The article walks through converting a chat‑based Hermes Agent into a maintainable, hand‑off‑ready system by building a control room, defining clear runtime and management files, applying security safeguards, and following a step‑by‑step production pipeline.
The article examines how AI is silently reshaping everyday life by enabling one‑person companies, redefining job roles, disrupting traditional education, and driving a shift toward networked, AI‑augmented organizations, supported by concrete industry examples and recent policy moves.
At QECon Shenzhen 2026, Xiaohongshu's tech team will present five technical talks that showcase how AI agents are applied to architecture risk analysis, change automation, large‑model load‑testing data construction, end‑to‑end testing, and client‑side performance, illustrating concrete engineering solutions and measurable productivity gains.
This guide explains the concept of AI Agent Skills, walks through creating, installing, and managing a Skill—including file structure, YAML metadata, progressive loading, platform-specific considerations—and introduces a one‑stop development assistant that streamlines Skill development and deployment.
The article explains how agent hooks add programmable, deterministic control to AI agent workflows by binding custom handlers to specific lifecycle events, demonstrates six core hooks with concrete Python examples, and shows how this separation of policy from model memory reduces errors, speeds feedback, and improves auditability.
The article dissects Claude Code's Hooks system, detailing its 27 lifecycle events, four hook types, the special behavior of Stop Hooks with exit code 2, the self‑validation loop, practical patterns like the Ralph Loop, and the design trade‑offs and mitigation strategies.
Andrew Ng argues that while AI is reshaping many jobs—from coding to content creation—it is not triggering a wholesale collapse of the employment market; instead, the narrative of an AI‑driven job apocalypse is fueled by hype, pricing strategies, and companies using AI as a convenient excuse for layoffs.
The author argues that although AI can produce syntactically correct code, it lacks the deep domain knowledge, debugging expertise, and architectural judgment required in real‑world projects, so programmers remain essential and must adapt by using AI as a tool rather than viewing it as a replacement.
The playbook breaks the startup journey into four stages—idea, MVP, launch, and scale—detailing what to do, common pitfalls, and how Anthropic’s Claude (Chat, Cowork, Code) can be applied at each stage to compress cycles, improve decision‑making, and turn founders into AI‑augmented product leaders.
Anthropic’s 36‑page AI‑native founders playbook breaks the startup journey into idea, prototype, launch, and scale phases, detailing research‑driven validation, Claude Code‑powered development, automated testing, growth‑engine creation, and organizational scaling while warning of common pitfalls.
This article walks readers through why many users are switching from Claude Code to Codex, explains the two Codex product forms, details installation, account setup, UI navigation, permission choices, and demonstrates practical tasks such as generating reports, PPTs, web searches, automation, and building a snake game via the CLI, while also offering tips to avoid common pitfalls.
Anthropic’s new Claude for Small Business embeds AI into concrete workflows, offering 15 ready‑to‑use agents that connect to QuickBooks, PayPal, HubSpot and Slack via the Claude Cowork desktop app, with detailed payroll, month‑close, Monday brief and marketing scenarios, transparent pricing, and built‑in security safeguards.
This guide walks developers through selecting, installing, and using the six core ECC components—Rules, search‑first, Reviewer Agent, Quality‑Gate, Documentation‑Lookup, and minimal Hooks—to create a streamlined, conflict‑free AI‑assisted coding workflow for Claude Code, emphasizing a consult‑first, minimal‑install approach.
The article analyses OpenSpec’s default core workflow, explains why the five‑command core profile can feel limiting, and walks through a four‑step process to unlock six additional expanded commands, then compares three workflow modes that suit different development rhythms.
Anthropic released an open‑source Claude‑for‑Legal repository that bundles twelve role‑specific plugins, five managed‑agent recipes, and over twenty connectors, enabling law firms to automate contract review, NDA triage, amendment tracking, and other routine tasks directly within Claude’s workflow.
This guide explains what Claude Code skills are, categorizes common skill types, provides concrete examples for each category, and offers detailed best‑practice recommendations for building, testing, sharing, and managing skills within Claude’s AI ecosystem.
The AC/DC framework reimagines software development by moving verification from post‑commit CI pipelines to the moment code is generated, letting AI agents write, check, and fix code in a self‑correcting loop, while redefining human engineer responsibilities.
This article documents a step‑by‑step OpenSpec workflow that starts with requirement exploration, generates proposal, design, specs, review and task artifacts, executes them to scaffold a React 19 + TypeScript + Vite + Tailwind project, handles GitHub integration, validates the build, and archives the change while sharing practical lessons and pitfalls.
The Xiaohongshu PMO team outlines four iterative versions of an AI‑powered project‑management agent—from a simple knowledge‑base consultant to a shared, role‑aware assistant with long‑memory and multi‑channel integration—detailing design principles, architectural choices, lessons learned, and a roadmap toward fully AI‑run project management.
The article explains how Spec‑Driven Development (SDD) transforms AI‑generated code from risky demos into production‑ready features by defining executable specifications, enforcing review, injecting context, and automating verification, illustrated with a concrete order‑export example.
This article explains how Ansible automates repetitive operations such as bulk software installation, configuration changes, service restarts, application deployment, and log collection, guiding readers through installation, core concepts, inventory setup, common modules, multiple real‑world Playbooks, role organization, Vault security, troubleshooting, and best‑practice risk warnings.
This article reviews four open‑source projects that together cover YouTube downloading (yt‑dlp), AI‑powered clipping (Youtube‑clipper‑skill), a web‑based precise cutter (retrogtx/youtube‑clipper), and GitHub Actions automated archiving (nikzad‑avasam/youtube‑dl), detailing their features, installation steps, and ideal user scenarios.
The article debunks the myth that automation eliminates jobs by tracing the ATM era, three waves of software testing evolution, and current AI trends, showing that repetitive tasks disappear while roles requiring judgment and context shift and expand.
AutoPentestX is an open‑source, Linux‑focused automated penetration testing framework that integrates tools like Nmap, Nikto, SQLMap and Metasploit into a single command workflow, stores results in SQLite, generates detailed PDF reports, and includes installation, usage instructions, legal compliance notes, and future development plans.
This article dissects OpenSpec’s four‑step AI programming workflow, exposing why completing the process often still yields buggy code, and proposes five concrete upgrades—including spec reviews, atomic task checks, runtime verification, TDD practices, and archive gate‑keeping—to close the quality gap.
OpenAI has open‑sourced the Apache‑2.0 licensed openai‑cli, which can be installed via Homebrew or Go and lets users invoke models such as GPT‑5.5 directly from the command line, outputting structured JSON/YAML and supporting piping, file arguments, and built‑in GJSON filtering, streamlining AI workflows without writing SDK code.
OpenAI introduced the open‑source openai‑cli, a native terminal tool that replaces cumbersome SDKs, offering Unix‑style structured output, image generation, speech transcription, project management, and seamless command‑line integration for AI workflows.
Goose is an open‑source, Rust‑based AI agent that runs locally, handling the entire development workflow—from installing dependencies to running tests—while supporting 15+ LLM providers via the ACP protocol and offering desktop, CLI, and API interfaces for developers, analysts, and ops engineers.
In a recent interview, ClaudeCode founder Boris Cherny declares that coding has been solved, showing how AI now writes most of the code, automates PR reviews, schedules self‑healing loops, and predicts a future where software development becomes a universal skill despite current limits with legacy code.
The worklog‑cli is a lightweight, zero‑AI‑dependency npm command‑line tool that lets developers record tasks, extract Git commits, and generate weekly or monthly reports with a single command while staying fully compatible with the original Claude Code knowledge base.
Jack Clark’s Import AI analysis forecasts that, based on accelerating benchmark scores such as SWE‑Bench and METR, there is a 60% probability that by the end of 2028 AI systems will be able to autonomously design and train the next generation of more capable models, reshaping research, economics, and alignment challenges.
The article compares OpenClaw, a manually configured, fully controllable automation tool, with Hermes Agent, an automatically self‑evolving agent, detailing their design philosophies, learning mechanisms, pros and cons, and provides a decision matrix and best‑practice recommendation to use them together for optimal efficiency.
This article provides a ready‑to‑use Bash script that, when placed in a system‑wide or user profile directory, automatically displays hostname, uptime, load average, IP address, CPU and memory usage, and disk mount statistics each time you log into a Linux server, along with color‑coded formatting and customization tips.
OpenAI’s open‑source Symphony re‑imagines AI‑assisted coding by turning Linear issue boards into autonomous Agent workspaces that run 24/7, letting engineers focus on task definition and result approval while delivering up to a 500 % increase in merged PRs and dramatically lowering the barrier to AI‑generated code.
AI speeds up output but also widens existing skill gaps, turning capable users into fast decision‑makers while leaving others with vague results; the article explains how AI acts as an amplifier, why basic tasks disappear, and what abilities are needed to stay valuable.
A Hangzhou court ruled that firing an employee because artificial intelligence can perform the same tasks is illegal, ordering the company to pay over 260,000 RMB in compensation and establishing a legal precedent that AI substitution alone does not constitute a valid reason for termination.
The CLAUDE.md rule file, now with over 100k stars on GitHub, defines four concise principles that guide AI coding assistants like Claude Code and Cursor to think before coding, stay simple, make surgical changes, and execute goal‑driven verification, dramatically improving code quality and developer efficiency.
Pentest‑AI is an MIT‑licensed, locally‑run framework that automates reconnaissance, authentication, vulnerability chaining, PoC validation, and report generation for web, AD, cloud, and more, delivering a client‑ready Markdown/HTML/PDF/SARIF report in about four minutes with a single command.
This article provides a comprehensive walkthrough of Claude Code, covering its core capabilities, cross‑platform installation, login methods, basic commands, advanced features like hooks and MCP, a detailed comparison with GitHub Copilot, best‑practice prompts, and FAQs, enabling developers to boost productivity with an AI‑driven terminal assistant.
As large language models mature, prompt‑writing roles are disappearing, prompting engineers to shift from crafting prompts to designing end‑to‑end AI workflows; this article outlines a three‑step system‑reconstruction protocol, common pitfalls, and practical guidelines for transitioning into workflow architecture.
Phalanx is an open‑source, polyglot‑based automation framework for Kali Linux that coordinates Python, Bash and other scripts, provides a planner, engine and reporting modules, integrates with tools like Nmap and Metasploit, and generates traceable logs for efficient and flexible penetration testing.
This guide presents 20 practical Python skills for API testing, covering basic request handling, pytest fixtures, JSON validation, database helpers, framework abstraction, dynamic data generation, Allure reporting, CI pipeline integration, AI‑driven test case creation, intelligent retries, performance and security testing, and engineering best practices to transform manual testing into an intelligent, automated workflow.
This article introduces Hermes Agent, an open‑source self‑evolving AI assistant that remembers your preferences across sessions, outlines its core capabilities, walks through system requirements, one‑click installation, model configuration, common commands, advanced features like cron jobs and browser integration, and provides troubleshooting tips.
This article explains how to choose between ChatGPT, Claude, Claude Code, and Codex, detailing Codex's seven core capabilities—including local file access, persistent memory, plugins, skills, image generation, computer control, automation, and the Chronicle screen‑monitoring feature—through concrete examples and step‑by‑step walkthroughs.
This tutorial walks through configuring an enterprise WeChat robot, linking it to Hermes' message gateway, building a skill that runs CPU and memory checks, scheduling periodic inspections, and automatically sending the results to the WeChat robot for hands‑free server performance monitoring.
This article reviews eleven Claude Code Skills, explaining how each plugin—such as Superpowers, planning‑with‑files, frontend‑design, and Commit Helper—adds structure, memory, and automation to AI‑assisted development, and offers practical recommendations on which to install first.
ml‑intern, an open‑source AI agent from Hugging Face, automates the full ML workflow—reading papers, generating code, training and deploying models—using an asynchronous event‑driven loop with submission and event queues, supporting interactive and headless modes, Slack notifications, and multiple LLM back‑ends.
This guide explains the simple file structure of a Claude Skill, compares it with CLAUDE.md, shows where to store skills at personal, project, or plugin level, and provides detailed best‑practice tips, code examples, and validation steps for creating effective, on‑demand AI agent skills.
This article presents a practical collection of high‑frequency tools—including Python, Shell, SQL, Mermaid, Pandoc, curl, ImageMagick, and PlantUML—that can be wrapped as Agent Skills to give AI agents real execution power, illustrated with concrete prompts and scripts that cut manual work from hours to seconds.
The article explains how Claude Code’s Code Review plugin automates multi‑agent PR reviews with confidence scoring, details installation and configuration steps, shows the end‑to‑end workflow, compares it to Superpowers plugins, and lists alternative review approaches for developers.
The article explains how a self‑healing platform improves SRE reliability by reducing MTTR, preserving error‑budget, automating high‑impact incident remediation, enforcing safety guardrails, and shifting team focus from firefighting to sustainable reliability engineering.
When an HTTPS certificate expires, browsers show warnings, users abandon sites, services become unavailable, and security is weakened, so this article explains the TLS fundamentals, the risks of expiration, real‑world outage cases, and provides step‑by‑step guidance on acquisition, deployment, automated renewal, monitoring, and best‑practice procedures for reliable certificate management.
A publicly exposed server revealed a large‑scale automated attack in which threat actors used the Bissa scanner tool, AI‑assisted code, and hard‑coded Telegram bots to exploit the React2Shell (CVE‑2025‑55182) vulnerability, stealing credentials from more than 900 enterprises and reporting each success in real time.
The article explains that large‑scale incidents overwhelm on‑call engineers who must manually piece together context from countless signals, and shows how a self‑healing automation platform can take over repetitive, known failure patterns, verify fixes, and reduce fatigue while keeping humans in the loop for oversight.
This article details Coohom's AI‑driven, automated workflow for multilingual testing, covering the four main localization pain points, the construction of an AI language‑validation system, practical implementations for UI and API testing, and measurable results that reduced defect rates and cut regression time from a week to minutes.
The article examines AppleScript’s core capabilities—inter‑application communication, UI scripting, and system commands—while revealing the lower‑level macOS APIs such as Apple Events, Accessibility, JXA, and XPC that developers can use for faster, more powerful automation.
The article presents a data‑driven review of more than 50 AI Skills, grouped into five core scenarios, detailing their installation counts, key functions, and practical impact, to help senior developers choose the most effective plugins for accelerating development, design, documentation, and product growth.
The Claude Code plugin ecosystem has exploded to over 9,000 extensions with the leading plugins surpassing 50‑100k installs; this guide explains the five plugin architecture types, evaluates six functional directions, and recommends tailored plugin combos for full‑stack engineers, frontend developers, solo creators, and team leads.
The article details ClawSweeper, an AI‑driven maintenance bot for OpenClaw that scans and automatically closes thousands of stale issues and pull requests each day, explains its decision criteria, workflow, rate‑limit constraints, and how it turns the README into a live dashboard.
The article outlines fifteen mature AI Agent scenarios across office productivity, customer service, software development, and data analysis, explains how each works, ranks their readiness, and discusses why some applications are ready for large‑scale use while others remain experimental.
Agent Skills is an open‑source standard that defines reusable SKILL.md packages, a unified directory layout, and a progressive‑disclosure workflow, enabling AI agents across tools such as Antigravity to automatically discover, activate, and execute shared capabilities for faster, more consistent automation.
The author reflects on automating reading with AI, distinguishing information gathering from thinking exercises, and proposes a three‑question framework to decide when automation adds value versus when personal reading is essential, ultimately choosing to limit AI to pre‑ and post‑reading tasks.
This guide explains why AI Agent Operators are emerging as a new profession, contrasts the role with Prompt Engineers, outlines four core skills—CLI, agents.md, structured inputs, and business judgment—provides a step‑by‑step workflow, a 90‑day training roadmap, common pitfalls, and references from Deloitte and McKinsey.
The article introduces drawio‑mcp, an official open‑source MCP server that lets Claude‑series AI generate editable draw.io XML diagrams instantly, eliminating tedious manual dragging, alignment, and styling, and outlines four integration methods—MCP App Server, MCP Tool Server, Claude Code Skill, and Project Instructions—plus export formats, built‑in shape library, and maintenance workflow.
Healthpeak, a large medical‑real‑estate REIT, replaced fragmented spreadsheets and manual data entry with Palantir AIP’s ontology‑driven AI operating system, achieving automated billing, voice‑driven workflows, reduced errors, and a scalable, data‑centric operation that frees managers to focus on tenant relationships.
OpenAI’s official ChatGPT for Excel plugin embeds AI directly into Excel, offering natural‑language commands and a suite of AI‑prefixed functions that can generate tables, clean data, extract information, auto‑fill, translate, and even pull financial data, dramatically reducing manual spreadsheet work.
Harness Engineering, now buzzing across the tech community, promises a ten‑fold productivity boost by replacing hand‑written code with a structured AI‑driven system, and the article breaks down its definition, evolution from Prompt to Context to Harness, core components, real‑world examples, and the associated risks and debates.
In 2026, a leading e‑commerce platform cut A/B test preparation from 3.2 days to 47 minutes, boosted experiment throughput 4.3× and GMV 2.8% by applying a three‑step automation workflow, an intelligent analysis engine with three‑level reasoning, and a three‑tier human‑machine decision guard.
The article explains how fragile UI automation scripts hinder performance testing and shows a three‑layer self‑healing approach using Playwright and Python that reduces script failures, cuts maintenance time, and integrates with monitoring to quickly detect UI performance issues.
This talk details how Tencent Games leverages AI to transform its data governance from rule‑based, passive processes into a semantic, service‑oriented paradigm, addressing resource waste, low collaboration efficiency, and scalability challenges while delivering measurable improvements in cost, speed, and asset quality.
This guide breaks down a 103‑minute Codex tutorial into practical steps, showing how to organize projects, run multiple agents in parallel, and turn one‑off prompts into reusable Skills and automated workflows for AI‑assisted software development.
This article provides a Bash script that automatically gathers Linux system information—including OS details, uptime, CPU and memory usage, disk utilization with tiered alerts, network interfaces, top memory‑consuming processes, key service status, pending updates, recent error logs, load average, TCP connections, and zombie processes—and shows how to schedule it with cron for daily reporting.
This guide presents 35 concrete Claude Code techniques—each with a ready command or prompt—to streamline project bootstrapping, session handling, code quality, architecture, API design, automation, debugging, and recovery for faster, more reliable software development.
OpenAI’s new ChatGPT Workspace Agent preview transforms the chatbot from a passive assistant into an autonomous digital employee that can fetch data, run analyses, generate reports, and interact with enterprise systems, promising higher ROI for businesses while raising security, ethical, and employment concerns.
This article presents 35 hands‑on Claude Code techniques, each paired with a ready‑to‑use command or prompt, covering project initialization, session management, code quality, architecture review, automation, documentation, dependency handling, debugging, and recovery to help developers harness the AI coding assistant efficiently.
The author recounts how a bare‑bones Claude implementation missed edge cases, then introduces ten open‑source Claude Code Skills that embed a disciplined workflow—brainstorming, planning, execution, TDD, systematic debugging, parallel reviews, git worktrees, and diagram generation—showing installation commands, real‑world examples, and concrete benefits.
This comprehensive guide walks you through Claude Code’s market dominance, core design philosophy, step‑by‑step installation, a complete reference of basic and advanced CLI commands, slash commands, keyboard shortcuts, work modes, and real‑world workflows, helping developers unlock the full power of the AI‑driven programming assistant.
This guide shows how to streamline Python API testing by using ten practical decorators—covering automatic retries, timing, token injection, detailed logging, environment skipping, schema validation, timeout enforcement, cleanup, HTTP recording, and concurrent stress testing—each illustrated with real‑world code examples and usage patterns.
This guide explains what Agent Skills are, how they differ from traditional prompts, the three core design mechanisms, step‑by‑step creation of a Skill—including file structure, YAML metadata, and markdown instructions—plus advanced tips, real‑world use cases, and troubleshooting advice.
This article analyses the evolution of software engineering, examines the U.S. Department of Defense’s distributed software‑factory network, identifies governance and integration challenges for large defence organisations, and proposes a “total‑branch” design that unifies platform, process and team structures to achieve scalable, secure DevSecOps delivery.
The article analyzes how leading internet companies embed AI agents across the entire data‑warehouse lifecycle to automate governance, presenting real‑world case studies from Alibaba, ByteDance, JD.com and Tencent, and quantifies benefits such as over 65% reduction in manual effort, 50% drop in metric duplication, and a 40% boost in resource utilization.
The article explains how the emerging "Harness Engineering" paradigm—highlighted by OpenAI, Stripe and Anthropic—shifts AI development from prompt tweaking to building full control systems, promising ten‑fold efficiency gains, new architectural components, and both opportunities and risks for developers.
This article explains multi‑agent AI collaboration, outlines its core characteristics, breaks down the technical workflow of task decomposition, role assignment, communication and conflict resolution, compares leading frameworks, and showcases three practical scenarios—from financial report automation to game NPC ecosystems and intelligent customer service.
After months of using Claude Code, the author discovers that the real performance gap comes from the Skills you add—not the model itself—showing how ten carefully chosen Skills can transform Claude Code from a simple coding assistant into a versatile, repeatable digital teammate for browsing, summarizing, testing, refactoring, and more.
The article details how a three‑engineer team used OpenAI's Codex agents to generate an entire production‑ready software stack—including over a million lines of code, 1,500 pull requests, and a full CI/CD pipeline—in roughly one‑tenth the effort of manual coding, while describing the architectural, operational, and organizational adjustments required for such agent‑first development.
The article reviews four open‑source projects—BuilderPulse, AutoProber, wx‑favorites‑report, and awesome‑claude‑design—that automate daily research, hardware probing, personal data visualization, and design system creation, helping indie developers cut hours of repetitive work each week.
The article explains how conventional "smart" apps merely react to user commands, while AI Agents combine large language models, tool‑calling capabilities, and explicit goals to autonomously plan, act, and iterate, offering a new software paradigm with both promising use cases and current limitations.
This article provides an in‑depth, eight‑dimension comparison of Hermes Agent and OpenClaw, examining their core philosophies, learning abilities, integration options, deployment ease, security, standout features, overall strengths, and guidance on selecting the right AI agent for different user scenarios.
The article deeply compares shift‑left testing with traditional testing across five dimensions—goal orientation, participants, timing, technical means, and quality metrics—showing how early defect prevention, cross‑functional collaboration, embedded quality checkpoints, automation, and measurable outcomes can dramatically reduce defects and accelerate delivery.
The report analyzes recent global data on Agentic AI in the workplace, highlighting rapid adoption forecasts, job impact numbers, practical implementation steps, successful case studies across finance, healthcare, and manufacturing, and the governance risks that could derail projects.
Claude Code Game Studios is a virtual game‑studio framework that assembles 49 AI agents, 72 slash commands, and 12 automation hooks to automate the entire game‑development pipeline—from concept brainstorming to release—cutting a typical two‑week design phase down to 2‑3 days and supporting Unity, Unreal, and Godot.
This guide breaks down Claude Code’s 50‑plus commands into three logical categories, highlights the top ten daily‑use commands with concrete examples and code snippets, and walks through advanced tricks, shortcut keys, hidden options, and a full‑day automation workflow to dramatically boost developer productivity.
This article introduces Claude Code, an agentic command‑line AI coding assistant, explains its core features, walks through installation via Node.js, demonstrates a full Markdown editor project using Vue3, and details built‑in commands that streamline development tasks.
Learn how to design, write, test, and deploy reusable Claude Skills—custom instruction sets that automate document processing, code review, content creation, and data handling—by defining goals, crafting SKILL.md, adding scripts, creating trigger phrases, and measuring performance with concrete examples.
Amid widespread claims that AI will replace programmers, the article argues that current AI demos are limited to simple apps, while real software engineering requires deep problem definition, architecture design, and operational judgment—skills AI cannot replicate, making programmers' cognitive expertise more valuable than ever.
The article presents a Claude AI Skill that automatically creates detailed, color‑coded architecture diagrams as standalone HTML files, explains its design system, shows installation options via manual zip or Skills Hub, and demonstrates fast generation and iterative editing through simple prompts.
Learn how to turn daily repetitive Claude Code prompts into reusable Skills by identifying repeatable workflows, extracting five key Skill traits, applying a four‑step creation process, and iterating through observation, refinement, structuring, validation, and continuous improvement, illustrated with a real code‑review case study.
The author argues that traditional coding is dying as AI-powered tools such as Cursor enable non‑technical users to build and deploy functional software, highlighting faster development cycles, lower costs, and a shift in power dynamics that could reshape the future of programming.
The article analyzes Anthropic’s Co‑work, showing how the new AI collaboration system moves beyond answering questions to actively managing emails, calendars, documents, and Slack, turning fragmented digital tools into a unified workflow that lets knowledge workers treat AI as a true partner rather than a simple query engine.
An AI Agent is a large‑model system that can perceive its environment, plan steps, invoke tools, and remember past interactions to autonomously achieve user‑specified goals, distinguishing it from simple chatbots that only answer questions.
