Optimize focus coordination policy portfolio

What it's for

Moves Gitrevio beyond reporting meeting load: it can show which evidence-backed async, batching or protected-focus policies best balance delivery economics, deep work, response coverage and timezone fairness.

What you give it

Inputs split into evidence read from your connected systems, calibration your team owns, and numerical controls that affect precision but never the result's meaning.

{
  "budget": 500,
  "capacity_units": 3,
  "focus_shortfall_cost_per_minute": 10,
  "maximum_focus_shortfall_minutes": 50,
  "minimum_response_coverage": 0.85,
  "policy_options": [
    {
      "capacity_units": 1,
      "causal_effect_verified": true,
      "controls_verified": true,
      "depends_on": [],
      "design_reliability": 0.9,
      "evidence_verified": true,
      "excludes": [],
      "focus_gain_minutes_by_scenario": [
        150,
        250
      ],
      "id": "async-api",
      "implementation_cost": 100,
      "loss_reduction_fraction_by_scenario": [
        0.3,
        0.4
      ],
      "policy_type": "async_status_and_protected_focus",
      "prospectively_registered": true,
      "response_coverage_change_by_scenario": [
        -0.02,
        -0.03
      ],
      "timezone_burden_by_scenario": [
        2,
        4
      ],
      "workstream_id": "api"
    },
    {
      "capacity_units": 1,
      "causal_effect_verified": true,
      "controls_verified": true,
      "depends_on": [],
      "design_reliability": 0.9,
      "evidence_verified": true,

What you get back

This is the actual output of running the example above — computed by the same function the platform calls, not an illustration.

{
  "configuration": {
    "budget": 500,
    "capacity_units": 3,
    "maximum_cvar": null,
    "maximum_expected_loss": null,
    "maximum_focus_shortfall_minutes": 50,
    "maximum_timezone_burden": null,
    "minimum_response_coverage": 0.85,
    "tail_probability": 0.95
  },
  "decision": "portfolio_selected",
  "evidence_diagnostics": {
    "eligible_options": 2,
    "excluded_options": 0,
    "unverified_workstream_ids": []
  },
  "excluded_options": [],
  "interpretation": "The portfolio is aggregate decision support. Effects require prospective causal evidence and are shrunk by design reliability; selection does not authorize calendar changes, reduce incident coverage, or evaluate individual performance.",
  "method": "design_reliability_shrunk_common_scenario_shared_loss_focus_coordination_pareto_portfolio",
  "pareto_frontier": [
    {
      "capacity_units": 2,
      "expected_focus_shortfall_minutes": 0,
      "expected_loss": 1755.2,
      "expected_timezone_burden": 4.8,
      "expected_total_cost": 1955.2,
      "implementation_cost": 200,
      "loss_cvar": 3520,
      "loss_var": 3520,
      "minimum_response_coverage": 0.873,
      "selected_option_ids": [
        "async-api",
        "async-product"
      ]
    }
  ],
  "search": {
    "combination_count": 4,
    "evaluated_portfolios": 4,
    "feasible_portfolios": 1,
    "global_optimality_proven": true,
    "method": "exact_enumeration"
  },

How it works

Forecasting & survival — Estimate when something completes or fails, with censoring and unresolved work handled honestly rather than dropped.

1. 1 Admit only prospectively registered, controlled and causally verified aggregate policy effects; shrink loss reduction, focus gain and response change toward zero by governed design reliability while retaining full implementation and timezone burden.
2. 2 Evaluate one baseline or policy per workstream under common scenarios, count each shared loss group once, preserve dependencies/exclusions, and calculate focus shortfall, minimum response coverage, timezone burden, expected loss and upper-tail VaR/CVaR.
3. 3 Exact-enumerate or deterministically beam-search the feasible portfolio, expose solver certainty and the cost-risk-focus-timezone Pareto frontier, and return a human-reviewed plan rather than changing calendars.

Before you trust it

Every tool in the catalog ships with the conditions under which its answer is meaningful — and the conditions under which it should abstain instead of guessing.

Calibrating it to your org

Calibration workflow

1. 1 Define the management decision, target outcome, aggregate unit, privacy boundary, cadence, and prediction/intervention horizon for this organization.
2. 2 Build a tenant-scoped historical cohort using only information available before each prediction or decision; preserve zero periods, censoring, assignment probabilities, and unresolved outcomes when the method requires them.
3. 3 Estimate statistical parameters on training history, but obtain costs, utilities, risk tolerance, practical-effect thresholds, capacity, and policy constraints from accountable decision owners.
4. 4 Validate on later time windows or held-out aggregate units at the deployment grain, against a simple baseline and the function-specific validation strategy.
5. 5 Deploy only if the returned decision clears evidence, overlap, calibration, robustness, and guardrail checks; warning, unsupported, schema-gap, and fallback decisions are abstentions.
6. 6 Monitor realized outcomes, data drift, coverage, and decision regret; recalibrate at a governed cadence or after a detected regime/definition change, never merely because a stakeholder dislikes the result.

Call it from your AI

You don't wire up 388 tools in your MCP client. The GitRevio MCP server exposes 18 tools, three of which let an agent search the catalog, read a tool's schema, and run it — so the assistant finds this one on its own.

gitrevio_capabilities_search
  { "q": "choose aggregate async meetingbatching protectedfocus or" }
  → finds "optimize_focus_coordination_policy_portfolio"

gitrevio_capability_describe
  { "capability_id": "optimize_focus_coordination_policy_portfolio" }
  → returns the input schema and agent guidance shown on this page

gitrevio_capability_run
  { "capability_id": "optimize_focus_coordination_policy_portfolio", "arguments": { ... } }
  → returns the result shown above

Works in Claude Desktop, Claude Code, Cursor, Cline, Continue.dev, Goose and Aider. See the MCP server.

Related tools

See every tool in People, retention & knowledge →