Peppe's Working Notes
Search
Ctrl K
Peppe's Working Notes
Search
Ctrl K
DRAWINGS
Still Life Exercise - 04 Jan 2026
Still Life Exercise - 28 Dec 2025
"LLM as a judge" grading with a rubric gives more consistent results when evaluating Reflection (Agentic pattern)
$Building software products with AI
$Designing Agentic Workflows
$Evolution of roles in software engineering
Agentic AI can be less or more autonomous
Agentic AI works better for well know, linear processes
Agentic design patterns
Agentic workflows are only as good as their weakest component + error analysis
Agents can be evaluated objectively or subjectively
Agile practices only make sense when iteration is cheap
Coding with LLMs makes me think more
Context compression for better code generation
Digital Gardening, Slow Social Media & Intro
Do software systems integrating with AI still benefits from good software architecture?
Methods, methodologies and mindset
Peppe's Working Notes
Reflection (Agentic Pattern) can use external feedback from tools to improve output
Reflection (Agentic Pattern) consistently outperforms direct generation on a variety of tasks
Slow feedback loops and expensive computing forced optimization for machines over people
Software development is complex, not complicated
The correct response to complexity is probe, sense, respond
The increasing in uncertainty drove each era of software development practices
There are no best practices in complex systems
Select a result to preview
Reflection (Agentic Pattern) consistently outperforms direct generation on a variety of tasks