The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Back to feedPost
Built an AI-powered employee onboarding workflow that automatically processes user submissions, verifies employee data, integrates with Microsoft Entra ID and Jira Software, and manages Slack workspace access. The automation uses an AI Agent with memory capabilities to streamline onboarding decisions, assign permissions, update employee profiles, and invite users to relevant Slack channels based on role conditions such as manager status. Designed to reduce manual HR operations, improve onboarding speed, and create a scalable internal automation system.
The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Related posts
Remote onboarding was being treated like a checklist problem. The real problem was that new hires had no sense of arrival — no moment where the company said: you're here, and here's what that means. Onbrd needed to be the brand that changed that.
Nice! I love the energy the logo has
Telegram AI Agent with Memory, Tools, and Android Self-Hosting
Bzhela started as an experimental Telegram AI agent but evolved into a full research project focused on long-term memory, controlled context, and autonomous infrastructure. The goal was to build a context-aware assistant that tracks conversation flow and interacts with real-world tools without losing coherence in an active group chat.
The core of the system was a custom memory architecture. To prevent context collapse, I built a rolling strategy where older messages were compressed into a summary while fresh messages remained raw. I used Redis for short-term history and Pinecone for long-term fact retrieval. The agent actively extracted and managed facts, applying time-to-live limits to temporary memories so the database stayed clean.
This setup allowed the agent to be proactive rather than purely reactive. It operated with practical integrations tied to daily life. The agent checked local power outage schedules, managed Google Calendar events, and interacted bidirectionally with an iPhone via Shortcuts. It could trigger phone-side scenarios, like setting alarms or sending warnings based on battery levels.
The infrastructure was deliberately unconventional. Instead of a standard cloud server, the agent ran on a self-hosted Android phone without root. I set up a runtime using Termux, proot Ubuntu, and Node.js, managed by PM2. Cloudflare Tunnel ensured secure remote access. This gave the agent physical survivability via a power bank and access to real-world network signals.
Over several months, the system maintained a stable context, managing around 150 compressed facts and proactively messaging based on real-world triggers. It proved that an AI agent can act as a reliable, system-level tool rather than just a simple chatbot wrapper.
Key technical aspects:
- Custom memory stack using Pinecone and Redis
- Rolling context and automated chat summarization
- Event-driven proactive messaging
- Integrations with Google Calendar, webhooks, and iOS Shortcuts
- Self-hosted Android runtime with Termux and Cloudflare Tunnel
Building rolling memory with Redis + Pinecone on a self-hosted Android stack is serious agent engineering → this goes far beyond a typical “Telegram chatbot.”
Agentic AI Workflow for Real Estate Lead Enrichment (USA)
I built a production-grade, engineering-first workflow that turns minimal “clues” (company name, property address, or Tax ID) into a structured owner/contact dossier.
Stack: self-hosted n8n, OpenAI (GPT-5), Airtable (UI + database), Google Search, RealTrack (closed system)
Input → Output: 1–3 clues in → a complete enriched profile in ~60–120 seconds (with citations/links to sources) ready for sales outreach and due diligence.
The Problem (How the team worked before)
The client’s manual process looked like “crossfire research”:
- Find a company name + street / Tax ID
- Open multiple platforms/tabs
- Cross-check signals, collect evidence
- Compile a dossier in spreadsheets/CRM
This was slow (20–45 minutes per request), error-prone, and hard to scale.
I delivered an end-to-end agentic workflow that automates the same multi-platform research the team did manually — but faster and with consistent formatting.
1. ~90% reduction in pre-call research time per lead
2. ~60–120 seconds per lookup vs 20–45 minutes manually
3. ~$0.02 per enrichment request (token cost; excluding optional external services)
4. Self-hosted n8n: dramatically lower operational costs vs cloud pricing at scale
Amazing job Oleh!
Trending
Claude
Claude has entered the design space. How are you using Claude Design?
Contra University
Learn from expert creatives how to earn more using next-gen AI tools.
creativeaiflow
Creative AI workflows are evolving. What tools do you use, and what are their strengths and weaknesses?
portfolioreview
The best portfolios tell a story, not just show a grid. Share yours for feedback.
freelancerlife
Freelancer life is wins, pivots, and everything in between. What’s yours right now?