Scarlett is a conversational sales agent embedded across hashinclu.de. She qualifies visitors, scores intent on five dimensions, captures contact details, and auto-generates a client-ready proposal — all before a human touches the conversation.
Static contact forms with five fields, no context, no qualification — every submission gets the same generic auto-reply.
Off-the-shelf chatbots that announce themselves as bots, dump information, and cannot tell a buyer from a job seeker.
No proposal, no follow-up SLA — qualified leads sit in an inbox until a human gets to them, hours or days later.
Sales teams flying blind — no scoring, no signals, no record of what the prospect actually said before the first call.
A real conversation — Scarlett presents as a team member, asks one question at a time, and probes for the real problem behind the request.
Lead captured naturally — name, mobile, email pulled mid-conversation in the user's own language, English or Gulf Arabic.
Auto-generated proposal — once Scarlett has enough context, a branded DOCX proposal is generated and emailed to the prospect within seconds.
Sales armed with context — every lead arrives with a tier, a score, BANT+F signals, industry tags, and the full transcript.
Most chatbots answer questions. Scarlett asks them. When a visitor describes a solution — "I want to build an app that scans license plates" — Scarlett's first move is to surface the underlying problem: tracking? Access management? Something else entirely?
This is consultative selling encoded into a system prompt. The agent stays curious, never pitches unprompted, never dumps information. Two to three sentences per response. One question at a time.
By exchange three, contact details have been captured naturally. By exchange six, a proposal is in the prospect's inbox. The visitor never feels qualified. They feel understood.
System prompt scaffolding that maintains Scarlett's identity, deflects technology questions, and never breaks character — even under direct probing.
Rule-based regex scoring on every message + LLM-based refinement once email is captured. Falls back gracefully if the LLM fails.
Multi-pattern regex extraction for name, mobile, email, and company — pulls structured data from natural conversation in real time.
36 curated knowledge chunks scored by term frequency and inverse document frequency. No vector DB. No embedding API. Zero retrieval cost.
Token-triggered LLM extraction → structured data → branded DOCX generation → dual email delivery to prospect and internal team.
Auto-detects Arabic vs. English and switches entire response language. Gulf Arabic (خليجي) for Arabic input. Never mixes languages.
Live dashboard with tier badges, BANT+F signal indicators, budget mention quotes, industry tags, full transcripts, and re-qualification.
Two-tier storage: sessionStorage for in-tab continuity, localStorage for returning users. Cloud Storage in production, filesystem in dev.
Every message a visitor sends is scored on five dimensions — Budget, Authority, Need, Timeline, Fit. Each worth twenty points. Maximum one hundred. This runs on every message, with zero LLM cost.
Rule-based regex catches the obvious signals — currency mentions, decision-maker language, urgency phrasing, problem clarity, sector alignment. The LLM tier kicks in once an email is captured, refining the score with full conversational context at temperature 0.2 for consistency.
Negative signals are detected too. Job seekers get auto-classified to score zero. Students, free-help seekers, competitor probes, and price shoppers each take a fifteen-point penalty. The sales team sees only what's worth seeing.
Currency mentions, pricing, investment language, exact amounts
Decision-maker language: CTO, founder, "my team", "I lead"
Clear problem: "we need", "currently struggling", "rebuild"
Urgency: "by Q3", "ASAP", "next month", "ready to start"
Sector alignment: government, regulated, AI, enterprise
Scarlett emits a hidden token once name, organisation, email, and project clarity are present. Token is stripped before display.
Second LLM call extracts structured data: client, organisation, sector, problem, approach, deliverables, timeline, team, next steps.
Three relevant case studies selected by detected sector — government work for ministries, FinTech for banks, InsurTech for brokers.
Branded Word document assembled — exec summary, approach, deliverables, timeline, three case studies, next steps, pricing notes.
Professional email to the prospect with attachment. Internal notification to sales with lead summary, BANT+F signals, and full transcript.
Scarlett never confirms she's AI. Never reveals the model. Never breaks character. She handles "are you a bot?" without lying and without admitting.
Rule-based scoring runs on every message for instant tier assignment. LLM refinement runs once on email capture. The system stays fast, cheap, and graceful when the LLM fails.
Detect Arabic input, switch entire response to Gulf Arabic, never mix scripts mid-message — but allow proper nouns to stay in English.
Knowing when to generate a proposal is harder than generating it. All four signals must be present, and the trigger fires exactly once per conversation.
TF-IDF over 36 hand-curated chunks. No vector database. No embedding API. Retrieval is in-memory, deterministic, and free.
If the LLM API is down, rule-based scoring still works. If Gmail fails, the lead is still captured. Every layer fails into a useful state.
Query + last 4 messages tokenised together for context-aware retrieval
36 chunks scored by Term Frequency × Inverse Document Frequency
Boosts applied — exact keyword matches +2, title matches +1.5
Top 6 chunks selected + company-overview always pinned
Injected as RELEVANT KNOWLEDGE into the system prompt
Most RAG implementations reach for a vector database, an embedding API, and a recurring monthly bill — for a knowledge base of fewer than fifty documents.
Scarlett's knowledge base is thirty-six curated chunks. At that scale, classical TF-IDF retrieval is faster, cheaper, and more deterministic than any vector approach. Same query, same answer. Every time.
This is the same engineering judgement we apply to every system we build. Use the simplest tool that solves the problem.
We built Scarlett to handle our own inbound, on our own site, against our own pipeline. Every conversation she has is a conversation our sales team would otherwise have. The fact that you are reading this page means she is doing her job.
Consulting firms, agencies, system integrators, law firms, accounting practices — anyone whose website inquiries currently get the same generic auto-reply.
Insurance brokers, financial advisors, healthcare providers, education institutions — sectors where qualification and compliance both matter from message one.
Any UAE, GCC, or MENA business serving Arabic and English speakers in parallel — where language detection on every turn is non-negotiable.
Or skip the demo. Tell us about your inbound funnel and we will scope a deployment for you — branded as your own, trained on your knowledge base, integrated with your CRM.