{"playbooks": [{"slug": "coding-agents", "title": "Working with AI coding agents", "description": "Getting reliable work out of coding agents: instruction and context files, task scoping, reviewing agent-written code, repository conventions, hooks and workflow guardrails.", "count": 4, "latest": "Add a `verify` skill in `.claude/skills/` that starts your app or simulator, request property tests for round-trip and idempotence, and stop for a human after three failed rounds.", "url": "https://wpnews.pro/playbooks/coding-agents", "json": "https://wpnews.pro/playbooks/coding-agents.json"}, {"slug": "agent-architecture", "title": "Designing agent systems", "description": "Structuring agents: orchestration and multi-agent patterns, tool and MCP server design, memory, planning loops, state and handoffs.", "count": 2, "latest": "Give each parallel coding agent its own isolated remote environment with simulators and SSH access, and bar runner agents from editing the tests they execute so passing results stay trustworthy.", "url": "https://wpnews.pro/playbooks/agent-architecture", "json": "https://wpnews.pro/playbooks/agent-architecture.json"}, {"slug": "agent-security", "title": "Securing agents and AI tools", "description": "Sandboxing, scoped credentials, prompt-injection defence, permission and approval gates, egress control, supply chain of models and tools.", "count": 2, "latest": "Route agent-to-MCP authentication through AgentCore Identity's token vault so tokens are fetched, cached, and refreshed per user; choose Snowflake OAuth or three-legged SSO for per-user identity and reserve client_credentials for shared service users.", "url": "https://wpnews.pro/playbooks/agent-security", "json": "https://wpnews.pro/playbooks/agent-security.json"}, {"slug": "output-verification", "title": "Verifying model output", "description": "Grounding and checking what a model claims: citation and quote verification, hallucination detection, LLM-as-judge pitfalls, structured-output validation, human approval of actions.", "count": 0, "latest": "", "url": "https://wpnews.pro/playbooks/output-verification", "json": "https://wpnews.pro/playbooks/output-verification.json"}, {"slug": "evals-testing", "title": "Evals and testing for LLM apps", "description": "Measuring and regression-testing LLM apps and agents: eval datasets, benchmarks you run yourself, CI gates, tests on tool calls and traces.", "count": 1, "latest": "When prompting coding models for API calls, Dockerfiles or CI workflows, include a dated list of known upstream breaks with the fix for each; the eval cut broken-route picks from 37% to 16% for claude-sonnet-5.5, while a bare date did little.", "url": "https://wpnews.pro/playbooks/evals-testing", "json": "https://wpnews.pro/playbooks/evals-testing.json"}, {"slug": "rag-retrieval", "title": "Retrieval and RAG", "description": "Chunking, embeddings, keyword and hybrid search, reranking, vector stores, filtering, and measuring retrieval quality.", "count": 0, "latest": "", "url": "https://wpnews.pro/playbooks/rag-retrieval", "json": "https://wpnews.pro/playbooks/rag-retrieval.json"}, {"slug": "llm-cost", "title": "Controlling LLM cost", "description": "Cutting token spend and API bills: model routing, prompt and KV caching, batching, context budgets, moving work from models to code.", "count": 4, "latest": "Cap loop context or restart sessions from a handoff file of current priorities, and prune the system prompt, since caching was 78% of the bill and pruning would save about $93 a day.", "url": "https://wpnews.pro/playbooks/llm-cost", "json": "https://wpnews.pro/playbooks/llm-cost.json"}, {"slug": "inference-serving", "title": "Inference and self-hosting", "description": "Running models yourself: GPU memory, quantization, KV cache, serving engines, throughput and latency tuning, hardware choices.", "count": 1, "latest": "Budget VRAM for context growth: llama3.2:3b Q4_K_M held 351.22 tok/s at 4,096 context but dropped to 102.68 tok/s at 131,072 on a 16 GB RTX 5080.", "url": "https://wpnews.pro/playbooks/inference-serving", "json": "https://wpnews.pro/playbooks/inference-serving.json"}, {"slug": "production-ops", "title": "Running AI in production", "description": "Monitoring, tracing and alerting for LLM apps, incident response, rollouts, model upgrades and provider migrations, reliability.", "count": 2, "latest": "Run autonomous real-time resource allocation for agent workloads on Kubernetes, starting in read-only mode on your hardest environments, and reclaim idle agent memory via swap to avoid provisioning for peak spikes.", "url": "https://wpnews.pro/playbooks/production-ops", "json": "https://wpnews.pro/playbooks/production-ops.json"}, {"slug": "training-data", "title": "Fine-tuning and data", "description": "Fine-tuning, distillation, RL and preference tuning, synthetic data, dataset curation and labeling for models you train.", "count": 0, "latest": "", "url": "https://wpnews.pro/playbooks/training-data", "json": "https://wpnews.pro/playbooks/training-data.json"}]}