Forecast change adoption bass diffusion

What it's for

Turns rollout plans into calibrated adoption forecasts: leaders can see when AI tools, process changes, platforms, or controls will actually reach critical mass, where enablement capacity binds, and how much value is enabled under explicit assumptions.

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.

{
  "current_rollouts": [
    {
      "adopted_to_date": 20,
      "adoption_capacity_per_period": 15,
      "eligible_population": 100,
      "id": "ai-assistant-rollout",
      "value_per_adopter": 1000
    }
  ],
  "historical_rollout_periods": [
    {
      "adopted_at_start": 0,
      "cohort_id": "cohort-0",
      "eligible_population": 100,
      "id": "adoption-0-0",
      "new_adoptions": 10,
      "period": 0
    },
    {
      "adopted_at_start": 10,
      "cohort_id": "cohort-0",
      "eligible_population": 100,
      "id": "adoption-0-1",
      "new_adoptions": 10,
      "period": 1
    },
    {
      "adopted_at_start": 20,
      "cohort_id": "cohort-0",
      "eligible_population": 100,
      "id": "adoption-0-2",
      "new_adoptions": 10,
      "period": 2
    },
    {
      "adopted_at_start": 30,
      "cohort_id": "cohort-0",
      "eligible_population": 100,
      "id": "adoption-0-3",
      "new_adoptions": 10,
      "period": 3
    },
    {

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.

{
  "assumptions": [
    "Historical cohorts use the same adoption definition, period cadence, eligibility denominator, and no-churn convention as the current rollout.",
    "Adoption hazard is adequately represented by an organization-wide spontaneous innovation rate plus imitation proportional to current adoption; cohort heterogeneity beyond capacity is not modeled.",
    "Enablement capacity is a hard per-period cap and value_per_adopter is an owner-supplied enabled-value scenario, not causal value inferred from adoption activity."
  ],
  "configuration": {
    "horizon_periods": 6,
    "imitation_grid_points": 15,
    "innovation_grid_points": 15,
    "maximum_imitation_rate": 1,
    "maximum_innovation_rate": 0.2,
    "minimum_target_probability": 0.8,
    "simulations": 500,
    "target_adoption_fraction": 0.8
  },
  "decision": "target_adoption_not_yet_supported",
  "detail_counts": {
    "current_rollouts": 1
  },
  "executive_summary": {
    "current_adoption_fraction": 0.2,
    "expected_enabled_value_at_horizon": 74096,
    "horizon_adoption_fraction_p50": 0.74,
    "horizon_target_probability": 0.144,
    "posterior_imitation_rate_p50": 0.1429,
    "posterior_innovation_rate_p50": 0.1001
  },
  "interpretation": "The Bass posterior forecasts aggregate uptake under the supplied diffusion and capacity model. Boundary posterior mass, policy changes, churn, network targeting, or materially different cohorts require model expansion or abstention.",
  "method": "bayesian_capacity_constrained_bass_adoption_diffusion_v1",
  "period_forecast": [
    {
      "adoption_fraction_p10": 0.27,
      "adoption_fraction_p50": 0.3,
      "adoption_fraction_p90": 0.34,
      "expected_enabled_value": 30298,
      "period": 0,
      "probability_target_adoption": 0
    },
    {
      "adoption_fraction_p10": 0.35,
      "adoption_fraction_p50": 0.41,
      "adoption_fraction_p90": 0.45,
      "expected_enabled_value": 40432,

How it works

Sequential Bayesian & bandits — Learn while deciding — update beliefs as evidence arrives and choose where the next unit of effort is worth spending.

1. 1 Validate every historical cohort as a no-churn adoption stock-flow ledger with a constant eligibility denominator, consecutive periods, and adopted-at-start plus new-adoption reconciliation.
2. 2 Evaluate a bounded two-dimensional posterior grid for the Bass spontaneous-innovation and imitation rates using the binomial likelihood of new adoption among the remaining eligible population, retaining posterior boundary mass as a misspecification warning.
3. 3 Draw one organization-level parameter pair per simulation and propagate each current cohort forward, sampling adoption hazards as innovation plus imitation times current penetration while enforcing its hard enablement-capacity ceiling.
4. 4 Return aggregate and cohort adoption quantiles, probability of the governed target, and owner-supplied enabled value by period; abstain or expand the model when posterior mass presses against grid bounds or cohort/churn assumptions fail.

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": "forecast aggregate organizational change or tool" }
  → finds "forecast_change_adoption_bass_diffusion"

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

gitrevio_capability_run
  { "capability_id": "forecast_change_adoption_bass_diffusion", "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 Measurement integrity →