🗺️ Arno's AI Map: A Guide to AI Tools, Workflows & Best Practices 2026

🗺️ AI Generated Artifact of This Article

Optimizing AI Workflows: Key AI Working Procedures

To effectively harness artificial intelligence, understanding different AI working procedures is crucial. These models define how humans and AI collaborate for optimal productivity:

• Human First, AI Assist: human is focusing on the high-level tasks and design to instruct AI for high-level decision making or cross-multiple domain tasks.
• AI First, Human Assist in Sync: human design the task and instruct AI to do the task in a synchronous way, and human is focusing on revise and review the AI's work till the task is done.
• AI First, Human Assist in Async: human design the task and instruct AI to do the task in an asynchronous way, AI using Agentic approach to do the task, and human is focusing on later review and revise the AI's work till the task is done. These tasks are usually self-contained and not coupled with other domains, so AI can work independently.

your 24-hour copilot ~

Let's take software development as an example:

Human First, AI Assist

• App production, tech-architecture, and market high-level design within the artificial intelligence landscape.
• Core modules, core features, and core functions design.
• Key-decision making about the technology stack, architecture, and modules features, a vital part of AI best practices.
• Complex problem solving and reasoning, such as systematic and systemic reasoning.
• ...

In this mode, Arno try to create a systemic and systematic approach to leverage the power of AI and personal context engineering to do the high-level design and decision making, and then use the AI to assist in the low-level tasks. This approach is central to productivity with AI.

AI First, Human Assist in Sync

• app development, coding, and programming in specific modules
• write PRD, design documents, and technical documents
• code review, PR review, and design review
• software development lifecycle, such as devops, CI/CD, and testing
• ...

In this mode, dedicated AI tools are used to assist in the coding and programming tasks, such as Cursor, Github Copilot, and V0. These tools are designed to work in sync with human developers, providing real-time assistance and suggestions.

AI First, Human Assist in Async

ALL RUNNING in the background, passively and asynchronously.

• Do market or product research using specialized AI tools.
• Write unit-test and integration-test as part of an AI-driven development cycle.
• Refactor modules, features, and functions, optimizing AI workflows.
• Batch job on data processing or information processing.
• ...

In this mode, AI tools are used to work independently on specific tasks, such as Google Deep Research, Manus and Google Jules which can run in the server-end or background without human intervention. These tools are designed to handle specific tasks and can work asynchronously, allowing for greater efficiency and productivity with AI.

Practical AI Application Scenarios & Tool Recommendations

This section explores various scenarios where AI can be applied, along with recommended AI tools and platforms that fit each AI workflow.

Daily QA

Daily general QA task -> Gemini Pro / ChatGPT / Claude, deep understanding and reasoning

General knowledge and information retrieval.

• personal long-term memory matters in those daily QA tasks.
• add your preferred instruction to the AI to help it to do the daily simple task better.
• use search and tools to work with app and real-time info and data.
• use local file and chunks of text as extra context to work with.
• pick long-time reasoning for relatively complex tasks.
• for more complex or important question (tasks), use multi-models in comparison and combination to work with. (e.g. use strongest models from OpenAI, Anthropic, Google, etc.)
• use agent-mode for files, images, code evaluation based tasks.

Dedicated Tasks

For dedicated tasks, create Agent or Agentic Workflow to work with.

• use GPTs or GEMs(Gemini Agentic) to add system prompt, files (context), and tools to work with.
• for complex workflow, use Code based, or Workflow based agent to complete the task.
• use Alfred liked quick launch and quick action to find your dedicated agents and workflows.

Research, Study & Learning

For knowledge aggregation and research.

• use DeepResearch tools to combo(OpenAI + Google) to do the research and study for more perspective and insights.
• use Workspace to organize related context info in a project, using Google Notebook ML is a good choice.

Arno's SOP for research types of topics.

• create workspace for context gathering and basic QA (in one workspace)
• elaborate topics / problems with QA linked to thinking models, your thoughts, ideas, and experiences (Human First, AI Assist), ask interesting and deep questions and try to use AI to solve and combine your first-thoughts
• DeepResearch topic (shallow, deep x rich and poor context)
• generate basic Artifact (article + webpage)
• DeepResearch + Advanced Models to summary / organize and elaborate the topic
• integrate those results together -> Generate Final Artifact (WebPage or Article)
• [optional] add all of those materials and generated content or cited source into a Google Notebook ML for further analysis and insights

Coding & Programming: Tools and Techniques

Cursor x Cli Tools (ClaudeCode / GeminiCli / Codex)

Programming and coding tasks.

• vibe-coding & code-generation (codex, augment) for me, VSCode is the HUB for various of agentic tools and AI powered services and MCP
• tabs engineering, quick editing contents as needed
• software-development-lifecycle -> devops agentic tools
• use workspace / project as context QA (in ChatGPT)
• pick plugins / MCPs to connect to external services and tools
• encapsulate your SOPs of dev, and business workflows to skills

AI in Media Generation: Images, Video, and Audio

• image generation -> GPT / Nano Banana Pro of Google
• video generation -> Seedance (Bytedance) / Sora (OpenAI) / Grok's mini video generation
• audio generation
• 3D objects generation

Real Life Scenarios

Meta Thoughts

Arno is crafting eThink and eGnite app to let AI do the meta-thinking for daily thinking process and elaboration process.

I'm working in progress to craft them out 🧑‍🍳 ~

Writing & Editing

• use Cursor first approach, for text-completion and editing, all in markdown.
• create GPT like writing assistant to help me write and improve the writing quality.

English Learning

• talk and interact with ChatGPT often, to practice your listening and speaking skills.
• instruct ChatGPT to always respond in both English and your own mother language at the same time for reading and writing skills.
• for each turn of conversation, ask ChatGPT to summarize all core-concepts and key-points in the conversation memorize and keep track of your memory use Ebbinghaus Forgetting Curve to solidate your memory.

Information and Horizon

WIP

idea that sparks

• dig deeper with deep research: one research -> research conception and topic -> deeper research and build the zoom-in and zoom-out effect

Context Engineering: The Key to AI Productivity

WIP -> new article to write

Related

• 🪄 vibe coding bp

Trace

• 2025-04-20: initial version
• 2025-05-10: upgrade some more details and scenarios for AI to use and mapping to the tools and models
• 2025-05-23: add AI Working Procedure for better understanding of the AI working procedure and how to use the tools and models
• 2025-09-05: upgrade to the recent tools / platforms / services
• 2025-12-02: upgrade to the recent tools / platforms / services and add more details and scenarios for AI to use and mapping to the tools and models
• 2026-02-24: add deep-scenario driving context and upgrade more models and tools, services and platforms.