{
  "generated": "2026-08-01T23:34:43.596Z",
  "count": 14,
  "license": "Content © Santiago Santa María Morales, licensed CC BY 4.0. Attribution required: credit the author and link the canonical URL.",
  "license_spdx": "CC-BY-4.0",
  "license_url": "https://creativecommons.org/licenses/by/4.0/",
  "units": [
    {
      "id": "HRN-001",
      "slug": "definition-and-overview",
      "title": "Harness Engineering: Definition and Overview",
      "category": "Foundations",
      "status": "Draft",
      "summary": "Harness Engineering is the discipline of building reliable agentic systems for enterprise environments — the engineered scaffolding of memory, tools, orchestration, observability, evaluation, governance, and security that surrounds the model.",
      "updated": "2026-06-21",
      "evidence": {
        "evidenceLevel": "theoretical",
        "confidenceLevel": "medium",
        "sourceType": [
          "industry_observation",
          "personal_experience"
        ]
      },
      "related": [
        "HRN-002",
        "HRN-003",
        "HRN-004"
      ],
      "tags": [
        "harness-engineering",
        "agentic-systems",
        "foundations",
        "reliability",
        "enterprise-ai"
      ],
      "url": "https://santismm.com/en/handbook/definition-and-overview",
      "api": "https://santismm.com/api/handbook/HRN-001"
    },
    {
      "id": "HRN-002",
      "slug": "a-brief-history-of-harness-engineering",
      "title": "A Brief History of Harness Engineering",
      "category": "Foundations",
      "status": "Draft",
      "summary": "How the field moved from prompt engineering to tool use to agents to harnesses, and why the engineered scaffolding around the model became its own discipline.",
      "updated": "2026-06-21",
      "evidence": {
        "evidenceLevel": "theoretical",
        "confidenceLevel": "medium",
        "sourceType": [
          "industry_observation",
          "personal_experience"
        ]
      },
      "related": [
        "HRN-001",
        "HRN-003"
      ],
      "tags": [
        "history",
        "harness-engineering",
        "foundations",
        "agentic-systems"
      ],
      "url": "https://santismm.com/en/handbook/a-brief-history-of-harness-engineering",
      "api": "https://santismm.com/api/handbook/HRN-002"
    },
    {
      "id": "HRN-003",
      "slug": "the-harness-taxonomy",
      "title": "The Harness Taxonomy",
      "category": "Foundations",
      "status": "Draft",
      "summary": "A structured taxonomy of the harness — memory, tools, planning, orchestration, observability, evaluation, governance, and security — naming each component, its responsibility, and how the parts compose into a reliable agentic system.",
      "updated": "2026-06-21",
      "evidence": {
        "evidenceLevel": "theoretical",
        "confidenceLevel": "medium",
        "sourceType": [
          "industry_observation",
          "personal_experience"
        ]
      },
      "related": [
        "HRN-001",
        "HRN-005",
        "HRN-006",
        "HRN-009",
        "HRN-010"
      ],
      "tags": [
        "taxonomy",
        "harness-engineering",
        "foundations",
        "architecture",
        "agentic-systems"
      ],
      "url": "https://santismm.com/en/handbook/the-harness-taxonomy",
      "api": "https://santismm.com/api/handbook/HRN-003"
    },
    {
      "id": "HRN-004",
      "slug": "harness-engineering-principles",
      "title": "Harness Engineering Principles",
      "category": "Foundations",
      "status": "Draft",
      "summary": "The core engineering principles of the harness — reliability over capability, determinism boundaries, observability-first, evidence-first, defense in depth, least authority, graceful degradation, and idempotent actuation — that hold across every component.",
      "updated": "2026-06-21",
      "evidence": {
        "evidenceLevel": "theoretical",
        "confidenceLevel": "medium",
        "sourceType": [
          "industry_observation",
          "personal_experience"
        ]
      },
      "related": [
        "HRN-001",
        "HRN-003"
      ],
      "tags": [
        "principles",
        "harness-engineering",
        "foundations",
        "reliability",
        "design"
      ],
      "url": "https://santismm.com/en/handbook/harness-engineering-principles",
      "api": "https://santismm.com/api/handbook/HRN-004"
    },
    {
      "id": "HRN-005",
      "slug": "memory-in-agentic-systems",
      "title": "Memory in Agentic Systems",
      "category": "Memory",
      "status": "Draft",
      "summary": "How the harness governs what the model sees and remembers — working, short-term, and long-term memory; the context window as a budget; retrieval, compression, and deliberate forgetting.",
      "updated": "2026-06-21",
      "evidence": {
        "evidenceLevel": "theoretical",
        "confidenceLevel": "medium",
        "sourceType": [
          "industry_observation",
          "personal_experience"
        ]
      },
      "related": [
        "HRN-003",
        "PAT-004",
        "PAT-006"
      ],
      "tags": [
        "memory",
        "context-window",
        "retrieval",
        "compression",
        "agentic-systems"
      ],
      "url": "https://santismm.com/en/handbook/memory-in-agentic-systems",
      "api": "https://santismm.com/api/handbook/HRN-005"
    },
    {
      "id": "HRN-006",
      "slug": "observability-for-agentic-systems",
      "title": "Observability for Agentic Systems",
      "category": "Observability",
      "status": "Draft",
      "summary": "How to make a non-deterministic, multi-step agent inspectable — traces and spans, token and cost accounting, evaluation hooks, and deterministic replay — so the system can be debugged, measured, and trusted.",
      "updated": "2026-06-21",
      "evidence": {
        "evidenceLevel": "theoretical",
        "confidenceLevel": "medium",
        "sourceType": [
          "industry_observation",
          "personal_experience"
        ]
      },
      "related": [
        "HRN-003",
        "HRN-007"
      ],
      "tags": [
        "observability",
        "tracing",
        "spans",
        "replay",
        "cost-accounting"
      ],
      "url": "https://santismm.com/en/handbook/observability-for-agentic-systems",
      "api": "https://santismm.com/api/handbook/HRN-006"
    },
    {
      "id": "HRN-007",
      "slug": "evaluation-of-agentic-systems",
      "title": "Evaluation of Agentic Systems",
      "category": "Evaluation",
      "status": "Draft",
      "summary": "How to measure whether an agent is actually good and getting better — offline and online evaluation, golden sets, LLM-as-judge, regression suites, and task-completion metrics — turning agent development from craft into engineering.",
      "updated": "2026-06-21",
      "evidence": {
        "evidenceLevel": "theoretical",
        "confidenceLevel": "medium",
        "sourceType": [
          "industry_observation",
          "personal_experience"
        ]
      },
      "related": [
        "HRN-006",
        "PAT-009",
        "PAT-015"
      ],
      "tags": [
        "evaluation",
        "llm-as-judge",
        "golden-set",
        "regression",
        "task-completion"
      ],
      "url": "https://santismm.com/en/handbook/evaluation-of-agentic-systems",
      "api": "https://santismm.com/api/handbook/HRN-007"
    },
    {
      "id": "HRN-008",
      "slug": "governance-within-the-harness",
      "title": "Governance within the Harness",
      "category": "Governance",
      "status": "Draft",
      "summary": "Governance is an engineered harness layer that enforces policy, approvals, and guardrails at runtime, turning enterprise AI obligations into executable controls that gate every agent action.",
      "updated": "2026-06-21",
      "evidence": {
        "evidenceLevel": "theoretical",
        "confidenceLevel": "medium",
        "sourceType": [
          "industry_observation",
          "personal_experience"
        ]
      },
      "related": [
        "HRN-003",
        "GOV-001",
        "PAT-001"
      ],
      "tags": [
        "governance",
        "guardrails",
        "policy-enforcement",
        "approvals",
        "compliance"
      ],
      "url": "https://santismm.com/en/handbook/governance-within-the-harness",
      "api": "https://santismm.com/api/handbook/HRN-008"
    },
    {
      "id": "HRN-009",
      "slug": "planning-and-goal-management",
      "title": "Planning and Goal Management",
      "category": "Planning",
      "status": "Draft",
      "summary": "Planning and goal management is the harness layer that decomposes goals into executable plans, represents and tracks plan state, and replans under failure, making agent autonomy directed rather than reactive.",
      "updated": "2026-06-21",
      "evidence": {
        "evidenceLevel": "theoretical",
        "confidenceLevel": "medium",
        "sourceType": [
          "industry_observation",
          "personal_experience"
        ]
      },
      "related": [
        "HRN-003",
        "HRN-010",
        "PAT-010"
      ],
      "tags": [
        "planning",
        "goal-decomposition",
        "replanning",
        "task-management",
        "plan-representation"
      ],
      "url": "https://santismm.com/en/handbook/planning-and-goal-management",
      "api": "https://santismm.com/api/handbook/HRN-009"
    },
    {
      "id": "HRN-010",
      "slug": "orchestration",
      "title": "Orchestration",
      "category": "Orchestration",
      "status": "Draft",
      "summary": "Orchestration is the harness layer that drives execution—single vs multi-agent topologies, supervisor/worker delegation, routing, state machines, and durable workflows—turning a plan into reliable, resumable action.",
      "updated": "2026-06-21",
      "evidence": {
        "evidenceLevel": "theoretical",
        "confidenceLevel": "medium",
        "sourceType": [
          "industry_observation",
          "personal_experience"
        ]
      },
      "related": [
        "HRN-003",
        "HRN-009",
        "PAT-002",
        "PAT-005"
      ],
      "tags": [
        "orchestration",
        "multi-agent",
        "supervisor-worker",
        "state-machine",
        "durable-execution"
      ],
      "url": "https://santismm.com/en/handbook/orchestration",
      "api": "https://santismm.com/api/handbook/HRN-010"
    },
    {
      "id": "HRN-011",
      "slug": "security-for-agentic-systems",
      "title": "Security for Agentic Systems",
      "category": "Security",
      "status": "Draft",
      "summary": "Security for agentic systems is the harness layer that defends against prompt injection, sandboxes tools and permissions, prevents data exfiltration, and enforces agent identity and least privilege across every action.",
      "updated": "2026-06-21",
      "evidence": {
        "evidenceLevel": "theoretical",
        "confidenceLevel": "medium",
        "sourceType": [
          "industry_observation",
          "personal_experience"
        ]
      },
      "related": [
        "HRN-003",
        "GOV-001",
        "PAT-007"
      ],
      "tags": [
        "security",
        "prompt-injection",
        "least-privilege",
        "sandboxing",
        "data-exfiltration",
        "agent-identity"
      ],
      "url": "https://santismm.com/en/handbook/security-for-agentic-systems",
      "api": "https://santismm.com/api/handbook/HRN-011"
    },
    {
      "id": "HRN-012",
      "slug": "case-studies-in-harness-engineering",
      "title": "Case Studies in Harness Engineering",
      "category": "Case Studies",
      "status": "Draft",
      "summary": "Three representative, anonymized composite case studies showing how harness layers—memory, planning, orchestration, governance, security, observability—combine end-to-end to make enterprise agents reliable.",
      "updated": "2026-06-21",
      "evidence": {
        "evidenceLevel": "theoretical",
        "confidenceLevel": "medium",
        "sourceType": [
          "industry_observation",
          "personal_experience"
        ]
      },
      "related": [
        "ARCH-001",
        "ARCH-002",
        "HRN-001"
      ],
      "tags": [
        "case-studies",
        "end-to-end",
        "reliability",
        "enterprise-agents"
      ],
      "url": "https://santismm.com/en/handbook/case-studies-in-harness-engineering",
      "api": "https://santismm.com/api/handbook/HRN-012"
    },
    {
      "id": "HRN-013",
      "slug": "glossary",
      "title": "Glossary",
      "category": "Reference",
      "status": "Draft",
      "summary": "A canonical glossary of Harness Engineering and agentic-systems terminology—harness, agent, tool, orchestration, evaluation, span, RAG, MCP, guardrail, and more—with crisp, citable definitions.",
      "updated": "2026-06-21",
      "evidence": {
        "evidenceLevel": "theoretical",
        "confidenceLevel": "high",
        "sourceType": [
          "industry_observation"
        ]
      },
      "related": [
        "HRN-001"
      ],
      "tags": [
        "glossary",
        "reference",
        "terminology"
      ],
      "url": "https://santismm.com/en/handbook/glossary",
      "api": "https://santismm.com/api/handbook/HRN-013"
    },
    {
      "id": "HRN-014",
      "slug": "bibliography",
      "title": "Bibliography",
      "category": "Reference",
      "status": "Draft",
      "summary": "A curated, themed reading list for Harness Engineering—agents and orchestration, evaluation, security, governance and standards, and protocols—covering foundational papers, industry writeups, and regulatory frameworks.",
      "updated": "2026-06-21",
      "evidence": {
        "evidenceLevel": "theoretical",
        "confidenceLevel": "high",
        "sourceType": [
          "industry_observation",
          "paper"
        ]
      },
      "related": [
        "HRN-001",
        "GOV-001"
      ],
      "tags": [
        "bibliography",
        "reference",
        "reading-list",
        "standards"
      ],
      "url": "https://santismm.com/en/handbook/bibliography",
      "api": "https://santismm.com/api/handbook/HRN-014"
    }
  ]
}