Conversational AI Services
Build conversational AI systems with chatbots, voice AI, RAG-grounded answers, and lead qualification across WhatsApp, web, and internal workflows.
Explore Conversational AIConversational Sales Automation
A Conversational Sales Assistant That Drives Revenue
A real estate team needed every inbound lead answered, qualified, and followed up on without manual work. We built a conversational system that handles qualification, bookings, call transcription, and document dispatch in one flow. Zero manual follow-ups, stronger conversion, and a measurable revenue lift.
Business Impact
30%more revenue
Faster engagement and automated follow-ups close deals that used to slip away
Business Impact
Executive Outcomes
0manual follow-ups
Qualification and reminders run without someone chasing every lead
3xfaster conversion
Speed-to-lead drives significantly higher booking rates
100%automated
Qualification, reminders, and bookings run without manual work
30%more revenue
Faster engagement and automated follow-ups close deals that used to slip away
The Challenge
“The agent was losing momentum between inbound conversations, CRM updates, booking coordination, document sharing, and manual follow-ups. The initial setup relied on n8n flows and spreadsheet-based lead management, creating scaling and consistency limitations.”
Leads sat unanswered for hours while the agent juggled chat, CRM, and spreadsheets manually
Follow-ups depended on memory. No system tracked who needed a callback or a document
Call recordings piled up in Google Drive with no transcription, no summaries, no CRM sync
Booking updates from Cal.com required manual copy-paste into Close.com notes
Voice outreach campaigns were impossible without a dedicated team or call center
The Transformation
What changed after we built the system
Before
Leads sat unanswered for hours while the agent juggled chat, CRM, and spreadsheets manually
After
AI responds to inbound conversations within the batching window, qualifying leads automatically
Before
Follow-ups depended on memory. No system tracked who needed a callback or a document
After
48-hour follow-up reminders fire on schedule with zero manual tracking
Before
Call recordings piled up in Google Drive with no transcription, no summaries, no CRM sync
After
Call recordings are ingested from Drive, transcribed with Whisper, summarized, and logged to CRM
Before
Booking updates from Cal.com required manual copy-paste into Close.com notes
After
Booking lifecycle events sync directly into Close.com leads with structured notes
Before
Voice outreach campaigns were impossible without a dedicated team or call center
After
Voice campaigns generate personalized audio with ElevenLabs and dispatch through the messaging layer at scale
The batching window changed everything
Real estate leads type fast. They send three messages in 30 seconds: a greeting, a question about price, and a photo of a listing they saw online.
Without batching, the AI would reply to each message individually, creating a disjointed conversation that felt robotic. The 2-minute batching window consolidates all rapid messages into a single context, producing one coherent response.
The 5-minute ceiling prevents messages from waiting too long. If no new message arrives within 2 minutes, the batch closes and the AI responds. This creates a natural rhythm that mirrors how a human agent would actually read and reply.
How We Built It
Technical architecture for the curious
Entry
Inbound conversations hit the webhook, get validated, and route to admin or lead processing paths.
Twilio Messaging Webhookn8n Middleware (prod)Hono Server (dev)
Orchestration
Background tasks handle batching, qualification, follow-ups, call ingestion, and campaign execution.
Trigger.dev TasksMessage Batch SessionsScheduled Jobs
Data
Supabase stores lead state and conversation history. Sheets handle inventory lookups and campaign queues.
Supabase (leads, chat, media)Google Sheets (inventory, campaigns)Close.com CRM
AI
AI responses use structured output for qualification scoring. Langfuse traces every model call for debugging.
OpenRouter (GPT/Claude)Langfuse ObservabilityStructured Output Schemas
Media
Voice notes transcribed on ingest. Campaign audio generated with ElevenLabs and served from Supabase Storage URLs.
Whisper TranscriptionElevenLabs TTSSupabase Storage
Trigger.dev
Twilio
Supabase
Close.com
Cal.com
Google Drive
OpenRouter
ElevenLabs
Langfuse
TypeScript
Engineering Decisions
Tradeoffs we made and why
89commits
1engineer
6weeks
38test files
2-minute batching with 5-minute ceiling
Benefit
Coherent, human-like AI responses instead of fragmented replies to each message
Cost
Delayed first response in fast back-and-forth conversations
Fire-and-forget for non-critical paths
Benefit
Faster user-facing response times for the primary chat flow
Cost
Eventual consistency for side effects like CRM notes and welcome media
Acknowledge images without vision inference
Benefit
Significant cost savings and pipeline stability
Cost
No semantic understanding of shared images or screenshots
Supabase migration from Google Sheets for lead state
Benefit
Transactional safety, RLS policies, and proper relational queries
Cost
Higher initial engineering effort and migration complexity
Zod validation at every integration boundary
Benefit
Runtime type safety across 10+ external APIs
Cost
More upfront schema work and maintenance overhead per integration
Certain client names, proprietary workflows, screenshots, and internal assets referenced in this case study are protected under a non-disclosure agreement and have been anonymized or omitted to comply with our confidentiality obligations.
Want a system like this for your team?
Book a free 30-minute call. We will walk through your current workflow, find the biggest time sinks, and tell you exactly what we would automate.
30 minutes with Apurva. Not a sales call.
Book Your Free Audit
Proof of Work
More Case Studies
AI Search Product
Business Impact
10+ hrs saved/week
Per team on information lookup Hybrid RAG Workflow Assistant
Gave teams trustworthy workflow answers in one chat interface instead of manual lookup across tools. Hybrid retrieval routes each query type to the right system for speed and accuracy.
Next.js Qdrant RAG AI SDK
Technical Proof
Before: Hours searching across tools
Now: Instant answers, one chat
Social Lead Automation
Business Impact
3K+ leads/day
Qualified leads captured from Instagram daily Instagram DM Lead Pipeline
Turned high-volume Instagram inbox traffic into a consistent qualified lead pipeline. Typed automation handles ingestion, deduplication, enrichment, and CRM routing without daily breakdowns.
Trigger.dev BigQuery AI Qualification
Technical Proof
Before: Manual DM triage
Now: 3K+ leads qualified daily
Financial Services Automation
Business Impact
3x faster onboarding
Clients go live in days instead of weeks Funding Onboarding Orchestrator
Removed cross-client data risk from a mission-critical onboarding workflow. Atomic isolation, dynamic field mapping, and secure PDF generation replaced brittle Zapier operations.
Trigger.dev GoHighLevel Google APIs
Technical Proof
Before: Zapier + data leaks
Now: Zero contamination