ARCHIVED · DECEMBER 2025
December 2025
The Agentic Design Library as published in December 2025 — preserved exactly as it appeared on the homepage that month. Reading list of 9 essay-style pieces.
One Useful Thing
December 31, 2025
What Just Happened
Ethan Mollick
Mollick's running essay on the recent inflection — what just happened in agent capability, and what it means for operators trying to keep up.
philosophyinflectionAndrej Karpathy
December 29, 2025
2025 LLM Year in Review
Andrej Karpathy
Karpathy's year-end recap of LLM developments in 2025 — what shifted, what stuck, and what the agentic engineering inflection point looks like up close.
retrospectiveagentic engineeringMarkTechPost (Anthropic announcement)
December 21, 2025
Bloom: An Open-Source Agentic Framework for Automated Behavioral Evaluations
Anthropic
Anthropic's open-source agentic framework for automated behavioral evaluations of frontier models. A practical look at how to evaluate agent behavior at scale rather than relying on hand-crafted prompts.
evaluationopen sourcesafetyLatent Space
December 20, 2025
The 2025 AI Engineering Reading List
swyx
swyx's curated 2025 AI engineering reading list — the papers and essays that actually shifted how production teams build with AI in the past year.
curationresearchLatent Space
December 15, 2025
Software 3.0: Software in the Age of AI
Andrej Karpathy (talk transcript)
Karpathy's follow-up to Software 2.0: three eras of software (1.0 hand-written, 2.0 trained, 3.0 prompted). Natural language as the new programming surface; intent specification as the new skill.
frameworkphilosophyagentic engineeringMindStudio
December 10, 2025
Karpathy's Sequoia Talk: 5 Predictions About Agentic Engineering
Andrej Karpathy (talk recap)
Recap of Karpathy's Sequoia talk: five predictions about agentic engineering. Intent specification, judgment, review-as-skill, and the shift from typing code to managing systems that write it.
predictionsagentic engineeringEthicalML
December 5, 2025
Awesome Agentic Engineering Resources
EthicalML Maintainers
Curated practitioner resources for agentic engineering — tools, papers, evaluation frameworks, governance considerations, case studies.
curationresourcesMicrosoft Cloud Blog
December 4, 2025
Single Agents to AI Teams: The Rise of Multi-Agentic Systems
Microsoft
Microsoft's framing of the shift from single-agent products to multi-agentic teams. Coordinating agents, sub-task allocation, and what enterprise deployment looks like.
multi-agententerpriseAhead of AI
October 8, 2025
Components of a Coding Agent
Sebastian Raschka
Long-form technical essay on how production coding agents are built: harness, tools, memory, repo context, and how the pieces compose. Six building blocks of a coding agent, with the harness as the binding constraint.
technicalagent harnesscoding agents