Point One Zero Platform architecturev11 · generated viewSign in to edit
Governance › Citations

Citations

Every source behind this portal, in one place. Internal sources are engagement and program records; published sources are the guidance the guidelines were validated against; platform documentation grounds the overlays and externally validates specific principles. Where a principle on the Decision Register page has an external validation, the register is stronger for it, the reasoning is traceable, not asserted.

Internal sources

Confidential, internal architecture references, not for external distribution. Drop this page from client-facing copies, along with the discovery chips.

SourceOriginWhat it informed
I1Internship Wrap meeting notesPoint One Zero internal, Aug 19 2026Seed of the 36 architecture guidelines and the determination rule; the Smart Pipe antipattern was caught live in this review.
I2PE Platform Interactive Architecture GuidePoint One Zero internal, July architecture reviewAs-built evidence base. Contributed the decision-register mechanism, classification inheritance, restricted-store handling, scoped index lifecycle, source authority weighting, the canonical record, and identity passthrough. Its eleven layers map into the seven here without loss.
I3IC Memo Generation Platform, architecture overview diagramPoint One Zero internalContributed the deterministic rendering boundary (immutable templates, dynamic data only), the source catalog, source-of-truth-stays-in-the-estate, disaster recovery, and the append-only audit-trail statement.
I4Architecture Portal v1This program; superseded by this portalThe 28-step greenfield setup sequence in Environment & Operations was restored from it.
I5Architecture Guidelines Validation workbookCompanion Excel asset, Aug 19 2026The 36 guidelines validated line by line against S1 to S7 below; ten additional guidelines adopted from those sources.

Published engineering guidance

The validation base for the guidelines, the SSRA file grammar, and the pattern library.

SourceOriginWhat it informed
S1Building Effective AgentsAnthropic Engineering, Dec 2024The determination rule (workflows are predefined code paths), the simplicity principle, and the routing and orchestrator-workers shapes behind patterns P1 and P6.
S2Claude Code Best PracticesAnthropic docs, originally authored by Boris Cherny, Apr 2025The SSRA file grammar: constitutions, skills, commands, hooks as deterministic guardrails, permissions, verification loops.
S3How We Built Our Multi-Agent Research SystemAnthropic Engineering, Jun 2025P6 economics (the 15x rule and effort-scaling dispatch), the four-part delegation spec in agent definitions, bounded subagent summary contracts, end-state evaluation with LLM-as-judge, checkpoint-resume and rainbow deployments in the harness inventory, and the SSRA authoring guidance.
S4Writing Effective Tools for AgentsAnthropic Engineering, 2025The tool-design standard for the south servers: consolidation, namespacing, high-signal returns, pagination and truncation defaults.
S5Effective Context Engineering for AI AgentsAnthropic Engineering, 2025Context packs and just-in-time retrieval, compaction policy, system-prompt altitude, subagent context isolation.
S6Building Claude Code with Boris ChernyThe Pragmatic Engineer interviewPromotion-on-repetition (the build-twice rule), agentic search over static indexes, plan-then-build discipline.
S7Boris Cherny's 13 Claude Code TipsBoris Cherny, Jan 2026 (community transcription)Shared team constitutions via git, the verification feedback loop, subagents for verification, hooks for auto-format.

Industry platform documentation

External validation of specific principles, and the sources behind the cloud overlays.

SourceOriginWhat it informed
X1Palantir Foundry: Markings · inherited markings · removal guidancePalantir documentationValidates classification inheritance as default platform behavior: markings propagate to every derived dataset; removal is an explicit, permissioned exception.
X2Microsoft Purview: Sensitivity labels · best practicesMicrosoft documentationThe same principle shipped as label inheritance: sensitivity follows data into derived assets.
X3AWS Bedrock AgentCoreAWS documentationThe AWS overlay in Environment & Operations and the 28-step greenfield setup mapping.
X4Azure AI FoundryMicrosoft documentationThe Azure overlay in Environment & Operations.
X5Google Cloud Vertex AIGoogle Cloud documentationThe GCP overlay in Environment & Operations.
X6Model Context Protocol specificationmodelcontextprotocol.ioThe protocol beneath both boundaries: MCP is the bridge, never the business logic, the platform is a server northward and a client southward.
X7Matthew Coombs, Enterprise AI Architecture infographicLinkedIn, 2026The external reference architecture the diagram was contrasted against; the gaps identified fed the v2 model. The comparison view has since been retired from the portal so a single layer vocabulary appears; this citation stands as the record of what was borrowed.
X8Claude Managed Agents overviewAnthropic platform documentationThe managed-agent-runtime concept and the buy-versus-build open item on the Decision Register; terminology alignment across the portal (subagents, skills, slash commands, project memory).
X9AWS: S3 Vectors with Bedrock Knowledge Bases · S3 Vectors GA announcementAWS documentationThe vector-store decision guidance on the AWS overlay (OpenSearch for latency and throughput, S3 Vectors for massive cost-optimized collections, Knowledge Bases backing onto either), added while reconciling the AgentCore setup walkthrough.

Engineering Standards sources

Added Aug 21 2026 with the Engineering Standards section and the SSRA correction. These ground the skill anatomy, the project skeleton, the eval and judge controls, the observability conventions, the caching economics and the model-customisation routes.

SourceOriginWhat it informed
S8Agent Skills overviewAnthropic platform documentationThe corrected SSRA expansion, Skills, Scripts, References, Assets, the three-level progressive disclosure model, the rule that script source never enters context, and the on-demand reference-loading behaviour behind the Skill anatomy page.
S9Prompt cachingAnthropic platform documentationCache breakpoint placement, prefix ordering (tools, system, messages), TTL behaviour and the read-versus-write pricing structure behind the Token & cost engineering page.
S1012-Factor AgentsDex Horthy / HumanLayerThe engineering posture on the Project skeleton standard page: own your prompts, context window and control flow; structured output as the module contract; small focused agents; humans reached by tool call; errors compacted rather than looped on.
S11GenAI observability with OpenTelemetry · Langfuse OTEL endpointOpenTelemetry & Langfuse documentationThe vendor-neutral instrumentation standard: GenAI semantic conventions for span naming, model and token attributes, tool and agent spans, and content-capture opt-in. The basis for treating the observability backend as swappable.
S12Golden dataset evaluationLangfuse engineering guidanceGolden-set sizing (start at twenty to fifty, grow to a few hundred), the fast CI subset, dataset versioning, holdout partitions and monthly refresh from production failures.
S13LLM-as-a-judge bias and calibration literatureMT-Bench and successor studies; 2026 judge-reliability surveysThe judge control table: human calibration before promotion, cross-family judging against self-preference, order rotation against position bias, rubric decomposition, rationale requirements, verbosity normalisation and pinning the judge contract.
X10Bedrock model customisation · RFT for open-weight modelsAWS documentationThe managed supervised and reinforcement fine-tuning routes, reward-function grading with rule-based or AI judges, intermediate checkpoints, and custom model import for open-weight architectures.
X11Fireworks AI supervised fine-tuningFireworks AI documentationThe hosted tuning route: JSONL in standard chat-completion format, LoRA adapters trained elsewhere and uploaded for serving, and the vendor-boundary caution on the Model customisation page.
X12Multi-LoRA serving on SageMaker and BedrockAWS documentationAdapter-based customisation economics: frozen base weights, adapters swapped per request, several tuned variants sharing one GPU.