Artificer’s Grimoire — Edition 1 · March 9, 2026
Context engineering has solidified as the defining discipline of production agent work, SDD tooling is fragmenting into three distinct philosophies, and the Agentic AI Foundation is quietly becoming the governance layer for the protocols that matter.
Must Read
Context Engineering for AI Agents: Lessons from Building Manus
The Manus team shares hard-won lessons from four complete rebuilds of their agent framework. The standout insight: KV-cache hit rate is the single most important production metric for agentic workloads. With a 100:1 input-to-output token ratio and a 10x cost difference between cached and uncached tokens on Claude Sonnet, cache optimization is an economic concern as much as a performance one.
Why it matters: The 10x cost differential between cached and uncached tokens means your context engineering decisions directly impact per-task economics. For anyone running agents in production, the takeaway is concrete: keep your prompt prefix stable. Even a single-token change at the beginning of your context invalidates the cache for everything that follows. This should be a hard constraint in any agent system design, not an optimization you get to later.
Google ADK: Architecting Context-Aware Multi-Agent Systems for Production
Google’s ADK team codifies three design principles for production context management: separate storage from presentation, use explicit named transformations (not ad-hoc string concatenation), and scope context by default so agents must explicitly reach for more information rather than being flooded.
Why it matters: The “scope by default” principle is the most actionable insight here. Each agent should get the minimum context required and reach for more via tools — the opposite of the “dump everything into the context window” approach that most framework-based systems default to. The ADK’s tiered storage model (Sessions vs working context) is worth studying as a reference for anyone designing agent state management.
Understanding Spec-Driven Development: Kiro, spec-kit, and Tessl (Böckeler)
Birgitta Böckeler’s hands-on evaluation of three SDD tools is the most honest practitioner analysis in the space. Key findings: agents frequently ignored spec instructions despite having them in context; agents also went overboard eagerly following other instructions; and she was frequently confused about when to stay functional vs. add technical details. Her conclusion is telling: “To be honest, I’d rather review code than all these markdown files.”
Why it matters: This is a reality check for the SDD movement. The failure modes she describes — agents ignoring context, over-following instructions, functional/technical confusion — are the exact problems that governance layers, human review gates, and phased decomposition are designed to catch. If you’re adopting SDD, her critique argues for breaking specs into right-sized, session-scoped chunks rather than verbose up-front designs. The tooling isn’t mature enough to trust with a 50-page spec.
12 Factor Agents: Principles That Actually Ship
Dex Horthy’s 12 Factor Agents has become the de facto philosophical foundation for production agent engineering. The core insight: most successful AI products combine deterministic code with strategically placed LLM decision points rather than running as pure agentic loops. The “dumb zone” heuristic — context window utilization past 40% degrades performance — comes from Horthy’s separate Advanced Context Engineering for Coding Agents talk rather than the repo itself.
Why it matters: This is the clearest articulation of what production agent architecture actually looks like. Own your control flow in deterministic code (Step Functions, state machines, workflow engines). Own your context window (CLAUDE.md, structured prompts). Keep agents small and focused. Use tool calls to contact humans at decision boundaries. If your agent infrastructure doesn’t enforce these principles, you’re building a demo, not a product.
Worth Scanning
-
State of AI Agents 2026 (LangChain) — 1,300+ respondents, 57% have agents in production. Quality is the #1 barrier at 32%, surpassing cost. 89% have observability. Context engineering at scale cited as an ongoing difficulty by large enterprises.
-
Agentic AI Foundation Formed (InfoQ) — MCP, AGENTS.md, and goose donated to Linux Foundation. AWS, Microsoft, Google, Bloomberg, and Cloudflare as Platinum members. A Hacker News commenter quoted in the piece argues the foundation may be premature for a protocol barely a year old.
-
Microsoft Agent Framework RC (Microsoft) — Successor to AutoGen hit Release Candidate Feb 2026, merging multi-agent patterns with Semantic Kernel. Supports A2A, MCP, and AG-UI out of the box. Microsoft has GA slated for the coming weeks, without a firmer date.
-
arXiv: Context Engineering for AI Agents in OSS — Study of 466 open-source projects using AGENTS.md. Finds no established content structure — huge variation in prescriptive vs descriptive vs prohibitive approaches. Useful baseline for understanding community adoption.
-
SDD on Wikipedia — SDD now has a Wikipedia page. Traces roots to 2004 synergy of TDD and Design by Contract.
-
OpenAgents: Native MCP + A2A — Bills itself as the only framework with native support for both protocols — a vendor claim the Microsoft Agent Framework item above already contradicts. Interesting for agent interoperability patterns but early-stage.
-
AI Coding Landscape 2026 (ToolShelf) — Tracks 204 tools. Claude Code rated highest at 76. 95% open-source. The biggest shift: terminal-native agents composing with existing tools (pipes, scripts, CI) over IDE plugins.
New Tools & Repos
-
Agent-Skills-for-Context-Engineering — Comprehensive collection of context engineering skills for agent systems. Referenced by Peking University’s Meta Context Engineering research.
-
GitHub Spec Kit — GitHub’s SDD scaffolding CLI. Downloads templates, sets up spec-driven scaffolding. Experimental (v0.1.x).
Papers
- Context Engineering for AI Agents in Open-Source Software — Mohsenimofidi et al. — Preliminary study of AGENTS.md adoption patterns (the paper’s own framing). Analyzes content structure, presentation modes, and evolution over time across 466 projects.
Ecosystem Watch
-
OpenHands — 68.6K stars, $18.8M Series A. 70.4% on SWE-bench Verified in its official submission (a Claude Sonnet 4 configuration). Migrating from V0 to V1 architecture. Docker-based sandboxing with full browser automation. Positions itself as scaling from a single agent on a laptop to thousands in cloud infrastructure, with organization-level controls (role-based access, audit trails, quotas).
-
GitHub Copilot Coding Agent — Now assigns issues directly to coding agents. Autonomously writes code, creates PRs, responds to feedback. Enterprise-ready with audit logs and governance via Agent HQ.
-
Cursor Cloud Agents — Launched with dedicated VMs for each agent session. Agents test changes end-to-end before submitting PRs. Key UX insight: “only ask me for a review once it’s actually ready.”
The Long View
The convergence of SDD, context engineering, and 12 Factor Agents into a coherent discipline is the story of this period. A year ago, these were separate conversations. Now they’re clearly facets of the same problem: how do you make AI agents reliable enough to trust with production work?
The answer emerging from practitioners (not framework vendors) is surprisingly conservative: keep agents small and focused, own your control flow in deterministic code, treat context like a scarce resource, and put humans at the decision boundaries. These principles predate the industry names now being attached to them — and the teams that internalized them early are the ones shipping production agent systems today.
The protocol consolidation under neutral governance is worth watching closely — MCP and AGENTS.md inside the Agentic AI Foundation, A2A as its own separately hosted Linux Foundation project. If all three stabilize there, any well-architected agent infrastructure becomes a natural integration surface for all three. The teams investing in clean protocol boundaries now will have a significant advantage when these standards mature.
The Artificer’s Grimoire — weekly intelligence on harness engineering for agentic systems — a practitioner’s field guide, by Tim Schiller (Artificer Digital).