Deep Agents

Before writing your first deep agent, you need three decisions: which orchestration tool to use, how checkpoint granularity affects crash recovery, and how to design for idempotency. Get these wrong and you ship a system that duplicates side effects, loses hours of work on crashes, or burns budget silently.

Deep Agents is LangChain's batteries-included agent harness — planning, virtual filesystem, subagent spawning, and context management on top of LangGraph. The decision to reach for it over create_agent is the most important one you will make before writing a single line.

Context engineering is the discipline of keeping the right information in the agent's context window at every step. This article breaks down the four strategies Deep Agents provides — filesystem offloading, auto-summarization, subagent isolation, and progressive disclosure — explains the real APIs behind each, and covers the failure modes you will hit in production.

A decision-first guide to customizing Deep Agents: when to add custom tools, which filesystem backend fits your persistence needs, how to stack middleware correctly, and how to configure subagents without paying for a Sonnet when Haiku will do.

ACP is the open standard that lets any coding agent work in any supporting editor — built by Zed and JetBrains in Oct 2025. This article covers when ACP adds value over built-in IDE AI, how the protocol actually works, how to build an ACP-compatible agent with deepagents-acp, and what breaks in production.

Fleet is LangSmith's no-code agent builder (rebranded from Agent Builder, March 2026). The critical first decision is the authorization model: Assistants (user's OAuth, private inbox) vs Claws (fixed credentials, shared access). This article covers that decision, channels, schedules, Skills, the Tool Server, observability, permissions, cost model, and self-hosted deployment.

Which coding agent should you actually use? A decision-first comparison of 9 agents — Claude Code, Cursor, Codex CLI, GitHub Copilot, Deep Agents CLI, Windsurf, Devin, Aider, and Augment Code — with April 2026 model versions, benchmark data, the scaffold-vs-model insight, failure modes, and cost reality.

Most teams should NOT build a custom coding agent — Claude Code or the Deep Agents CLI with skills files is usually sufficient. This article tells you when building custom is justified, walks through the correct setup, and covers the failure modes, cost math, and evaluation strategy that actually matter in production.

Agentic tools handle most repetitive coding automatically via context files — manual prompting skill pays off for novel patterns, ambiguous requirements, and custom agent system prompts. This article covers when to invest, which techniques consistently move the needle, how to measure whether your prompts actually work, and the failure modes that waste the most engineer time.