{
  "platformId": "chatgpt-work",
  "workflowSlug": "weekly-operating-review",
  "directAnswer": "The weekly operating review is the first workflow this guide recommends most teams start with, and the reasoning is structural: recurring, multi-source, tedious to assemble by hand, and safe while read-only. The agent reads your week (chat exports, project system, dashboards, meeting notes, prior commitments, the decision log) and compiles a source-backed operating brief: what changed, what is blocked, who owns what, which actions have no owner, and which decisions are waiting. It cites every claim to its source, drafts without changing anything, and stops before judgment: the priorities you set, the risks you accept, and the decisions themselves stay in the room.",
  "topUseCases": [
    {
      "interventionId": "task-2578:weekly-operating-review:approval-required",
      "taskId": "task-2578",
      "task": "Keep records of customer interactions or transactions, recording details of inquiries, complaints, or comments, as well as actions taken.",
      "workflowId": "weekly-operating-review",
      "authorityMode": "approval-required",
      "centralityScreen": {
        "value": 0.3662340406,
        "importance": {
          "value": 0.8825000000000001,
          "sourceField": "role-tasks-kv:task-2578.importance"
        },
        "occupationalRelevance": {
          "value": 0.8220999999999999,
          "sourceField": "role-tasks-kv:task-2578.relevance / 100"
        },
        "frequency": {
          "kind": "modal-response-share",
          "modalResponseSharePct": 50.48,
          "collectionDate": "2026-06-03",
          "sourceField": "role-tasks-kv:task-2578.modalResponseSharePct"
        }
      },
      "agentFit": {
        "value": 0.9025,
        "sourceField": "rule:digital-feasibility-and-capability-fit-single-count.v2"
      },
      "distribution": {
        "value": 0.9,
        "sourceField": "roles-kv:aiPlaybook.delegatedTasks[task-2578].observed-distribution"
      },
      "evidenceConfidence": "weak",
      "withinGateScore": 0.29747359947734997,
      "gate": {
        "status": "approval-required",
        "reason": "A person must approve the verifiable handoff before action."
      },
      "capabilityIds": [
        "connected-apps-files",
        "deliverable-generation"
      ],
      "expectedArtifact": "The customer-signal section of the weekly brief: interaction volumes, escalations, and unresolved complaints with source citations",
      "humanReviewPoint": "Verify escalations and unresolved complaints against the source records; ownership and response decisions stay with the team.",
      "riskLevel": "medium"
    },
    {
      "interventionId": "task-20709:weekly-operating-review:approval-required",
      "taskId": "task-20709",
      "task": "Formulate, direct, or coordinate marketing activities or policies to promote products or services, working with advertising or promotion managers.",
      "workflowId": "weekly-operating-review",
      "authorityMode": "approval-required",
      "centralityScreen": {
        "value": 0.0789217344,
        "importance": {
          "value": 0.81,
          "sourceField": "role-tasks-kv:task-20709.importance"
        },
        "occupationalRelevance": {
          "value": 0.9822,
          "sourceField": "role-tasks-kv:task-20709.relevance / 100"
        },
        "frequency": {
          "kind": "modal-response-share",
          "modalResponseSharePct": 9.92,
          "collectionDate": "2026-06-03",
          "sourceField": "role-tasks-kv:task-20709.modalResponseSharePct"
        }
      },
      "agentFit": {
        "value": 0.9025,
        "sourceField": "rule:digital-feasibility-and-capability-fit-single-count.v2"
      },
      "distribution": {
        "value": 0.9,
        "sourceField": "roles-kv:aiPlaybook.delegatedTasks[task-20709].observed-distribution"
      },
      "evidenceConfidence": "weak",
      "withinGateScore": 0.06410417876640001,
      "gate": {
        "status": "approval-required",
        "reason": "A person must approve the verifiable handoff before action."
      },
      "capabilityIds": [
        "connected-apps-files",
        "deliverable-generation",
        "long-running-projects"
      ],
      "expectedArtifact": "The coordination section of the weekly brief: this week's marketing activities with owners, blockers, and slipped commitments cited",
      "humanReviewPoint": "Confirm the cited activities and slipped commitments before the review; priorities and trade-offs are set in the room.",
      "riskLevel": "high"
    }
  ],
  "workflows": [
    {
      "id": "weekly-operating-review",
      "goal": "Compile the week into a source-backed operating brief that surfaces decisions without making them.",
      "inputs": [
        "Chat workspace export for the week (Slack or Teams, read-only)",
        "Project-system export: status, blockers, owners",
        "Meeting notes, dashboards, prior commitments, and the decision log"
      ],
      "connectedSystems": [
        "Read-only collaboration workspace",
        "Read-only project and document repositories"
      ],
      "steps": [
        "Inventory the authorized sources first; mark anything missing or stale so the brief's blind spots are visible up front.",
        "Extract what changed: metrics that moved, blockers with their owners, actions nobody owns, and decisions waiting on someone, each with its citation.",
        "Compare against last week's commitments; anything promised and not delivered gets named, with its source span, not smoothed over.",
        "Draft next week's candidate priorities, risks, and escalations as proposals, with the open questions listed unresolved.",
        "Stop at the draft: nothing in any source system changes, and no decision in the brief is made by the brief."
      ],
      "expectedArtifact": "Weekly operating brief: changes, blockers, owners, unowned actions, pending decisions, and proposed priorities, every claim cited",
      "starterPrompt": "Here are this week's sources: the chat export, the project-system export, meeting notes, dashboards, last week's commitments, and the decision log. Compile the operating brief: what changed, what is blocked and who owns it, which actions have no owner, and which decisions are waiting. Cite every claim to its source. Compare against last week's commitments and name anything promised but not delivered. Propose next week's priorities as proposals. Change nothing in any system, and make no decisions; where the sources are silent or stale, say so instead of filling the gap.",
      "humanReviewPoint": "The room sets the priorities, accepts the risks, and makes the decisions; the brief assembles and surfaces, it never adjudicates.",
      "commonFailure": "A brief that smooths over a missed commitment, assigns an owner nobody agreed to, or quietly resolves a decision that belonged to the meeting."
    }
  ],
  "setupRecommendations": [
    {
      "item": "Connect the chat workspace, project system, and document repositories read-only; the brief drafts on its own surface and writes back nothing.",
      "rationale": "The workflow's safety comes from its read-only boundary: it can see the whole week precisely because it can change none of it.",
      "capabilityIds": [
        "connected-apps-files",
        "approval-enterprise-controls"
      ]
    }
  ],
  "prompts": [
    {
      "id": "operating-brief",
      "title": "Compile this week's operating brief",
      "prompt": "From the sources I connected, compile the weekly operating brief: changed metrics, blockers with owners, unowned actions, and pending decisions, every claim cited. Compare against last week's commitments and name what slipped. Propose priorities; decide nothing.",
      "expectedArtifact": "Cited weekly operating brief",
      "humanReviewPoint": "Priorities and decisions are set in the review, not in the draft."
    },
    {
      "id": "evidence-audit",
      "title": "Audit the brief's evidence before the meeting",
      "prompt": "Before I bring this brief into the review: list every claim it makes with its citation, flag any claim whose source is stale or missing, and separate what the sources show from what the brief inferred. I want to know exactly where the brief is standing on solid ground.",
      "expectedArtifact": "Claim-by-claim evidence audit",
      "humanReviewPoint": "You decide which weak-evidence claims survive into the meeting."
    },
    {
      "id": "unowned-actions",
      "title": "Hunt the unowned actions",
      "prompt": "Sweep this week's sources for actions that were raised, promised, or implied but have no named owner or date. List each with its source span. Do not assign owners; surfacing them is the job, assigning them is the meeting's.",
      "expectedArtifact": "Unowned-actions list with source spans",
      "humanReviewPoint": "Ownership gets assigned in the room, on the record."
    },
    {
      "id": "decision-queue",
      "title": "Build the pending-decision queue",
      "prompt": "From the decision log and this week's discussions, list every decision that is open: what it is, who it is waiting on, what evidence exists on each side, and how long it has been open. Frame each one; resolve none of them.",
      "expectedArtifact": "Pending-decision queue with framing",
      "humanReviewPoint": "Decisions resolve in the review; aging ones escalate by your rule, not the agent's."
    },
    {
      "id": "commitment-diff",
      "title": "Diff this week against last week's commitments",
      "prompt": "Here is last week's brief with its commitments. Diff it against this week's sources: what was delivered, what slipped, what changed shape. Name the slips plainly with their source spans; no softening.",
      "expectedArtifact": "Commitment diff with source spans",
      "humanReviewPoint": "What a slip means, and what happens about it, is the room's call."
    },
    {
      "id": "recurring-setup",
      "title": "Set this up as a recurring draft",
      "prompt": "Set this brief up to compile on a schedule before our weekly review, from the same read-only sources, to the same format, stopping at the draft every time. If a source is unavailable on a run, produce the brief with that gap named rather than skipping the run.",
      "expectedArtifact": "Recurring brief configuration with gap-handling rule",
      "humanReviewPoint": "The recurring draft still lands in your review; recurrence never becomes autonomy."
    }
  ],
  "humanOwnedResponsibilities": [
    "Priorities, risk acceptance, and every operating decision: the brief surfaces the decision queue, the room resolves it",
    "Ownership assignment: unowned actions get named by the brief and owned by people, in the meeting",
    "Judgment on slipped commitments: the diff names them, what happens next is leadership's",
    "The write boundary: nothing the agent produces changes a source system"
  ],
  "risks": [
    {
      "id": "brief-becomes-the-decider",
      "level": "medium",
      "description": "A well-written brief can quietly become the decision: proposed priorities read as set, inferred owners read as assigned, and a smoothed narrative hides a slipped commitment.",
      "mitigation": "Proposals labeled as proposals, owners only from explicit sources, slips named plainly with citations, and the read-only boundary structural."
    }
  ],
  "sources": [
    {
      "id": "occupation-marketing-managers",
      "title": "Marketing Managers occupational render model",
      "url": "https://singulariki.com/roles/marketing-managers",
      "publisher": "gold.onet_role_starter_surface",
      "lastReviewedAt": "2026-06-03"
    },
    {
      "id": "occupation-customer-service-representatives",
      "title": "Customer Service Representatives occupational render model",
      "url": "https://singulariki.com/roles/customer-service-representatives",
      "publisher": "gold.onet_role_starter_surface",
      "lastReviewedAt": "2026-06-03"
    },
    {
      "id": "openai-chatgpt-work",
      "title": "ChatGPT Work and Codex",
      "url": "https://help.openai.com/en/articles/20001275-chatgpt-work-and-codex",
      "publisher": "OpenAI",
      "lastReviewedAt": "2026-07-11"
    },
    {
      "id": "openai-work-deliverables",
      "title": "Creating and editing documents, spreadsheets, and presentations with ChatGPT Work",
      "url": "https://help.openai.com/en/articles/20001278-creating-and-editing-documents-spreadsheets-and-presentations-with-chatgpt-work",
      "publisher": "OpenAI",
      "lastReviewedAt": "2026-07-11"
    },
    {
      "id": "openai-work-cloud-browser",
      "title": "Using cloud browser in ChatGPT",
      "url": "https://help.openai.com/en/articles/20001280-using-cloud-browser-in-chatgpt",
      "publisher": "OpenAI",
      "lastReviewedAt": "2026-07-11"
    },
    {
      "id": "openai-work-desktop-browser",
      "title": "Using the built-in browser in the ChatGPT desktop app",
      "url": "https://help.openai.com/en/articles/20001277-using-the-built-in-browser-in-the-chatgpt-desktop-app",
      "publisher": "OpenAI",
      "lastReviewedAt": "2026-07-11"
    },
    {
      "id": "openai-chatgpt-skills",
      "title": "Skills in ChatGPT",
      "url": "https://help.openai.com/en/articles/20001066",
      "publisher": "OpenAI",
      "lastReviewedAt": "2026-07-11"
    },
    {
      "id": "openai-chatgpt-scheduled-tasks",
      "title": "Scheduled Tasks in ChatGPT",
      "url": "https://help.openai.com/en/articles/10291617-tasks-in-chatgpt",
      "publisher": "OpenAI",
      "lastReviewedAt": "2026-07-11"
    },
    {
      "id": "openai-workspace-agents",
      "title": "ChatGPT Workspace Agents for Enterprise and Business",
      "url": "https://help.openai.com/en/articles/20001143",
      "publisher": "OpenAI",
      "lastReviewedAt": "2026-07-11"
    }
  ],
  "freshness": {
    "platformVersion": "2026-07-09-launch",
    "platformReviewedAt": "2026-07-11",
    "occupationalDataVersion": "O*NET 30.3",
    "occupationalDataGeneratedAt": "2026-06-03T05:05:52.989984+00:00"
  },
  "quality": {
    "uniqueOccupationalOrTaskEvidence": false,
    "validPlatformSpecificWorkflow": true,
    "clearOutputArtifact": true,
    "realCapabilityMatch": true,
    "meaningfulHumanReviewSection": true,
    "sourcesAndFreshness": false,
    "distinctInternalRelationships": true,
    "noUnresolvedFactualOrProductVersionFailure": false,
    "indexable": false
  }
}