Posts

This is the Day 2 companion exercise. Complete Day 1 first. Yesterday you ran your first API call through DeepSeek’s official API. Today you do one thing: switch to a different platform, change two parameters in the same code, and run it again. You’ll see that learning one platform’s API means you’ve learned them all, as long as they’re compatible with the OpenAI interface. What Is an Aggregator Platform An aggregator platform is a middle layer. You register one account, top up once, and get access to dozens of AI models (OpenAI, Anthropic, Google, etc.) without signing up at each official platform separately. ...

Why I Need Three OpenCode Configs I have three opencode.json files in my ~/.config/opencode/ directory. The reason is simple: I wanted to run oh-my-openagent (omo from here on) and oh-my-opencode-slim (oms from here on) side by side, comparing them to understand where each one’s boundaries lie. omo is the full version—it comes with a batch of built-in agents (Sisyphus, Atlas, Prometheus, Oracle, Explore, Librarian, Metis, Momus, etc.), plus the ones I register on demand. The core is the fallback chain and the Sisyphus orchestrator: throw a refactoring task at Sisyphus, and it breaks the task down for Prometheus to plan, Atlas to execute the plan and distribute subtasks, Explore to search code, Oracle to analyze, then Sisyphus aggregates the results. oms is the slim version—it also has an orchestrator as the main agent responsible for executing tasks, but the difference is in the review phase: oms uses council multi-model consensus, where multiple councillors review results in parallel, and the Council agent synthesizes outputs from all councillors to reach a final conclusion. ...

This is the Day 1 companion exercise for the AI Path L1→L2 Upgrade Guide. Read Part 1 first, then come back here to practice. Today you do exactly one thing: run hello_api.py from Part 1 and see AI reply in your terminal. Prerequisites Complete these steps from Part 1 (skip if already done): Register a DeepSeek developer account (Part 1, “Register for API Accounts”) Get your API key and save it to a .env file (Part 1, “API Key Safety”) Install uv and Python 3.12 (Part 1, “Install Python”) Create a virtual environment and install dependencies (Part 1, “Create a Virtual Environment”) Confirm your project directory looks like this: ...

Series: AI Agent Experiment Methodology (Part 3) Previous: The Experiment Design Was Fine, So Why Did the LLM Still Fail? TL;DR: In a double-blind experiment, Variant B won 4/4 scenarios and generated clean data. But design review revealed the rubric had 3/8 dimensions directly testing the target variable, exceeding the 1/3 ceiling and nearly becoming a self-fulfilling prophecy. In a separate validation, one scenario scored perfectly while another exposed a defect—if we had run only the first, the defect would have shipped. Both traps were caught by reviewing the design, not by running the experiment. ...

TL;DR: This is Part 1 of the “AI Path L1→L2 Upgrade Guide” series. Four parts total, one per week of practice. This article takes you from chat windows to APIs, automating your AI interactions through code, laying the foundation for batch processing and autonomous task-execution AI. Introduction: From “I Ask AI” to “Programs Ask AI” If you finished the L0→L1 graduation checklist, you might remember one line from the graduation post: “Register for an API account and use Python to print your first AI reply.” Today is that day. ...

Series: AI Agent Experiment Methodology (Part 2) Part 1: How to Use Double-Blind Experiments to Validate Skill Changes TL;DR: Round one of the double-blind experiment: B won 3/4 scenarios but failed the magnitude filter. Verdict: “insufficient evidence.” Investigation revealed S1-A’s output was polluted by terminal color codes, and the scorer diligently scored 8 dimensions on ANSI garbage. After reconstructing the execution context, B won 4/4. The failure wasn’t in the experiment design—it was in how sub-agents’ context boundaries were constructed. ...

📖 This is Part 5 of 5 in the “AI Path L0→L1 Upgrade Guide” series: Series Navigation + Graduation Checklist. Series Navigation Part Topic Core Content Part 1 Understanding Your Tools LLM fundamentals (not a search engine), working memory vs. long-term memory, mainstream platforms and specialized tools Part 2 From Vague Questions to Precise Instructions The RBGO prompt framework, Chain-of-Thought reasoning, format constraints Part 3 Turning AI Into Your Collaboration Partner Iterative follow-up questions, context management (new conversations / progress summaries / chunked processing), role-playing Part 4 Building Your Personal System Prompt library, scenario-to-tool mapping (international and China options), layered knowledge management Part 5 Graduation & Next Steps L1 graduation checklist, L1→L2 dual-path preview ...

TL;DR: You changed a skill. How do you know it’s actually better, not just confirmation bias? I ran a double-blind experiment: two versions, four scenarios, independent blind scoring. The scorer saw X=2.44, Y=2.41 and said “can’t tell them apart.” After unblinding: simplified version won 4/0. Series: AI Agent Experiment Methodology (Part 1) Next: The Experiment Design Was Fine. The LLM Still Failed. The 0.03 Gap I shortened a review skill from 159 lines to 89 lines. Wanted to verify the simplified version actually worked better, so I ran a double-blind experiment. ...

The biggest obstacle to building a Prompt library isn’t the tool. It’s knowing how to organize it. Yesterday you picked 5 Prompts; today I’ll show you a complete real template. Directory Structure This structure uses the Markdown folder approach. You can copy it directly: prompt-library/ ├── writing/ │ ├── email.md │ ├── article-summary.md │ └── ... ├── analysis/ │ ├── data-interpretation.md │ ├── case-breakdown.md │ └── ... ├── daily/ │ ├── meeting-notes.md │ └── ... └── README.md (global notes) The record format for each Prompt: ...

Today’s Practice From your recent AI conversations (coding, writing, analysis), pick 5 prompts that actually worked well. Record them using the template from Part 4: Original Prompt + Effectiveness + Iteration. Where you record them doesn’t matter. A notes app, Notion, or a plain text file all work. Don’t overthink the tool. If you can’t find your chat history, spend 20 minutes creating 5 prompts you’ll definitely use at work. For example: “Check the edge cases in this code,” “Rewrite this technical article for beginners,” “Extract the 3 main issues from these 100 pieces of user feedback.” ...