Scarlet Beast Scarlet Beast Hunting Truth in a World of Shadows
Transmissions
NEWStartup Frameworks are for sale — buy a launch-ready business, not a slide deck.Sep 04 NEWTech’s Tinder — a swipe-to-match deal engine for hardware buyers and sellers — joins the framework catalogue.Sep 04 NEWSignal — the creators network for the people who build the machines (formerly networkedin) — joins the framework catalogue.Sep 03 NEWScarlet Beast Poker is packaged for acquisition — platform, native apps, the Hiss AI and the public API.Sep 03 LIVEBusiness Plans — every scope, timeline and price we quote, in one vault.Sep 01 NEWFree technical audit — one call, no pitch, a written findings list you keep either way.Aug 28 LIVEGROWL — the crypto and forex exchange, plus an algorithmic bot marketplace.Aug 26 LIVEHiss — production poker AI: deep reinforcement learning, computer vision, real-time inference.Aug 22 NEWPerformance engineering — measurable TTFB, LCP and CLS gains on enterprise traffic.Aug 18 NEWAdobe Commerce and Shopify Plus modernization — migrations that ship without downtime.Aug 05 NEWThe technology stack is published — what we run, why we chose it, what it costs.Aug 01 NEWStartup Frameworks are for sale — buy a launch-ready business, not a slide deck.Sep 04 NEWTech’s Tinder — a swipe-to-match deal engine for hardware buyers and sellers — joins the framework catalogue.Sep 04 NEWSignal — the creators network for the people who build the machines (formerly networkedin) — joins the framework catalogue.Sep 03 NEWScarlet Beast Poker is packaged for acquisition — platform, native apps, the Hiss AI and the public API.Sep 03 LIVEBusiness Plans — every scope, timeline and price we quote, in one vault.Sep 01 NEWFree technical audit — one call, no pitch, a written findings list you keep either way.Aug 28 LIVEGROWL — the crypto and forex exchange, plus an algorithmic bot marketplace.Aug 26 LIVEHiss — production poker AI: deep reinforcement learning, computer vision, real-time inference.Aug 22 NEWPerformance engineering — measurable TTFB, LCP and CLS gains on enterprise traffic.Aug 18 NEWAdobe Commerce and Shopify Plus modernization — migrations that ship without downtime.Aug 05 NEWThe technology stack is published — what we run, why we chose it, what it costs.Aug 01
Markets
BTC$79,738▲ +0.40%ETH$2,459▲ +0.41%SOL$103.15▲ +1.63%XRP$1.41▲ +0.48%BNB$763.51▲ +6.83%ADA$0.2165▲ +1.01%DOGE$0.0874▲ +2.81%LINK$11.84▲ +1.76%AVAX$7.54▲ +2.51%DOT$0.9176▲ +7.97%LTC$53.59▲ +6.43%TRX$0.3331▲ +1.43%BTC$79,738▲ +0.40%ETH$2,459▲ +0.41%SOL$103.15▲ +1.63%XRP$1.41▲ +0.48%BNB$763.51▲ +6.83%ADA$0.2165▲ +1.01%DOGE$0.0874▲ +2.81%LINK$11.84▲ +1.76%AVAX$7.54▲ +2.51%DOT$0.9176▲ +7.97%LTC$53.59▲ +6.43%TRX$0.3331▲ +1.43%
GROWL feed

Statement of Work · SOW-01

Concept-first
AI outbound engine

Every prospect on the call list gets a working, branded demo of the client’s product — built from their own public data the night before anyone dials — and an AI voice agent opens the call by pointing at it. Concept in, client out.

Prepared by Scarlet Beast  ·  Date 20 September 2026  ·  Status Draft for discussion

The offer

The edge is sequence, not volume.

A normal cold call asks a prospect to imagine the product. This one opens with a URL they can load while still on the phone, showing their own logo, palette and data inside the thing being sold. The ask moves from “give me thirty seconds” to “I already built it, tell me what’s wrong with it.”

That inversion is the whole thesis, and it only works if building 100 tailored concepts costs hours rather than weeks. Everything below exists to make the concept cheap enough to give away before a prospect has agreed to anything.

~$2Cost per bespoke concept
800 msTurn latency budget
13 wksSignature to pilot readout
2 armsConcept vs. control
SubsystemWhat it doesThe hard part
Prospect GraphFinds companies matching a chosen segment, fingerprints their public stack, resolves a reachable phone number and a namePhone numbers, not companies. Finding the business is easy; a number that reaches an owner is the scarce input
Concept FactoryClones brand assets and real data off the prospect’s public presence into a sandbox tenant of the client’s product, configures it, records a walkthrough, renders a one-page deckUnattended throughput and taste. 100 concepts a night, none of which look auto-generated
Voice AgentDials, opens on the concept, qualifies, handles objections, books or warm-transfers, and writes the call back to CRMTurn latency and barge-in. Past roughly 800 ms of silence the prospect hangs up on a robot
Context ServiceAssembles a per-prospect dossier and retrieves objection and segment playbooks so the agent speaks to this company, not to a categoryRetrieval has to finish before the dial, not mid-sentence

The fifth component is the one that makes this a test rather than a claim. Phase 5 splits the same list into a concept-first arm and a no-concept control arm, dialed by the same agent with the same opener minus the URL. If meeting-set rate does not separate, the Concept Factory is expensive theatre and the engagement stops at Phase 5 having spent a pilot budget instead of a platform budget.

Scope of work

Seven phases. Nothing accepted on a demo.

Nineteen phase-weeks of work compressed into 13 calendar weeks, plus 6 optional weeks after the readout. Phases 1 and 2 run in parallel, as do 3 and 4, so first supervised dials land in week 12 and the pilot readout in week 13. Each phase is accepted on a criterion that can be checked in an afternoon.

PhaseWksDeliverableAccepted when
0 · Definition2One segment, one product, a written concept spec, a written definition of “qualified meeting”, and a compliance baseline reviewed by the client’s counselAll five documents signed. No build starts before counsel signs the calling plan
1 · Prospect Graph3Discovery and enrichment pipeline, scoring model, 1,000 seeded records1,000 companies in the segment, 60% or more carrying a verified phone number and a named contact, fully DNC-scrubbed
2 · Concept Factory4Brand extraction, sandbox provisioning, product configuration, walkthrough capture, one-page deck render100 concepts built unattended in one overnight run; 90% or more pass a blind 5-point visual QA; median build under 6 minutes
3 · Voice Agent5Asterisk/ARI call control, streaming media pipeline, dialogue policy, voicemail drop, warm transfer50 supervised test calls at median turn latency 800 ms or less and p90 1.5 s or less, barge-in working, zero dials outside permitted windows
4 · Context & CRM3Dossier packer, pgvector knowledge base, CRM schema, attribution IDs, call scoringDossier assembled pre-dial in 20 s or less; every test call transcribed, scored, and joined to its concept ID
5 · Pilot2100 concept-first dials, 100 control dials, instrumented readoutBoth arms complete on the same list, readout delivered with confidence intervals on meeting-set rate
6 · Platform6Multi-tenancy, self-serve offer onboarding, usage metering and billing — optionalA second tenant loads its own offer and list and dials, with no Scarlet Beast engineering time

Work not listed above is out of scope by default. Anything added moves through a written change order with its own price and its own acceptance criterion.

Technical architecture

Two pipelines meet at the dial.

The asset pipeline runs overnight and is throughput-bound; the call pipeline runs in real time and is latency-bound. They share one database and never share a process.

ASSET PIPELINE — OVERNIGHT, THROUGHPUT-BOUND Seed lists+ web presence Prospect Graphdiscover · enrich · score Concept Factory100 builds / night Asset CDNdemo · video · deck Compliance Gateconsent · DNC · windows Context Servicepre-dial dossier CALL PIPELINE — REAL TIME, LATENCY-BOUND DialerAsterisk ARI Prospecton the phone Voice PipelineSTT → Claude → TTS RECORD CRM + attributionone row per concept ID Warm transfer to closer Scorecard + control arm SIP trunk audio

Left to right: a list becomes scored prospects, scored prospects become concepts and a dossier, the Compliance Gate decides which of them may lawfully be dialed today, and only then does the Dialer place a call whose audio the Voice Pipeline drives.

ComponentWhat it ownsBuilt on
Prospect GraphCompany discovery, public-stack fingerprinting, contact resolution, scoringPostgres, headless Chromium, enrichment APIs
Concept FactoryBrand extraction, sandbox provisioning, product configuration, walkthrough capture, deck renderPlatform connector, Playwright, ffmpeg, worker queue
Asset CDNThe per-prospect demo URL, the walkthrough video, the one-page PDFCloudflare Pages and R2
Compliance GateDNC scrubbing, calling windows by timezone, consent state, recording rules by jurisdictionRules service over Postgres, national and state DNC feeds
Context ServicePre-dial dossier assembly and playbook retrievalpgvector, Claude
DialerOrigination, call control, recording, transfer, voicemail detectionAsterisk with ARI, SIP trunk
Voice PipelineStreaming transcription, turn policy, speech synthesis, barge-inAsterisk ExternalMedia, streaming STT, Claude, ElevenLabs
CRMProspects, concepts, calls, outcomes, attribution IDsPostgres
ScorecardPer-call scoring, arm comparison, operator dashboardsPostgres with Grafana

The one architectural decision worth arguing about is that retrieval happens before the dial, not during it. A dossier assembled mid-turn adds 200 to 600 ms to the first response, which is exactly where a cold call is lost. The Context Service packs a fixed-size bundle per prospect ahead of the call and the Voice Pipeline treats it as read-only state.

The call

Eight moves, one budget.

The budget is the time between the prospect finishing a sentence and hearing the first syllable back: 800 ms median, 1.5 s at p90. Past that the prospect concludes they are talking to a machine that is thinking, and hangs up.

DIALER PROSPECT STT AGENT CRM 800 ms turn budget Dial, detect human vs voicemail Attach pre-packed dossier Opener naming the concept URL Prospect speaks Streaming transcript Reply, barge-in enabled Book, transfer, or end Transcript, score, outcome

The dashed band is the only part of the call that is a hard engineering constraint: end-of-speech to first syllable, every turn.

StageBudgetNote
End-of-speech detection120 msVoice activity detection, tuned per trunk codec
Final transcript150 msStreaming STT, partials already delivered
Context assembly10 msDossier is pre-packed, so this is a memory read
First model token300 msClaude, short system prompt, cached prefix
First synthesized audio150 msStreaming TTS, sentence-level chunking
Trunk and jitter70 msSIP trunk round trip
Total to first syllable800 msThe number the pilot is held to

Three behaviours carry the call and each is a separate piece of work. Barge-in stops synthesis inside 100 ms when the prospect talks over the agent, because an agent that talks through an interruption reads as a robocall no matter how good the voice is. Voicemail detection routes to a 20-second drop naming the concept URL rather than attempting a conversation with an answering machine. Warm transfer hands a live, qualified call to a human closer with the transcript already on their screen, which is the only moment in the system where a person is required.

The agent’s dialogue policy is written and versioned as a document, not buried in a prompt string: opener, qualification questions, an objection library keyed to the segment, the booking path, the transfer path, and the hard stops. Every call is scored against that policy, so a change to the policy is measurable against the calls that preceded it.

Stack and integrations

One connector per engagement.

Everything is either already running at Scarlet Beast or is a commodity with two viable vendors. The only layer that changes from engagement to engagement is the connector to whatever the client sells, and Phase 0 builds exactly one.

LayerChoiceAlternativeWhy this one
Demo substrateOne connector to the client’s product: a sandbox tenant, a trial org, or a scripted instanceA cloned copy of the client’s own demo environment per prospectFree, disposable tenants are what make 100 throwaway concepts economic. Ecommerce platforms, most B2B SaaS and self-hosted products all provide one; Phase 0 confirms it before anything is priced
Browser automationPlaywright on headless ChromiumPuppeteerBrand extraction and product configuration both need a real browser; Playwright’s tracing makes failed builds debuggable
TelephonyAsterisk with ARI, SIP trunk to TwilioDirect carrier trunk, or a managed voice-agent APIOwning call control keeps recording, transfer and per-call logic in our code; a managed API would be faster to stand up and far harder to tune
Media transportAsterisk ExternalMedia over RTPAudioSocketExternalMedia gives raw frames to the pipeline without a second process in the path
TranscriptionStreaming STT with partial resultsTwo vendors benchmarked in Phase 3Partials are what let the agent start thinking before the prospect stops talking
ReasoningClaude — a small model for turn-taking, a larger one for objection handlingSingle-model fallbackTurn latency and reasoning quality want different models; the policy decides which one a turn needs
SpeechElevenLabs streamingSecond vendor benchmarked in Phase 3Sentence-chunked streaming is the difference between 150 ms and 900 ms to first audio
DataPostgres with pgvectorNoneOne database for CRM, prospect graph and embeddings keeps attribution a join rather than a pipeline
AssetsCloudflare Pages and R2S3 and CloudFrontAlready in use for Scarlet Beast properties, and a concept URL has to load instantly on a phone mid-call
ObservabilityGrafana over Postgres, full call recordingsHosted APMPer-call scoring is the product metric, so it lives with the data rather than in a vendor

The two integrations that carry schedule risk are programmatic provisioning and configuration of the client’s own product, which differs by product and sometimes needs the client’s engineers, and SIP trunk provisioning, where number acquisition and carrier vetting can take longer than the engineering. Both start in Phase 0 rather than when their phase opens.

Compliance and consent

Consent-first, by construction.

This section is the reason the architecture looks the way it does, and it is written by an engineer rather than a lawyer. Nothing here is legal advice, and Phase 0 does not close until the client’s counsel has reviewed and signed the calling plan.

The governing fact: on 8 February 2024 the FCC ruled that an AI-generated voice is an “artificial” voice under the TCPA, which places AI voice calls in the same regulated category as prerecorded calls rather than making them illegal outright. Marketing calls in that category need prior express consent, and prior express written consent for calls to wireless numbers, plus caller identification and a working opt-out. There is no general business-to-business exemption: the FTC’s Telemarketing Sales Rule exempts many B2B solicitations from the national Do Not Call registry, but the TCPA’s autodialer and artificial-voice rules apply to any number, and a sole proprietor’s mobile keeps full protection. Several states also run their own registries that reach business lines; counsel enumerates them for the target segment in Phase 0.

Sources: Wiley — FCC extends TCPA restrictions to AI-generated voices  ·  LeadCompliant — B2B telemarketing rules

That collides directly with the naive version of this idea, because a large share of small-business phone numbers are the owner’s mobile. An AI voice cold-dialing that list is the expensive kind of mistake. So the engine is built consent-first, and the Concept Factory turns out to be the consent mechanism as well as the pitch.

  1. The concept is delivered before the call — by email, DM or an existing channel — as a link to the prospect’s own branded demo.
  2. The concept page carries the opt-in: a named, specific, written consent to be contacted by an automated or AI voice call about this concept, logged with timestamp, IP and the exact language shown.
  3. Only consented records enter the AI dialing queue. The Compliance Gate refuses the rest at the database level, not in application code.
  4. Non-consented prospects route to a human-dialed queue, where the same dossier and the same concept URL are used by a person. Both paths are in scope; only one of them can be automated end to end.
RuleEnforcement
Consent on fileRow-level: the dialer’s query cannot return an unconsented record
DNC scrubNational plus applicable state and internal lists, re-scrubbed within 31 days of the dial
Calling window8am to 9pm in the called party’s timezone, derived from area code and company address, with the stricter of the two applied
Identity disclosureThe opener states the caller’s name, the company on whose behalf the call is made, and that the voice is AI, within the first sentence
Opt-outHonored in-call by intent, not keyword, and written to a suppression list shared across every campaign within 24 hours
Recording consentTwo-party-consent states get the notice before any audio is retained; state determined before the dial, not after

Two further constraints are worth stating because they cost money. Voice cloning of a real person is out of scope entirely: the agent uses a synthetic voice that belongs to no one. And the agent never claims to be human, including when asked directly, which costs some connect-rate and removes an entire category of risk.

The residual risk is real and should be priced rather than hidden. TCPA exposure runs per call, class actions are the normal remedy, and no engineering control substitutes for counsel’s sign-off on the specific list, the specific script and the specific consent language.

Commercial models

A retainer for the build. Success fees for the thesis.

Figures below are the proposed rate card, not a quote, and every one of them is negotiable before signature. All amounts in USD.

Default — hybrid

ComponentAmountTrigger
Build retainer$18,000 / mo × 4Monthly in advance, covering Phases 0 to 5
Operate retainer$9,500 / moBegins the month after pilot readout, 3-month minimum, 30 days notice
Infrastructure$1,400–2,900 / moAt cost, passed through with invoices, at 100 concepts and 2,000 dials per month
Meeting fee$250Per qualified meeting attended. “Qualified” is fixed in Phase 0 and does not move afterwards
Activation fee$750Per activation surviving 30 days, paid on the 31st day, not on activation
Trailing share12%Of attributable subscription revenue, 12 months from activation, from the client’s own billing export
Platform build$60,000Phase 6 only, fixed, at the client’s option after the readout

Swappable — the same SOW, three ways to pay for it

ModelUp frontOngoingUpsideTermFits when
Hybrid (default)$72,000 over 4 months$9,500 / mo + infra$250 / meeting, $750 / activation, 12% trailing for 12 months12 months from pilotThe client can fund a build and wants the operator’s incentives pointed at activations
Joint ventureNothingInfra split 50/5035% of attributable subscription revenue for 24 months, plus $150 per qualified meeting from the calling partner24 months; unwinds below 500 dials in the first 90 daysPartners bring product and phone time but no cash
Fixed fee$9k / $21k / $34k / $42k / $24k / $16k per phaseNone, or a separate operate SOWNonePer phaseThe client wants the asset, not a partner, and will run it themselves

Attribution decides the money, so it is mechanical rather than negotiated after the fact. Every concept carries an ID that travels through the demo URL, the signup link and the client’s activation webhook. An activation is attributable when it occurs within 90 days of a dial or a concept view carrying that ID, and the CRM row is the record of truth for both parties. Either side may audit it on 10 days notice.

Payment is net 15 for retainers and net 30 for success fees. Success fees are computed monthly from the client’s own billing export, so no party depends on the other’s dashboard.

Intellectual property. Scarlet Beast retains the engine, its code and its templates, and grants the client a perpetual, non-exclusive licence to run it for the client’s own offers. The client owns its prospect list, the concepts built for it, its call recordings and its CRM data. Segment exclusivity is available as a priced add-on under the fixed-fee model; under the joint venture it is implicit for the term.

Unit economics and pilot metrics

A bespoke demo costs about two dollars.

The variable cost of a 100-prospect campaign is roughly $210, and 95% of it is the concepts rather than the calls. That ratio is the finding that matters: giving away a working, bespoke demo to a stranger costs about two dollars, which is why the concept can precede the qualification instead of following it.

ItemUnit costBasis
Enrichment and fingerprinting$0.15Per prospect — enrichment API plus headless page loads
Concept build$1.20Per concept — provisioning, brand extraction, product configuration, capture and encode, deck render
Visual QA$0.852 minutes of a reviewer at $25/hr, on the 10% sampled plus every rejection
Unconnected dial$0.015Carrier only — roughly 88 of every 100 dials
Connected call$0.543 minutes: carrier 0.04, transcription 0.02, reasoning 0.11, speech 0.36, storage 0.01
Campaign of 100~$210$200 in concepts, $8 in telephony, the remainder in enrichment

Speech synthesis is two thirds of the cost of a connected call, so it is the first line to renegotiate at volume and the first place a cheaper model gets benchmarked in Phase 3.

Funnel stageConcept armControlWhat it tests
Decision maker reached12 / 10012 / 100List quality, not the pitch. Identical by construction
Past 60 seconds85Whether the opener buys attention
Concept opened6Whether the prospect actually looks
Qualified meeting31The primary endpoint
Activation within 30 days10Directional only at this sample size

Those numbers are hypotheses to be measured, not commitments, and the pilot has to be honest about its own power. At 100 dials per arm, a lift from 1% to 3% on meeting rate is indistinguishable from noise; detecting a move from 3% to 7% with 80% power takes roughly 465 dials per arm. The 100-dial pilot is a smoke test that proves the machine runs end to end and produces clean, attributable data. The powered comparison needs about 1,000 dials in total, which the engine can deliver in a week once Phase 3 is accepted.

One metric governs whether any of this ships: cost per qualified meeting, loaded with retainer and infrastructure. If it does not land below what the client currently pays an SDR for the same outcome, the readout says so.

Timeline, staffing and exclusions

Thirteen weeks, two hard dependencies.

Both start in week 1 regardless of which phase owns them: SIP trunk and number provisioning, and counsel’s review of the calling plan. Either one can put the whole schedule on the floor if it starts when its phase opens.

WeeksRunningGate at the end
1–2Phase 0, plus trunk provisioning and counsel review startedCalling plan signed, concept spec signed
3–6Phases 1 and 2 in parallel1,000 scored prospects and 100 concepts built overnight
7–11Phases 3 and 4 in parallel50 supervised calls inside the latency budget, dossiers packing in 20 s
12Integration, consent delivery to the pilot list, first live dialsBoth arms dialing, Compliance Gate refusing correctly
13Phase 5 pilot completes, readout deliveredGo or no-go on Phase 6
14–19Phase 6, only if the readout says goA second tenant self-onboards

Staffing is four people, none of them full-time across the whole engagement. Technical lead and architect at 0.8 FTE throughout; one backend engineer at 1.0 FTE on Phases 1, 2 and 4; one telephony engineer at 1.0 FTE on Phase 3; a designer doubling as visual QA at 0.3 FTE on Phases 2 and 5. From the client: a product owner for four hours a week, counsel in Phase 0, and a human closer reachable during pilot calling hours.

Assumptions. The client provides the product, a sandbox or partner account and credentials within five business days of start; the product can be provisioned and configured programmatically, or the client’s engineers provide an install path; counsel is available in Phase 0 rather than at the end; a trunk and numbers can be provisioned in the client’s name; and the chosen segment contains at least 3,000 identifiable companies with a public web presence. If the segment is thinner than that, Phase 0 picks a different one.

Out of scope unless added by change order: legal advice of any kind; DNC list subscriptions and carrier fees, which pass through at cost; building or modifying the client’s own product; connectors beyond the first one, which are priced per platform; inbound call handling, SMS, and any email sequencing beyond delivering the concept and capturing consent; integration with an existing CRM such as Salesforce or HubSpot; voice cloning of any real person, which is refused rather than priced; calling outside the United States and Canada, and calling in any language other than English; and closing the deals, which stays with the client’s closer throughout.

Open questions

Eight answers make this signable.

The first two change the price.

  • Which segment and which product go first? Every estimate above assumes one of each.
  • Who holds the calling number and the consent records — Scarlet Beast or the client? This allocates TCPA liability, and counsel should decide it, not the SOW.
  • Which commercial model, and who funds infrastructure in the months before any revenue?
  • Can the product be provisioned and configured programmatically without the client’s engineers touching it? If not, Phase 2 grows.
  • Does the product emit an activation webhook carrying a referrer parameter? Without one, attribution falls back to self-reporting and the trailing share gets argued about.
  • What does the client pay today for a qualified meeting? That is the number the readout is measured against.
  • Whose closer takes the warm transfers during the pilot?
  • Is the control arm acceptable? It spends about 100 dials of potential pipeline to find out whether the concept is doing the work — and it is the only part of this plan that can prove the idea rather than assert it.

SOW-01

Pick a segment. Pick a product.

Phase 0 is two weeks and it is the only part you have to decide anything to start.