{"slug": "a-standard-for-building-production-ai-agents-installable-claude-code-skills", "title": "A standard for building production AI agents (+ installable Claude Code skills)", "summary": "Anthropic, OpenAI, Cognition, Sierra, LangChain and leading practitioners have jointly developed a canonical standard for building production-grade agentic products, codified in a new open-source repository. The standard establishes five core principles — including determinism by default and eval-driven development — alongside a 7-layer harness architecture and a 10-question decision checklist. The release includes installable Claude Code skills that operationalize the standard directly within the editor, addressing the gap between agent demos and systems that survive production deployment.", "body_md": "### A canonical standard for building production-grade agentic products — plus a Claude Code skill set that operationalizes it.\n\n*Distilled from the production practices of Anthropic, OpenAI, Cognition, Sierra, LangChain, and leading practitioners — 2024–2026.*\n\n** Read the Standard →** ·\n\n**·**\n\n[Install the Skills →](#-install-the-skills)**·**\n\n[Reference Implementation ↗](https://github.com/AlexDuchDev/AgenticMind)\n\n[Decision Checklist →](#-the-10-question-checklist)\n\nAn agentic product is not \"a product with AI.\"It is a product where part of the process is dynamically directed by an LLM within adeterministic architecturewithexplicit trust boundaries.\n\nMost teams ship agent demos. Few ship agents that survive contact with production. The difference is almost never the model — it's the **architecture, the harness, and the eval discipline** around it. This repo is the field-tested standard for that work, plus a set of [Claude Code skills](/AlexDuchDev/agentic-product-standard/blob/main/skills) that put it into your editor.\n\n[Why this exists](#why-this-exists)[The five principles](#the-five-principles)[What's in this repo](#whats-in-this-repo)[Reference implementation](#reference-implementation)[Install the skills](#-install-the-skills)[The Autonomy Ladder](#the-autonomy-ladder)[The five composition patterns](#the-five-composition-patterns)[The 7-layer harness](#the-7-layer-harness)[The 10-question checklist](#-the-10-question-checklist)[Production readiness — Definition of Done](#production-readiness--definition-of-done)[Anti-patterns](#anti-patterns)[Reading list](#reading-list)[Contributing](#contributing)[License](#license)\n\nFive principles converged *independently* across the production practices of the labs and the leading practitioners. They are the spine of every decision in this standard:\n\n| # | Principle | What it means |\n|---|---|---|\n| 1 | Determinism by default, agency by necessity |\nEvery degree of autonomy must be earned, not granted upfront. |\n| 2 | Architecture beats framework |\nPatterns outlive libraries. |\n| 3 | Harness > model |\n98% of reliability lives in the code around the LLM. |\n| 4 | Context engineering is the core discipline |\nWhat enters the context window determines everything. |\n| 5 | Eval-driven development is non-negotiable |\nNo measurement → no improvement. No trace review → no understanding. |\n\nThe single most important rule:Architecture is what remains when the model improves. The model is the variable, the harness is the constant. Invest proportionally.\n\n```\nagentic-product-standard/\n├── STANDARD.md                          ← product-level canon — design a multi-agent product\n├── AGENT_STANDARD.md                    ← single-agent operational standard — build one agent\n├── templates/                           ← copy-paste artifact-contracts (contracts, schemas, envelope, evals)\n├── examples/                            ← worked example: the AgenticMind reference implementation\n└── skills/\n    ├── agentic-product-architect/       ← skill: design & ship agentic PRODUCTS (master router)\n    │   ├── SKILL.md                      ← master: router + philosophy\n    │   ├── architecture-design/          ← autonomy ladder, 5 patterns, single vs multi\n    │   ├── context-engineering/          ← write/select/compress/isolate, the 40% rule\n    │   ├── harness-engineering/          ← the 7 layers around the LLM loop\n    │   ├── tool-design-mcp/              ← MCP-first, <20 tools, RAG-MCP, sandboxing\n    │   ├── memory-architecture/          ← Mem0 / Zep / Letta / LangMem / files\n    │   ├── durable-execution/            ← Temporal Workflow + Activity pattern\n    │   ├── eval-driven-dev/              ← Husain/Shankar pyramid + judge calibration\n    │   ├── framework-selection/          ← LangGraph / Claude SDK / OpenAI SDK / others\n    │   ├── production-readiness/         ← 12-point Definition of Done audit\n    │   └── antipatterns-review/          ← code review through 12 known failure modes\n    └── agent-builder/                    ← skill: build ONE production-grade agent\n```\n\nTwo tracks, one standard:\n\n**Build one agent**→ read, fill the`AGENT_STANDARD.md`\n\n, drive it with the`templates/`\n\nskill.`agent-builder`\n\n**Design a product**→ read, drive it with the`STANDARD.md`\n\nskill (multi-agent, orchestration, framework choice).`agentic-product-architect`\n\nThe docs are the *reference*; the skills are the *practice* — they auto-load the right guidance while you design, build, and review. Both skills share the same ten sub-skills.\n\n** AgenticMind** is the flagship reference implementation of this standard — an auditable, self-improving knowledge & memory layer for agents over MCP (Apache-2.0, Postgres + pgvector, headless Bun). It puts the standard's memory-architecture, context-engineering, tool-design/MCP, eval-calibration, durable-execution, and observability layers into running, tested code.\n\n| Repo | Use it when | |\n|---|---|---|\n| 📐 | agentic-product-standard (this repo) |\nYou're designing or building an agent / agentic product — the standard + skills tell you how. |\n| 🧠 |\n|\nYou need a knowledge & memory layer for your agent — a working implementation you can run. |\n\n→ Layer-by-layer [AgenticMind case study](/AlexDuchDev/agentic-product-standard/blob/main/examples/agenticmind-case-study.md).\n\nThe skills work with [Claude Code](https://claude.com/claude-code). Install both tracks (they share sub-skills).\n\n**Fastest — one command** (via [skills.sh](https://www.skills.sh)):\n\n```\nnpx skills add AlexDuchDev/agentic-product-standard\n```\n\n**Or copy them in manually — user-level (available in every project):**\n\n```\ngit clone https://github.com/AlexDuchDev/agentic-product-standard.git\ncp -R agentic-product-standard/skills/* ~/.claude/skills/\n```\n\n**Project-level (scoped to one repo):**\n\n```\nmkdir -p .claude/skills\ncp -R /path/to/agentic-product-standard/skills/* .claude/skills/\n```\n\nClaude Code discovers skills via each `SKILL.md`\n\nand its YAML frontmatter. Once installed: `agent-builder`\n\ntriggers when you set out to build, implement, or review **one** agent; `agentic-product-architect`\n\ntriggers for **multi-agent products**, an agent loop, or any major framework (LangGraph, CrewAI, OpenAI Agents SDK, Claude Agent SDK, Pydantic AI, AutoGen). Ask a focused question — *\"Mem0 or Zep?\"*, *\"how should I structure context?\"*, *\"review my agent code\"* — and the relevant sub-skill loads directly.\n\nNever start with \"build an agent.\" Start with *\"what is the minimum autonomy this task requires?\"* The cost of getting this wrong is asymmetric.\n\n| Level | What it is | Use when |\n|---|---|---|\nL0 · Single LLM call |\nOne prompt → one response | Classification, extraction, summarization |\nL1 · Augmented LLM |\n+ retrieval, + tools, + memory | Q&A over docs, simple assistants |\nL2 · Workflow |\nDeterministic code orchestrates LLM steps | Path is known; predictability matters |\nL3 · Orchestrator-Worker |\nLLM decomposes within a bounded graph | Parallelizable, breadth-first work |\nL4 · Autonomous Agent Loop |\nLLM chooses the next step until termination | Path cannot be enumerated; cost is acceptable |\n\nEscalation rule:do not climb to L+1 until L delivers≥90% pass rateon a curated eval set.\n\nCompose agentic products from these primitives *like Lego* — before reaching for a framework.\n\n**Prompt Chaining**— sequential decomposition (outline → draft → polish)** Routing**— classifier + dispatcher to a specialist** Parallelization**— fan-out of independent subtasks + aggregation** Orchestrator-Workers**— central planner + dynamic workers** Evaluator-Optimizer**— generator + critic in a loop until acceptance\n\n**Meta-principle:** first try to solve the task by composing these patterns in deterministic code. A full agent loop is the *last* resort.\n\nIn a production agent, the harness — everything *around* the LLM loop — is **98% of the code**.\n\n```\n┌─────────────────────────────────────────────┐\n│  7. Observability & Tracing                 │ ← log EVERYTHING\n├─────────────────────────────────────────────┤\n│  6. Evaluation Layer (CI gates)             │ ← block regressions\n├─────────────────────────────────────────────┤\n│  5. Human-in-the-Loop (notify/ask/review)   │ ← approval gates\n├─────────────────────────────────────────────┤\n│  4. Guardrails (input/output validation)    │ ← defense in depth\n├─────────────────────────────────────────────┤\n│  3. Durable Execution (Workflow + Activity) │ ← pause/resume/retry\n├─────────────────────────────────────────────┤\n│  2. Context & Memory Management             │ ← write/select/compress/isolate\n├─────────────────────────────────────────────┤\n│  1. Agent Loop (gather → act → verify)      │ ← the \"agent\" proper\n└─────────────────────────────────────────────┘\n              ↕ MCP / function calling\n```\n\nPermission boundaries are enforced by code, never by prompt.The Replit incident of 2025 — an agent wiped a production database for 1,200+ companies despite an explicit \"code freeze\" in its prompt — is the canonical proof. The model will ignore prompt-level restrictions under enough pressure. Code won't.\n\nRun this before drafting any architecture. It unblocks 80% of design debates.\n\n```\n□ What is the minimum autonomy level (L0–L4) that solves this?\n□ Can it be solved by composing the 5 patterns without a full agent loop?\n□ Is the task breadth-first (parallelizable) or depth-first (coherent)?\n□ What are the 3 failure modes that would lose user trust first?\n□ Where are the permission boundaries? What MUST the agent NOT do?\n□ Which constraint dominates framework choice?\n□ Where does state live? (in-context = anti-pattern for long-running)\n□ Who validates outputs at each stage? (assertion / LLM judge / human review)\n□ Where do traces live, with what retention?\n□ Eval set: how many examples, who labels, how does it grow?\n```\n\nIf you can't answer half of these, **slow down and answer them together — don't write code yet.**\n\nAn agentic product is **not production-ready** until all 12 are satisfied. Full detail in [ STANDARD.md](/AlexDuchDev/agentic-product-standard/blob/main/STANDARD.md#part-iii-production-readiness--definition-of-done).\n\n| Context & state | Tools & permissions | Reliability | Evals & observability |\n|---|---|---|---|\n| Context < 40% | Destructive actions need approval | Durable pause/resume/retry | ≥50 evals per failure mode |\n| State externalized | Permissions in code, not prompt | Schema-validated outputs | Judges calibrated (TPR/TNR) |\n| Compaction tested | Sandboxed tool execution | Input/output guardrails | CI blocks regression; 100% traced |\n\nThe fastest way to recognize a doomed agent project — the skill set's `antipatterns-review`\n\nflags each with a diagnostic and a fix.\n\n- Multi-agent before a single-agent baseline\n- Framework abstractions before understanding the raw API\n- LLM judges without calibration against human labels\n- Permissions enforced through prompts\n- Memory as an afterthought\n- Generic evals (\"helpfulness,\" \"correctness\")\n- Likert scales in an LLM judge (binary only)\n-\n100 tools per agent\n\n- One agent for both breadth and depth\n- Deploying without trace monitoring\n- Hardcoded prompts without version control\n- Treating single-vendor benchmarks as ground truth\n\nThe operational base — not reference docs. Read in order:\n\n- Anthropic —\n*Building Effective Agents*(Schluntz & Zhang) - OpenAI —\n*A Practical Guide to Building Agents* - HumanLayer —\n*12 Factor Agents*(Dex Horthy) - Anthropic —\n*How we built our multi-agent research system* - Cognition —\n*Don't Build Multi-Agents*(Walden Yan) - LangChain —\n*Context Engineering for Agents*(Lance Martin) - Hamel Husain —\n*A Field Guide to Rapidly Improving AI Products*+*Your AI Product Needs Evals* - Anthropic —\n*Building agents with the Claude Agent SDK*\n\nThis standard is meant to evolve — the field moves fast. Corrections, new exemplars, framework updates, and translations are all welcome. See [CONTRIBUTING.md](/AlexDuchDev/agentic-product-standard/blob/main/CONTRIBUTING.md) and the [Code of Conduct](/AlexDuchDev/agentic-product-standard/blob/main/CODE_OF_CONDUCT.md).\n\nThe architectural canons (the autonomy ladder, the 5 patterns, single-vs-multi, the harness) are stable. Specific vendors and framework rankings will shift — those are exactly the kind of PRs we want.\n\n[MIT](/AlexDuchDev/agentic-product-standard/blob/main/LICENSE) — use it, fork it, ship with it.\n\n**If this saved you a week of architecture debates, star the repo ⭐ so others find it.**\n\n*v1.0 · assembled from production practices as of May 2026*", "url": "https://wpnews.pro/news/a-standard-for-building-production-ai-agents-installable-claude-code-skills", "canonical_source": "https://github.com/AlexDuchDev/agentic-product-standard", "published_at": "2026-05-31 05:00:23+00:00", "updated_at": "2026-05-31 05:15:11.901719+00:00", "lang": "en", "topics": ["ai-agents", "ai-products", "ai-tools", "ai-infrastructure", "large-language-models"], "entities": ["Anthropic", "OpenAI", "Cognition", "Sierra", "LangChain", "AlexDuchDev", "Claude Code", "AgenticMind"], "alternates": {"html": "https://wpnews.pro/news/a-standard-for-building-production-ai-agents-installable-claude-code-skills", "markdown": "https://wpnews.pro/news/a-standard-for-building-production-ai-agents-installable-claude-code-skills.md", "text": "https://wpnews.pro/news/a-standard-for-building-production-ai-agents-installable-claude-code-skills.txt", "jsonld": "https://wpnews.pro/news/a-standard-for-building-production-ai-agents-installable-claude-code-skills.jsonld"}}