Going further
LangGraph — Thinking in LangGraph
The mental model behind app-driven orchestration: explicit graphs, state machines, and developer-defined control flow. Includes the email-triage workflow example.
https://docs.langchain.com/oss/python/langgraph/thinking-in-langgraphUnix Was a Love Letter to Agents — Vivek Haldar
Argues that the Unix philosophy — small tools, text interfaces, composition — aligns perfectly with how LLMs work. "An LLM is exactly the user Unix was designed for."
https://vivekhaldar.com/articles/unix-love-letter-to-agents/Vercel — How to build agents with filesystems and bash
Practical guide to the filesystem-and-bash pattern. "Maybe the best architecture is almost no architecture at all. Just filesystems and bash."
https://vercel.com/blog/how-to-build-agents-with-filesystems-and-bashFrom "Everything is a File" to "Files Are All You Need" (arXiv 2025)
Academic paper arguing that Unix's 1970s design principles apply directly to autonomous AI systems. Cites Jerry Liu: "Agents need only ~5-10 tools: CLI over filesystem, code interpreter, web fetch."
https://arxiv.org/html/2601.11672Turso — AgentFS: The Missing Abstraction
Argues for treating agent state like a filesystem but implementing it as a database. "Traditional approaches fragment state across multiple tools—databases, logging systems, file storage, and version control."
https://turso.tech/blog/agentfsHow Claude Code is built — Pragmatic Engineer
Deep dive into Claude Code's architecture. "Claude Code embraces radical simplicity. The team deliberately minimizes business logic, allowing the underlying model to perform most work."
https://newsletter.pragmaticengineer.com/p/how-claude-code-is-builtWhat I learned building an opinionated and minimal coding agent — Mario Zechner
The author of Pi SDK on building a coding agent with under 1,000 tokens of instructions and no elaborate tool set. "If I don't need it, it won't be built."
https://mariozechner.at/posts/2025-11-30-pi-coding-agent/Agent Design Is Still Hard — Armin Ronacher
Building production agents requires custom abstractions over SDK primitives. "The differences between models are significant enough that you will need to build your own agent abstraction." Covers cache management, failure isolation, and shared filesystem state.
https://lucumr.pocoo.org/2025/11/21/agents-are-hard/Minions: Stripe's one-shot, end-to-end coding agents — Alistair Gray
Stripe's homegrown coding agents that operate fully unattended — from task to merged PR — producing over 1,000 merged PRs per week. Orchestrates across internal MCP servers, CI systems, and developer infrastructure.
https://stripe.dev/blog/minions-stripes-one-shot-end-to-end-coding-agentsThe two patterns by which agents connect sandboxes — Harrison Chase
Agent IN sandbox (runs inside, you connect over the network) vs sandbox as tool (agent runs locally, calls sandbox via API). Each has different trade-offs for security, iteration speed, and coupling.
https://x.com/hwchase17/status/2021261552222158955