Cross‑Platform Development: A Practical Playbook

Facing the AI era, the Sogou Input Method team leveraged the Kuikly cross‑platform framework to build an AI‑driven coding pipeline, creating structured AI context, standardized Spec‑Kit workflows, and custom tools that cut new page development from three days to one while boosting code accuracy and documentation quality.

Cross‑platform developmentKuiklySpec Kit

0 likes · 15 min read

How AI Coding Transformed Kuikly’s Cross‑Platform Development: A Practical Playbook

Tencent Technical Engineering

Mar 23, 2026 · Artificial Intelligence

How to Turn AI into a Reliable S‑Level Web‑Testing Engineer: 4 Hard‑Earned Lessons

The article explains why powerful AI models still fail complex web‑testing tasks without proper business SOPs, and presents four concrete engineering lessons—limited context, explicit step definitions, checklist‑driven validation, and iterative self‑revision—to train an AI into a dependable, self‑checking S‑grade testing employee.

AIIterative Developmentautomation

0 likes · 18 min read

How to Turn AI into a Reliable S‑Level Web‑Testing Engineer: 4 Hard‑Earned Lessons

Tencent Technical Engineering

Mar 9, 2026 · Artificial Intelligence

How Does OpenClaw Power Multi‑Agent AI? A Deep Dive into Architecture, Deployment, and Risks

This article explains OpenClaw’s core framework, multi‑agent communication mechanisms, deployment options on cloud or local machines, hardware recommendations, IM tool selection, session and memory management, skill handling, version control, and practical use cases while highlighting important security considerations.

DeploymentLLMOpenClaw

0 likes · 26 min read

How Does OpenClaw Power Multi‑Agent AI? A Deep Dive into Architecture, Deployment, and Risks

Tencent Technical Engineering

Mar 2, 2026 · Artificial Intelligence

Turn AI from Intern to Certified Expert with CloudBase Agent Skills

This article explains how to package eight years of cloud development experience into Agent Skills, enabling AI to generate production‑ready code, overcome local‑only limitations, and follow secure engineering practices through progressive skill loading, cloud‑native authentication, and database access controls.

AI Agent SkillsProduction‑Ready AIServerless

0 likes · 20 min read

Turn AI from Intern to Certified Expert with CloudBase Agent Skills

Tencent Technical Engineering

Feb 27, 2026 · Artificial Intelligence

What Will AI Look Like in 2026? Insights from 8 Tech Giants

This article compiles and analyzes 2026 AI trend reports from eight leading technology companies, highlighting key themes such as AI agents, infrastructure, application scenarios, safety regulations, quantitative metrics, and shared consensus points to forecast the next phase of AI development.

2026 predictionsAI agentsAI governance

0 likes · 14 min read

What Will AI Look Like in 2026? Insights from 8 Tech Giants

Tencent Technical Engineering

Feb 11, 2026 · Backend Development

How WFS Ultra Achieved 200 Gbps TCP Throughput, Surpassing RDMA‑Based 3FS

The article details how the WFS Ultra project re‑engineered a traditional TCP‑based distributed file system with a Run‑To‑Completion thread model, ultra‑core async networking, full‑link zero‑copy, and load‑adaptive prefetch, enabling 200 Gbps Fio throughput that exceeds the RDMA‑accelerated 3FS benchmark.

Distributed File SystemRun-to-CompletionTCP performance

0 likes · 10 min read

How WFS Ultra Achieved 200 Gbps TCP Throughput, Surpassing RDMA‑Based 3FS

Tencent Technical Engineering

Feb 2, 2026 · Artificial Intelligence

Why Neural Networks Are the Hidden Engine Behind Modern AI: From Basics to Large Language Models

This comprehensive guide walks through the fundamentals of neural networks, activation functions, training methods, and how they power large language models, while also covering tokenization, self‑attention, transformer architectures, AI infrastructure, and practical usage through agents and retrieval‑augmented generation.

Agent SystemsArtificial IntelligenceGPU infrastructure

0 likes · 75 min read

Why Neural Networks Are the Hidden Engine Behind Modern AI: From Basics to Large Language Models

Tencent Technical Engineering

Jan 30, 2026 · Artificial Intelligence

Can Rendering Thought Chains as Images Speed Up LLM Reasoning?

This article introduces Render‑of‑Thought (RoT), a novel paradigm that compresses chain‑of‑thought reasoning into visual embeddings using frozen vision encoders, achieving 3‑4× token reduction, faster inference, and improved interpretability while requiring minimal pre‑training.

Inference OptimizationLatent SpaceMultimodal

0 likes · 12 min read

Can Rendering Thought Chains as Images Speed Up LLM Reasoning?