Skip to content

Chatbot-as-a-Service

Service ownership

Owner: application-services (apps-pm@clouddigit.ai) — Status: GA — Last audited: 2026-05-11

Multi-channel chatbots — web widget, WhatsApp Business, Facebook Messenger, IVR — backed by Cloud Digit-hosted LLMs.

What it is

A turnkey chatbot platform that pulls together:

  • A flow builder for conversation design
  • LLM integration via LLM-as-a-Service (sovereign-resident inference)
  • A knowledge-base ingestor (PDF, docx, web)
  • A vector store (via Vector Database)
  • Channel adapters (web, WhatsApp, Messenger, Telegram, voice)
  • Human-handoff to your existing CRM / helpdesk
  • Analytics dashboard

Why this exists separately from the inference layer

Building a production chatbot from raw inference is real work — RAG pipeline, intent classifier, fallback routing, escalation gating, audit trail, channel adapters, NLP for Bengali and Banglish, abuse filters. Chatbot-as-a-Service bundles all of it.

Use cases

  • Banking customer support (balance enquiry, branch locator, FAQ)
  • Government citizen services (forms, statuses, eligibility checks)
  • E-commerce (order status, returns, recommendations)
  • Healthcare (appointment booking, FAQ, triage front-line)

Languages

  • Bengali — first-class (intent recognition, response generation)
  • English — first-class
  • Banglish (Bengali in Latin script) — handled
  • Other languages on request

Compliance

  • All conversations stay on Cloud Digit infrastructure
  • Per-conversation retention configurable; default 90 days
  • Optional zero-retention mode (no message ever stored beyond the session)

Pricing

Per-conversation-month + per-channel-month + the underlying LLMaaS token usage. See Pricing.

Operate this service

Hosted conversational AI — LLM-backed, with retrieval, tools, and BD-localized integrations.

Use cases

  • Customer support (banking, telco, e-commerce)
  • Internal knowledge bot (HR, IT support)
  • Sales assistant (lead qualification)
  • Bangla-language native chatbots

IAM

Role Can do
chatbot.viewer View bots, conversation logs
chatbot.editor Edit bot instructions, knowledge base
chatbot.deployer Deploy bots to production channels
chatbot.admin Manage bots, integrations, model selection

Architecture

User → Channel adapter → Chatbot engine → LLM + Retrieval + Tools ↓ [Vector DB / KB] [External APIs]

Channels supported

  • WhatsApp Business API
  • Facebook Messenger
  • Web widget
  • SMS (via local operators)
  • bKash chat
  • Custom (REST API)

Knowledge base

Document ingestion: - PDF, DOCX, HTML, Markdown - Auto-chunking and embedding - Stored in Vector DB - Re-index nightly

Compliance

For regulated industries (banking, healthcare): - All conversations logged - PII detection + redaction - Audit-trail for AI decisions - Human escalation path

Metrics

Metric Healthy Alert
chatbot.conversations_per_hour varies
chatbot.first_response_time_ms p95 < 2000 > 5000
chatbot.completion_rate > 80% < 60% (users abandoning)
chatbot.handoff_rate < 20% > 40% (bot weak)
chatbot.satisfaction > ⅘ < 3.5/5
chatbot.errors_per_hour low spikes

Tuning the bot

Weekly review: - Top 10 conversation flows (where do users go?) - Top 10 handoff reasons (where does bot fail?) - Top 10 dissatisfaction signals

Refine: - Improve knowledge base where retrieval misses - Add explicit tool calls for actions - Update system prompt for tone / boundaries

A/B testing

Multiple bot versions live; route by user cohort:

bash cd chatbot deploy --bot acme-support \ --traffic 'v1.4=80,v1.5=20'

Metrics split by version; promote winner.

Tool calls

Chatbot can invoke tools: - Look up customer order status - Check account balance - Schedule callback - Create support ticket

Each tool is a function definition + endpoint; chatbot LLM decides when to call.

Multi-language

Bangla + English on the same bot: - Auto-detect user language - Respond in same language - KB in both languages (or one with translation layer)

Conversation logging

Per channel + privacy policy: - Logged: all turns, metadata (channel, timestamp, etc.) - Redacted: PII (auto-detected; can configure aggressiveness) - Retention: 90 days default; longer for compliance

Bot hallucinating

Bot invents facts not in knowledge base: - Strengthen system prompt: "answer only from provided context, otherwise escalate" - Add explicit grounding via retrieval - Lower temperature - Improve KB coverage

No bot is hallucination-free; mitigate.

Bot doesn't understand Bangla

Possible causes: - Wrong model selected (use bangla-llm-7b or a multilingual one) - KB only in English; user query in Bangla finds nothing - Mixed script (Bangla in Latin chars) confuses retrieval

Handoff doesn't reach human

User asks for human; transfer fails: - Human team unavailable (off-hours) - Channel doesn't support handoff (WhatsApp policy) - Bug in escalation workflow

For 24/7 needs: hire shifts or accept after-hours queue.

Tool call failed

Bot tried to invoke a tool; error: - Backend API down - Authentication issue - Schema mismatch (bot sent wrong format)

Bot should gracefully degrade — say "I can't do that right now, let me get a human." Don't expose backend errors.

Conversation history confused

Bot loses context mid-conversation: - Token limit reached for the model - Conversation reset by channel timeout - Bug in context management

Most LLMs handle 4k-128k tokens; long conversations need summarization.

Privacy / PII leakage

Bot replied with PII it shouldn't have: - KB ingestion didn't redact PII (re-ingest with stricter redaction) - Bot recovered PII from history of another user (cross-user leakage; bug) - User intentionally probed; bot disclosed

Audit; investigate; tighten.

Bot deploy broke production

A new bot version causes regressions: - Roll back: cd chatbot rollback --bot acme-support - Investigate in sandbox - Re-deploy with fix + A/B test before full

Cost spike

LLM token costs ramping: - Long context windows (more history per turn) - Bot generating excessively long responses - Many low-value conversations (broaden funneling earlier)

Cap with hard quotas; tune for efficiency.