SITEBORNE SIGNAL MODULE

AnswerMap — cited website guidance

Answers natural-language questions from approved website sources and links every supported claim back to its source.

Try the demonstration Add to a project brief

BUSINESS OUTCOME

What this capability changes.

Reduce information friction
Expose approved answers
Escalate unknown questions

Best for

Professional firms, Service businesses, Software companies

AI: requiredStatus: active

From $3,500

Care from $250/month

Seeded demonstration usageAvailable

System view

Required

cloudflare-workers, cloudflare-ai-gateway, cloudflare-workers-ai, cloudflare-vectorize, cloudflare-d1

Optional

cloudflare-r2, cloudflare-kv, cloudflare-ai-search

Fallback

Semantic retrieval, source excerpts, conventional search, and contact escalation.

Provider dependencies

cloudflare-workers, cloudflare-ai-gateway, cloudflare-workers-ai, cloudflare-vectorize, cloudflare-d1, cloudflare-r2, cloudflare-kv, cloudflare-ai-search

Last verified

2026-08-01

Provider limits, terms, model availability, and pricing may change. Production accounts remain client-owned.

Data classification

Public website content
Optional approved documents

LAUNCH ALLOWANCE

Low-volume inference

Optional inference for classification, summarization, and query rewriting.

Current limit: 10,000 neurons/day; model availability varies and some models require Workers Paid.
Expected light use: Low-volume classification, summarization, metadata, and query rewriting.
What consumes it: Model-specific neuron consumption, resetting daily at 00:00 UTC.
Fallback: Deterministic output or retrieval-only result.
Paid successor: Workers Paid or approved generation adapter
Commercial use: Commercial use permitted for approved models under current terms.
Data warning: Model registry and policy checks are mandatory.
Last verified: 2026-08-01

View all referenced allowances

Low-volume inference: 10,000 neurons/day; model availability varies and some models require Workers Paid.
Semantic retrieval: 30M queried vector dimensions/month and 5M stored vector dimensions.
Beta cited retrieval accelerator: Open-beta allowance described as 20K queries/month, 100K files/instance, and 500 crawled pages/day; terms may change with notice.

Upgrade triggers

daily requests — 75%. Optimize cache or review paid tier.
answer support rate — below target. Restrict answer generation and show retrieval-only results.

Conventional fallback: Semantic retrieval, source excerpts, conventional search, and contact escalation.

View implementation proof

Decision rationale

The implementation favors semantic HTML, static rendering, typed content, and isolated on-demand routes. Optional AI never controls pricing, eligibility, or emergency routing.

Controls

WCAG 2.2 AA target
Provider-neutral adapters
Usage caps and kill switches
Client-owned production accounts
Conventional fallbacks

Verified evidence

Mock mode runs from a clean clone without paid credentials.
Kill switch and allowance states are typed configuration.
Primary navigation and contact paths remain independent of this module.

Known limitation

External provider allowances and production behavior require owner accounts and deployment-time verification.