CWM · The consumer intelligence core
Consumer World Model turns member, order and behavior facts into consumer understanding that teams, applications and AI can use. Start with the available standard analysis, then connect it to your workflow.
500,000 welcome credits with a new CWM account
Consumer World Model
Facts → Understanding
Member, order and behavior data
Consumer signals and behavioral representations
Your console, application or AI workflow
One member prediction returns next behaviors and personal purchase windows, combining consumer signals with brand demand context when the tenant fusion head is ready.
Interactive example
All states and numbers are synthetic examples, not live predictions or workspace readiness. No customer data is sent.
Behavior predictions remain available. Purchase windows stay unavailable until the brand's fusion head is trained and validated.
One final distribution over this example's four supported events. Next-event probabilities are uncalibrated.
| Next event | Probability |
|---|---|
| Purchase | 37% |
| Portal visit | 28% |
| Email click | 21% |
| Coupon redemption | 14% |
Email sent is an input context event, not a prediction target. Its probability is null. Other unsupported or uncovered events also stay unavailable.
Personal CWM signals + TimesFM brand demand context.
Chance of at least one purchase. These windows are cumulative; do not add them together or to the event distribution.
One member request returns distribution and purchaseWindows together.
curl --request GET \
"https://YOUR_API_HOST/api/v2/cwm/members/YOUR_MEMBER_UUID/next-behaviors" \
--header "Authorization: Bearer YOUR_API_KEY"{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "cwm_predict_next_behaviors",
"arguments": {
"member_id": "YOUR_MEMBER_UUID"
}
}
}Replace the API host, member UUID and API key with your workspace values.
Required access · predictions:read returns behaviors. Also grant metrics:read (or *) to enable purchase windows when the model is ready.
Synthetic excerpt only. Brand-model responses also include the full event catalog and coverage metadata; public-prior references use a separate six-class vocabulary.
{
"predictionKind": "next_event",
"unit": "probability_0_1",
"status": "degraded",
"distribution": {
"status": "ok",
"vocabulary": "member_event",
"normalization": "conditional_on_supported_events",
"calibrated": false,
"rows": [
{
"key": "purchase.completed",
"label": "Purchase",
"probability": 0.37,
"rank": 1,
"availability": "predicted"
},
{
"key": "portal.visited",
"label": "Portal visit",
"probability": 0.28,
"rank": 2,
"availability": "predicted"
},
{
"key": "email.clicked",
"label": "Email clicked",
"probability": 0.21,
"rank": 3,
"availability": "predicted"
},
{
"key": "coupon.redeemed",
"label": "Coupon redeemed",
"probability": 0.14,
"rank": 4,
"availability": "predicted"
},
{
"key": "email.sent",
"label": "Email sent",
"probability": null,
"rank": null,
"availability": "context_only"
}
]
},
"purchaseWindows": {
"unit": "probability_0_1",
"probabilities": {
"7": null,
"30": null,
"90": null
},
"calibrated": false,
"envelope": {
"status": "unavailable",
"backend": "cwm-timesfm-2.5",
"reasonCodes": [
"fusion_not_trained"
]
}
},
"reasonCodes": [
"fusion_not_trained"
]
}Synthetic data · TimesFM 2.5
An example forecast from 128 days of synthetic history. Compare the recent pattern with future daily demand and its quantiles.
Synthetic demand units
| Date (UTC) | Point forecast | q10–q90 |
|---|---|---|
| 2026-10-05 | 22.9 | 22.8–23.0 |
| 2026-10-06 | 21.3 | 21.2–21.4 |
| 2026-10-07 | 18.7 | 18.6–18.8 |
| 2026-10-08 | 17.1 | 17.0–17.1 |
| 2026-10-09 | 17.7 | 17.6–17.7 |
| 2026-10-10 | 20.0 | 20.0–20.1 |
| 2026-10-11 | 22.3 | 22.3–22.4 |
| 2026-10-12 | 22.9 | 22.9–22.9 |
| 2026-10-13 | 21.3 | 21.2–21.3 |
| 2026-10-14 | 18.7 | 18.6–18.7 |
| 2026-10-15 | 17.1 | 17.0–17.2 |
| 2026-10-16 | 17.7 | 17.6–17.7 |
| 2026-10-17 | 20.0 | 19.9–20.1 |
| 2026-10-18 | 22.4 | 22.3–22.4 |
| 2026-10-19 | 22.9 | 22.8–23.0 |
| 2026-10-20 | 21.3 | 21.2–21.4 |
| 2026-10-21 | 18.7 | 18.6–18.7 |
| 2026-10-22 | 17.1 | 17.0–17.1 |
| 2026-10-23 | 17.7 | 17.6–17.7 |
| 2026-10-24 | 20.0 | 19.9–20.0 |
| 2026-10-25 | 22.3 | 22.3–22.4 |
| 2026-10-26 | 22.9 | 22.8–22.9 |
| 2026-10-27 | 21.3 | 21.2–21.3 |
| 2026-10-28 | 18.7 | 18.6–18.7 |
| 2026-10-29 | 17.1 | 17.0–17.2 |
| 2026-10-30 | 17.7 | 17.6–17.7 |
| 2026-10-31 | 20.0 | 20.0–20.1 |
| 2026-11-01 | 22.4 | 22.3–22.4 |
| 2026-11-02 | 22.9 | 22.8–22.9 |
| 2026-11-03 | 21.3 | 21.2–21.3 |
Synthetic example, generated with TimesFM 2.5 weights. The forecast starts on 2026-10-05 (UTC); dates are fixed for the demo. Quantile coverage is uncalibrated. Values do not represent a customer's demand or individual purchase probabilities.
Receive one final probability distribution and ranking. The evaluated brand model takes priority, with up to 23 covered targets. When it is unavailable, internal public-prior models form a single six-class reference. Unsupported and context-only events remain unavailable.
Included automatically in the same member response: a tenant-private lightweight head combines CWM signals with TimesFM brand trends. Ready heads serve directly; missing training or evaluation leaves only the purchase windows unavailable.
Where the TimesFM 2.5 service is configured and daily history is complete, forecast revenue, orders or units sold for up to 90 days, with point estimates and nine quantiles.
Next-event probabilities sum to 100% over supported candidates and are uncalibrated. Purchase windows separately estimate at least one purchase within 7/30/90 days and are cumulative, never normalized with event classes. Elapsed silence is not conditioned in the event vector. The public-prior reference has not earned workspace validation.
Demand quantiles describe aggregate uncertainty; they are not individual purchase intervals and have not been calibrated. Missing data remain unavailable. No accuracy lift is asserted before your own evaluation.
Review observed behavior, consumer state and standard-model signals for purchase, long gaps and cart removal. Results identify missing data and the limits of each signal.
Explore behavioral lookalikes, clusters and anomaly review. Similarity helps you investigate an audience; it is not a promised conversion rate.
Use the CWM console, REST API or MCP from your application or AI client. Scoped keys control access to your workspace.
Usable analysis requires supported data and enough behavioral history. Unavailable signals are reported explicitly; a new account does not contain customer data or predictions.
Illustrative workflow · not a live prediction
Imported with your workspace identity and permissions.
Your team or application chooses how to use the result.
Console / REST API / MCP
Review analysis in the console or let an authorized application or AI client query CWM. Import supported facts, create a scoped key and follow the public reference for available operations.
Read the API & MCP reference →Prepaid usage
New CWM accounts receive welcome credits. Eligible operations deduct credits at the published rates. Purchase additional credits in your workspace; your balance and usage remain visible there.
Register with email and password or Google, and agree to the CWM user agreement. Service availability is shown during registration.
Try CWM →Research & advanced model direction
The broader CWM direction includes behavioral modeling and digital twins. Research benchmarks, per-brand model validation and simulation are described separately from the standard operations available in the self-service workspace.
CWM / Harness / Loop Marketing
Consumer intelligence · Core
Consumer World Model
Understand behavior, review consumer signals and discover audiences. Use CWM through its workspace, API or MCP.
Explore CWM →AI execution · Runtime
SocialHub Harness
Give AI the context, skills and tools to complete work. Keep execution within permissions, budgets and review rules.
Explore Harness →Marketing outcomes · Application
Agentic Retention Loop
Capture behavior, decide the next action, activate across channels and accumulate loyalty. Feed outcomes into the next cycle.
Explore Loop Marketing →Observed outcomes inform the next cycle. Model updates depend on data quality and validation.
CWM
Create a workspace, explore the console and connect your consumer data. Purchase credits when you need more capacity.
500,000 welcome credits with a new CWM account
Harness + Loop Marketing
Explore how CWM, Harness and Loop Marketing fit your existing data, channels and team workflows.
Book a demo →