ARCHIVED · OCTOBER 2025
October 2025
The Agentic Design Library as published in October 2025 — preserved exactly as it appeared on the homepage that month. Reading list of 9 essay-style pieces.
One Useful Thing
October 22, 2025
The Shape of the Thing
Ethan Mollick
Mollick on the emerging shape of AI work. The contours of what frontier models do well, where they fail, and how those edges are migrating month over month.
philosophyfrontier modelsarXiv
October 12, 2025
Fundamentals of Building Autonomous LLM Agents
Trends in Autonomous Agents (TUM seminar)
Technical report surveying the architecture and implementation methods of LLM-powered autonomous agents. Perception, reasoning, planning, memory, and execution as the canonical subsystems.
researcharchitectureAhead 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 agentsAnthropic
September 29, 2025
Effective Context Engineering for AI Agents
Anthropic Engineering
Context engineering as the primary lever for agent behavior. Structured note-taking, compaction, memory tools, and tool-result clearing — the techniques that keep long-running agents coherent without prompt thrash.
context engineeringmemorytool useAhead of AI
September 10, 2025
Beyond Standard LLMs
Sebastian Raschka
Deep-dive on what makes contemporary LLM systems different from the 2023 baseline — tool use, memory architectures, post-training on agent trajectories, and the shift in how agents are evaluated and tuned.
technicalLLMsarchitectureArtificial Intelligence Review (Springer)
September 1, 2025
Agentic AI: A Comprehensive Survey of Architectures, Applications, and Future Directions
Peer-reviewed survey
Academic survey of agentic AI. Taxonomies of agent architectures, deployment patterns across domains, evaluation methodology, and open research directions.
researchsurveyacademicAnthropic
August 12, 2025
Managed Agents
Anthropic Engineering
Anthropic's framing of managed agents as long-running services. Lifecycle management, resumption, persistence, and the operational surface around durable agent execution.
managed agentsproductionlifecycleAnthropic
June 13, 2025
How We Built Our Multi-Agent Research System
Anthropic Engineering
Engineering retrospective on Anthropic's internal multi-agent research system. Orchestrator-worker patterns, evaluation, where multi-agent helped and where it didn't.
multi-agentproductioncase studyAnthropic
December 19, 2024
Building Effective Agents
Anthropic Engineering
The canonical production-agents essay. Five composable workflow patterns — prompt chaining, routing, parallelization, orchestrator-workers, and evaluator-optimizer. Core argument: simple patterns beat complex frameworks in production agent systems.
design patternsarchitectureproduction