| 41e45f718995fdd9… | The number of Qdrant vectors is expected to equal the CXU count so that each CXU has a corresponding vector representation. | active | contextual | yes | |
| 98ab0c25410fc03b… | The Neo4j graph is estimated to contain about 100 non-CXU nodes for hierarchy, agents, and memory structures in addition to CXU content. | active | contextual | yes | |
| 86a913f86d0e82a4… | The source corpus for the knowledge graph is estimated to include more than 150 files, indicating the expected document ingestion scope. | active | contextual | yes | |
| 81cd63cd2d607787… | The graph is estimated to contain about 15 named relationship types and more than 500 relationship instances, indicating the expected connectivity model. | active | contextual | yes | |
| ea6a51a80dd1c2d6… | The knowledge graph is estimated to use 12 top-level sets plus approximately 15 sub-sets as its organizational structure. | active | contextual | yes | |
| b7e66bb69b34d7ed… | After six months, the knowledge graph is estimated to contain between 3,000 and 5,000 total CXUs, reflecting projected growth over time. | active | contextual | yes | |
| 6c93dcb5c30f3ed3… | The estimated initial load for the knowledge graph is between 1,200 and 2,500 total CXUs, indicating the expected starting content volume. | active | contextual | yes | |
| 48034777a99939b0… | The Granola workflow should flag action items and decisions with high confidence so that important meeting outcomes are surfaced reliably. | active | contextual | yes | |
| 0c41bdcefcef5a79… | The Granola workflow should auto-assign extracted CXUs to CLIENTS and PROJECTS sets based on meeting attendees and title so that meeting knowledge is categorized automatically. | active | contextual | yes | |
| 8472e0ec3b923d4f… | The Granola workflow should extract CXUs using the zeroth-internal profile so that meeting content is transformed according to the internal extraction configuration. | active | contextual | yes | |
| 10aba57b79f42ee6… | After each meeting, the Granola integration should query Granola for the transcript as the first step in the meeting extraction workflow. | active | contextual | yes | |
| 064e6036a255e209… | Granola meeting integration should be configured for continuous extraction from meeting transcripts so that meeting knowledge is regularly captured into the graph. | active | contextual | yes | |
| 41aeeb945eedadca… | The Google Drive sync job should flag potential conflicts between new and existing CXUs for human review so that inconsistencies can be resolved before acceptance. | active | contextual | yes | |
| bb9c86d612e4acac… | The Google Drive sync job should assign newly extracted CXUs to appropriate sets after extraction so that the knowledge graph preserves organizational structure. | active | contextual | yes | |
| 241a58b537e0bf66… | After detecting changed files, the Google Drive sync job should run the extraction pipeline on those changed documents so that new knowledge can be processed into CXUs. | active | contextual | yes | |
| b55885fd6a0a241b… | A periodic Google Drive sync job should first monitor both Drive folders for new or modified files so that document changes are detected for downstream processing. | active | contextual | yes | |
| 83ebd54b101be419… | The scheduled task pyrana-daily-research-review already reads PYRANA_PLATFORM_ARCHITECTURE_REFERENCE.md as part of the current daily research pipeline. | active | contextual | yes | |
| 89b0b8afdfddab64… | The MCP tool context_search_entities should find all entities related to a target term such as Patrick or code interpreter so that entity-centric exploration is possible. | active | contextual | yes | |
| 16b40e3353735594… | The MCP tool context_feedback should record whether a retrieved CXU was helpful or unhelpful so that the feedback can feed Q-values. | active | contextual | yes | |
| 422926e064df13fe… | The MCP tool context_publish_cxu should publish a pre-formed CXU, such as one produced during contract review, when the knowledge unit is already structured. | active | contextual | yes | |
| b7f1e9905b9e209f… | The MCP tool context_publish should publish new CXUs derived from meeting notes or new documents so that fresh knowledge enters the internal graph. | active | contextual | yes | |
| b0b74e7807a10429… | The MCP tool context_graph_traverse should walk relationships such as Client to Projects to SOWs so that proposal context can be assembled from connected entities. | active | contextual | yes | |
| 3b03de59c5e72d60… | The MCP tool context_retrieve_cxu should fetch a specific CXU by ID when verbatim clause insertion is needed. | active | contextual | yes | |
| d2ae25bc148af3ab… | The MCP tool context_query should be used to answer natural-language questions against the internal knowledge graph, such as asking for standard SLA terms. | active | contextual | yes | |
| 625390bdfa413a26… | The internal knowledge graph is the first deployment target for the PYRANA Context Engine MCP Server so that MCP-based context capabilities are initially applied to internal knowledge use cases. | active | contextual | yes | |
| e867ae82b5647965… | The roadmap backlog already contains a specification for the PYRANA Context Engine MCP Server under idea c5676045-4787-4ea9-847c-82f46d3c868f, which serves as a reference point for integration planning. | active | contextual | yes | |
| b6a16dfbba21bbe1… | The query context should support a sets_exclude list so that the agent can explicitly exclude sets such as FINANCIAL_OPS from retrieval. | active | contextual | yes | |
| c0b41ba2a459dd27… | The query context should support a sets_include list so that the agent can explicitly include target sets such as CONTRACT_STANDARDS, CLIENTS:PATRICK, and SALES_POSITIONING in retrieval. | active | contextual | yes | |
| 250cb15eef32524e… | The query context may include an optional client_scope field, such as PATRICK, so that retrieval is narrowed to a specific client sub-set when needed. | active | contextual | yes | |
| e4c4601718e3d9ea… | The query context should include a task_type field, such as proposal_generation, so that the system can prioritize relevant sets for the current task. | active | contextual | yes | |
| d469813b3d1e291d… | The query context should include an agent_type field with values such as cowork, claude_code, or scheduled_task so that the system knows which kind of agent is making the request. | active | contextual | yes | |
| 2fbdfd7c9ac087e6… | The query context should include a user identifier, such as an email address, so that the knowledge graph can evaluate access and retrieval in relation to the requesting user. | active | contextual | yes | |
| ba4b0f78dad772cd… | When an agent such as Cowork, Claude Code, or a scheduled task queries the knowledge graph, it should declare its query context so that retrieval can be scoped and prioritized appropriately. | active | contextual | yes | |
| 4cc4799af6c942f4… | IP_PATENTS should be accessible to Leadership and Engineering because intellectual property strategy is confidential. | active | contextual | yes | |
| f510fb65971803f8… | CLIENTS:* sets should be accessible only to assigned team members because client data must be handled on a need-to-know basis. | active | contextual | yes | |
| f72e15076e5405f7… | COMPANY_POLICIES should be accessible to all team members because those policies apply to everyone in the organization. | active | contextual | yes | |
| 364ecd75268dae8e… | CONTRACT_STANDARDS templates should be accessible to all team members because reusable templates are intended for organization-wide use. | active | contextual | yes | |
| 986a7121422e940b… | The deployment is single-tenant for Zeroth Agents internal use, but the knowledge graph should still enforce access scoping across set categories so that information access matches sensitivity and need-to-know boundaries. | active | contextual | yes | |
| 236b857c32b208a6… | The number of PostgreSQL rows is estimated to equal the CXU count plus additional metadata rows. | active | contextual | yes | |
| cf26feff5d593bcf… | The number of Qdrant vectors is estimated to be equal to the total CXU count. | active | contextual | yes | |
| eca948ba01d7be99… | The source corpus for the knowledge graph is estimated to include more than 150 files. | active | contextual | yes | |
| e324763ab0620bbf… | The graph is estimated to use approximately 15 named relationship types and more than 500 relationship instances. | active | contextual | yes | |
| eff3fe124bd6f86c… | The estimated set structure consists of 12 top-level sets and approximately 15 sub-sets. | active | contextual | yes | |
| aee45e5d3dc53577… | After six months, the knowledge graph is estimated to contain between 3,000 and 5,000 total CXUs. | active | contextual | yes | |
| 7aed3839f61607ff… | The estimated initial load for the knowledge graph is between 1,200 and 2,500 total CXUs. | active | contextual | yes | |
| a490a8f92cdac9b2… | The Granola integration should flag action items and decisions with high confidence after extracting and assigning meeting CXUs. | active | contextual | yes | |
| 3b340923d97fc13b… | The Granola integration should extract CXUs using the zeroth-internal profile after retrieving each meeting transcript. | active | contextual | yes | |
| b7f071cb1af3a199… | After each meeting, the Granola integration should query Granola for the transcript as the first step in continuous extraction. | active | contextual | yes | |
| f3f0599e5defaf5d… | The Google Drive sync process should flag potential conflicts between new and existing CXUs for human review after assigning new CXUs. | active | contextual | yes | |
| b94cd456d4d331d6… | The Google Drive sync process should assign newly extracted CXUs to appropriate sets after processing changed documents. | active | contextual | yes | |