Sonika Vankadari
Automation Engineer | n8n, Apollo.io, AI Lead Enrichment
Ready for work
Sonika is ready for their next project!
Built a retrieval-augmented generation chatbot for a blockchain/digital ecosystem client whose product documentation was scattered across files, leaving users and internal teams with no fast, reliable way to get answers. The bot pulls strictly from the client's own docs — a Google Drive folder acts as the single source of truth, where any file created or updated is automatically downloaded, chunked, embedded with Cohere, and upserted into a Supabase vector store, so the knowledge base stays current without manual re-indexing.
The chat agent, running on a Groq-hosted LLM for fast responses, is instructed to always query the vector store first, optimizing each user question into a targeted search before answering — and it's explicitly constrained to respond only from retrieved data, admitting when nothing relevant is found rather than guessing.
Postgres-backed chat memory keeps context across a session, so it handles natural follow-ups instead of treating every message as a fresh conversation. The result: a self-updating support assistant that answers accurately and never fabricates product details.
0
22
HubSpot → Clay → Airtable Enrichment & Interest Tracking Pipeline
Built an automated pipeline that keeps CRM data enriched and interest signals tracked without manual work. New or updated HubSpot contacts are automatically pushed to Clay for enrichment (company size, industry, LinkedIn, job title), then synced into Airtable as a clean, always-current record. A second flow captures Airtable form submissions — when someone expresses interest in a product/service — matches them against the enriched contact, and logs it directly to their record. Unmatched submissions get flagged to the team instantly instead of getting lost.
Fixes: manual re-entry between CRM and enrichment tools, stale contact data, and untracked interest signals from prospects.
0
33
Autonomous Crypto Newsroom: Built a 24/7 automation for a UAE-based crypto newsletter client that monitors 15+ RSS feeds (CoinDesk, Coin-telegraph, The Block, Decrypt, and others), identifies the most relevant breaking stories, generates full SEO-optimized articles with an AI agent, creates a custom photorealistic image per story using a Hugging Face diffusion model, and simultaneously publishes to WordPress, Twitter, and Telegram running unattended every few hours.
0
50
Apollo Lead Enrichment Pipeline: Built a 13-node automation that pulls company and contact data from Apollo, enriches it with website scraping, scores leads using AI (Llama 3.3), and generates personalized outreach - all written back to Google Sheets automatically. Cuts hours of manual prospect research down to minutes.
1
106