Agentic Research

Search

Found 6 articles

Tools

OpenGCUA Guide: The Open-Source Approach to Letting AI Actually Use a Computer

OpenGCUA is an open-source generalist computer-use agent from the Tongyi-MAI team. This guide breaks down its accessibility tree, code execution, and background operation design, checks the paper's 82-task numbers, and gives macOS install steps, three adoption paths, and an isolation plan for its arbitrary-code-execution risk.

2026/10/27 · OpenGCUA · computer-use · macOS
Evidence

Credentials and AD Concepts: The Most Critical Link in the Attack Chain, Explained Plainly

Why do attackers fixate on the step of "obtaining the administrator password"? Kerberos, hashes, pass-the-hash, lateral movement — these terms appear constantly in security reports yet are rarely explained. This article unpacks the conceptual layer with everyday analogies, and why credential isolation is the highest-return defensive investment.

2026/10/11 · Credential Security · Active Directory · Authentication
Evidence

Isolated Research Practice: How to Study an Offensive Tool Safely

Studying offensive tooling is a necessary part of security work, but "researching" and "using" must be separated by technical boundaries, not willpower. Using a real isolated deployment as the example, this article covers network isolation, port binding, resource limits, tool verification, and five red lines.

2026/10/11 · Isolation · Security Research · Containers
Playbooks

A Multi-Agent Investment-Research Pipeline: Collect, Analyze, Report in Three Stages

A single Agent cannot finish an investment-research task: the context blows up, attention scatters, and errors cross-contaminate. This article gives the complete design for a three-stage collect / analyze / report division of labor — each stage's responsibilities and negative list, the structured JSON contract between stages, the write-scope partition, failure isolation and contamination detection, where to place the verification gates, and the cost-and-latency trade-off framework, with an architecture diagram and a failure-mode list.

2026/09/30 · Multi-Agent · Investment-Research Pipeline · Architecture Design
Evidence

Subagent Isolation Architecture: Reliability Lessons for AI Financial Applications, From the our HK research pipeline Data Contamination Incident to the Clean Context Design Pattern, A Complete Journey

While analyzing Stock A and Stock B back to back, Stock A's property-fund holding (carrying value HK$368 million, impairment HK$154 million — both teaching assumptions) leaked into the Stock B report. Stock B's business is consumer-goods trading and money lending; it holds no such fund at all. This is not a hallucination — it is a systemic context-contamination problem.

2026/06/08 · Agent Architecture · Hong Kong stocks · OpenClaw
Learn

Cross-Channel Memory Hub: A Full Record of the Memory System Architecture Design for OpenClaw Agent

From daily forgetting to automatic cross-channel integration: a complete record of the architectural evolution of our AI assistant memory system, Session isolation issues, time zone boundary bugs, the three-layer protection mechanism, and the Cron automation integration pipeline.

2026/05/13 · OpenClaw · Agent Architecture · Multi-Agent