Latest
One Person, a Whole Team: How aSPARK Turns Claude Code into an Agile Delivery Process
Why I built an agile AI team as a Claude Code plugin, how the SPARK loop works, and what happened when I ran a real feature through it.
Blog
Filter by Tag:
-
AI Beyond Language Models: World Models, Embodied Systems, and Physical AI
A practical way to categorize modern AI systems beyond LLMs, from perception and simulation to action in the physical world.
- ai-models
- world-models
- physical-ai
-
Qwen 3.6 vs Current Anthropic Models Performance, Cost, and Takeaways
A practical comparison of Qwen 3.6 and Claude 4.x on benchmark performance, token economics, and model selection strategy.
- llm
- model-comparison
- cost-optimization
-
Long-Form LLM Generation With Low Token Cost An Engineering Report
Engineering lessons from production-like long-form LLM pipelines with bounded retrieval, segmentation, and strong observability.
- llm
- prompt-engineering
- retrieval
-
From Prompt Chaos to Agent Flow My Biggest Leverage Building This App
Why moving from manual prompt juggling to agentic end-to-end workflows significantly improved my development efficiency.
- agents
- workflow
- ai-applications
-
Agent Workflow in Practice
A practical workflow for planning, execution, and review with AI agents.
- agents
- best-practices
- workflow