Zakeen Khan
AI Automation Engineer who save time and money using n8n.
New to Contra
Zakeen is building their profile!
Project title: AI Voice & Text Personal Assistant for Slack
Project description:
Built a conversational AI assistant in n8n that lives inside Slack and handles both voice and text messages, giving users a personal assistant they can talk to naturally, without switching apps or typing long commands.
The problem: The client wanted a way for their team to quickly get answers or delegate tasks through Slack, including by voice, without building a separate app or bot from scratch, and needed the assistant to hold context across a conversation rather than treating every message as a one-off.
What I built:
Message filtering: Every incoming Slack message is automatically checked to filter out bot-generated messages, so the assistant only responds to real human input.
Voice and text handling: The system detects whether the incoming message is a voice note or plain text. Voice messages are automatically downloaded and transcribed into text using an audio transcription model, while text messages pass straight through, so both input types end up in the same format for processing.
Conversational AI agent with memory: The transcribed or typed message is sent to a personal AI agent (built on Groq) that generates a response. The agent uses a memory module to retain context across the conversation, so it can handle follow-up questions naturally rather than starting fresh every time.
Instant reply in Slack: Once the agent generates a response, it's posted straight back into the Slack channel, so the interaction feels like a live conversation.
Outcome: The client's team now has a Slack-native assistant that understands both typed and spoken messages, remembers conversation context, and responds instantly, no separate app, no manual transcription, no lost context between messages.
3
0
32
Project title: AI-Powered Document Classification & Organization System
Project description:
Built an automated document intake and filing system in n8n that watches a Google Drive folder, reads incoming files, uses AI to figure out what each document is, extracts the relevant data, and files it into the correct folder automatically, replacing manual document sorting entirely.
The problem: The client was manually opening every new file dropped into their Drive, figuring out whether it was a contract, invoice, or general document, extracting the key details by hand, and moving it to the right folder, a slow and error-prone process as document volume grew.
What I built:
Automatic file detection and text extraction: Whenever a new document lands in Drive, the system downloads it and detects its file type (PDF, Excel, or image), then extracts the raw content using the appropriate method for that format, including AI-based text extraction for scanned images.
AI-based document classification: Extracted content is passed through a classification step that determines whether the document is a contract, an invoice, or a general document, routing it down a different path depending on its type.
Type-specific data extraction:
Contracts are processed by an AI agent (Google Gemini) that extracts structured contract data against a defined schema, prepares metadata, and moves the file into a dedicated Contracts folder
Invoices are processed by a separate AI agent (Groq) that extracts invoice-specific data, prepares metadata, and moves the file into an Invoices folder
General documents are summarized by an AI agent (OpenAI), have metadata prepared, and are archived into a general Archive folder
Centralized record keeping: Regardless of document type, every processed file's metadata is logged into a central document metadata store, giving the client a searchable record of everything that's been filed.
Outcome: The client's document intake is now fully automated end to end, new files are read, classified, and filed into the correct folder with extracted metadata, without anyone manually opening or sorting a single document.
0
17
End-to-End E-Commerce Operations Automation (Orders, Shipping, Support, Refunds)
0
13
Graphic Designer Agency is an n8n workflow that turns Telegram into a full creative-production desk for MIUC (Millennium Institute University College). A marketing-team member messages a Telegram bot with a campaign idea; an LLM agent acting as a Creative Director proposes a concept, formats and headline in one turn, waits for a tap on “Approve,” then automatically writes generation prompts, calls free-tier image and video generation APIs, delivers the finished asset back to Telegram, and can publish the approved image straight to the company LinkedIn page all without the user leaving the chat.
0
19