HiveCraft

Areas of practice

Dimensions, in plain language.

Each dimension is an area of everyday practice. The summary tells you what it is about; the technical layer below opens the structure if you want it.

These are the areas the model pays attention to. Each one has a short, plain summary you can recognise your own practice in. The technical structure behind each dimension is available on request via the toggle below.

What follows is the everyday-language version. The technical layer is one click away.

Show the technical detail behind this
  • D1 · Group A Operational Versioning & Reproducibility
    3 categories 7 items

    Summary

    Reproducible builds, prompt/code/model version-pinning, deterministic re-runs, and artifact lineage.

    Group context

    Day-to-day discipline of running an agentic-software-development practice — the engineering hygiene that keeps the hive accountable, repeatable, and recoverable.

    Indicative cross-walk

    • ISO 27001:2022 A.8.32
    • NIST SSDF PO.3
    • CMMI CM

    These are anchor-references only. The full per-item cross-walk lives in the canonical reference.

  • D2 · Group A Operational Observability & Telemetry
    3 categories 8 items

    Summary

    Run-level traces, agent invocation logs, cost / latency / quality metrics, and live drift signals.

    Group context

    Day-to-day discipline of running an agentic-software-development practice — the engineering hygiene that keeps the hive accountable, repeatable, and recoverable.

    Indicative cross-walk

    • NIST CSF 2.0 DE.CM
    • SPACE framework
    • MLOps maturity (level 2+)

    These are anchor-references only. The full per-item cross-walk lives in the canonical reference.

  • D3 · Group A Operational Continuous Integration
    2 categories 6 items

    Summary

    Automated test gates, prompt regression suites, eval-on-commit, and merge protections.

    Group context

    Day-to-day discipline of running an agentic-software-development practice — the engineering hygiene that keeps the hive accountable, repeatable, and recoverable.

    Indicative cross-walk

    • NIST SSDF PW.7
    • CMMI PR

    These are anchor-references only. The full per-item cross-walk lives in the canonical reference.

  • D4 · Group A Operational Deployment & Release
    3 categories 8 items

    Summary

    Progressive rollout, blue/green or canary release, rollback playbooks, and deployment audit trails.

    Group context

    Day-to-day discipline of running an agentic-software-development practice — the engineering hygiene that keeps the hive accountable, repeatable, and recoverable.

    Indicative cross-walk

    • ISO 27001:2022 A.8.31
    • NIST SP 800-53 CM-3
    • MLOps maturity

    These are anchor-references only. The full per-item cross-walk lives in the canonical reference.

  • D5 · Group B Knowledge KB Curation & Lessons
    3 categories 8 items

    Summary

    KB section discipline, lessons capture, deprecation hygiene, and read-tracking discipline.

    Group context

    How the hive captures, validates, and propagates knowledge across humans and agents — KB curation, lessons, retrievability, and onboarding semantics.

    Indicative cross-walk

    • ISO 9001 7.1.6
    • COBIT 2019 BAI08

    These are anchor-references only. The full per-item cross-walk lives in the canonical reference.

  • D6 · Group B Knowledge Retrieval & Grounding
    3 categories 8 items

    Summary

    Retrieval quality, grounding traceability, citation discipline, and hallucination-control evidence.

    Group context

    How the hive captures, validates, and propagates knowledge across humans and agents — KB curation, lessons, retrievability, and onboarding semantics.

    Indicative cross-walk

    • NIST AI RMF 1.0 (MAP/MEASURE)
    • ISO/IEC 25010

    These are anchor-references only. The full per-item cross-walk lives in the canonical reference.

  • D7 · Group B Knowledge Onboarding & Pedagogy
    3 categories 9 items

    Summary

    Stakeholder onboarding, agent-orientation paths, role-based training, and pedagogy evidence.

    Group context

    How the hive captures, validates, and propagates knowledge across humans and agents — KB curation, lessons, retrievability, and onboarding semantics.

    Indicative cross-walk

    • ISO 9001 7.2
    • CMMI OT

    These are anchor-references only. The full per-item cross-walk lives in the canonical reference.

  • D8 · Group C Risk Security & Hardening
    2 categories 7 items

    Summary

    Secret hygiene, supply-chain security, agent permission scoping, and hardening drift detection.

    Group context

    How the hive manages security, regulatory, ethical, and operational risk — drift, red-teaming, jurisdictional obligations, and AI disclosure.

    Indicative cross-walk

    • ISO 27001:2022 A.5/A.8
    • NIST CSF 2.0 PR.AA
    • PCI DSS
    • CIS Benchmarks

    These are anchor-references only. The full per-item cross-walk lives in the canonical reference.

  • D9 · Group C Risk Compliance & Jurisdiction
    4 categories 10 items

    Summary

    GDPR, EU AI Act, sector-specific regimes, jurisdiction-obligation registry, and DPIA evidence.

    Group context

    How the hive manages security, regulatory, ethical, and operational risk — drift, red-teaming, jurisdictional obligations, and AI disclosure.

    Indicative cross-walk

    • GDPR Art. 6/7/13/14/30/32
    • EU AI Act Art. 9/15/16/26/50
    • ISO 27701
    • ISO 42001

    These are anchor-references only. The full per-item cross-walk lives in the canonical reference.

  • D10 · Group C Risk Risk Register & Tabletops
    3 categories 8 items

    Summary

    Active risk register, scheduled red-team exercises, tabletop simulations, and post-mortem feedback.

    Group context

    How the hive manages security, regulatory, ethical, and operational risk — drift, red-teaming, jurisdictional obligations, and AI disclosure.

    Indicative cross-walk

    • ISO 31000
    • ISO 22301
    • NIST CSF 2.0 ID.RA
    • MITRE ATT&CK Navigator

    These are anchor-references only. The full per-item cross-walk lives in the canonical reference.

  • D11 · Group C Risk AI Disclosure & Transparency
    2 categories 7 items

    Summary

    Public AI-disclosure artifacts, decision-explainability, model cards, and use-case transparency.

    Group context

    How the hive manages security, regulatory, ethical, and operational risk — drift, red-teaming, jurisdictional obligations, and AI disclosure.

    Indicative cross-walk

    • EU AI Act Art. 50
    • NIST AI RMF (GOVERN)
    • Microsoft RAI MM

    These are anchor-references only. The full per-item cross-walk lives in the canonical reference.

  • D12 · Group D Outcome Deliverable Acceptance
    3 categories 5 items

    Summary

    Stakeholder-acknowledged acceptance of deliverables, signed sign-offs, and rejection-rate tracking.

    Group context

    Outcomes the practice produces for stakeholders: deliverable acceptance, customer feedback loops, business-level impact.

    Indicative cross-walk

    • ISO 9001 8.6
    • CMMI VV

    These are anchor-references only. The full per-item cross-walk lives in the canonical reference.

  • D13 · Group D Outcome Stakeholder Outcomes
    4 categories 9 items

    Summary

    Customer-impact metrics, business-value tracking, stakeholder feedback loops, and outcome-based KPIs.

    Group context

    Outcomes the practice produces for stakeholders: deliverable acceptance, customer feedback loops, business-level impact.

    Indicative cross-walk

    • SOC 2 (CC)
    • SPACE framework
    • CMMI OPP

    These are anchor-references only. The full per-item cross-walk lives in the canonical reference.

See the scoring overview · Ask a question