AI Ops at F5 Hiring Solutions (remote) | AI Automation Product Developer | Built Anti-Gravity AI - 14 sales / 7 countries / tinyurl.com/mrx38kre

Joined April 2025
2,542 Photos and videos
Pinned Tweet
New journey :)
1
2
84
Aakash retweeted
New journey :)
1
2
84
Aakash retweeted
After months of late nights and hundreds of cups of coffee - Anti-Gravity is finally LIVE on the Google Play Store I built this because: I wanted a PDF tool that didn't spy on my documents. 100% Private (No Cloud) Elite AI Chat & OCR Lifetime Access (No annoying subscriptions!)
My First Android App is on Playstore (In close testing) I built the PDF toolkit I always wanted. - No subscriptions. - No cloud uploads. - No privacy compromises. - NO watermarks. Just local AI-powered analysis, OCR, and pro tools on your Android. I built Anti-Gravity with more than 15 professional tools and the Gemini AI Neural Engine to be the only PDF suite you’ll ever need. Anti-Gravity Private AI PDF is officially in closed testing. NOTE: The App will be now in a close testing period for 14 days with 12 testers. If you wanna try this and help me with making it better with your valuable feedback you are most welcome. Benefits - You will get a lifetime subscription DMs are open :)
18
5
50
4,774
This is extraordinary.
never touch me again
26
Aakash retweeted
Built a RAG Pipeline & Chatbot with n8n, Google Gemini, Pinecone, and Google Drive. The workflow takes a PDF from Google Drive, extracts and chunks the content, creates embeddings with Gemini, stores them in Pinecone, and lets a chatbot answer questions using only the document context. This was a solid practical project to learn about n8n because I had to debug real issues around PDF parsing, embedding dimensions, and retriever/tool-calling behavior inside the AI agent. Potential use cases: - Customer support from help docs - Internal knowledge bots - Sales/product documentation assistants - Company policy Q&A I also added a sanitized workflow, architecture notes, and setup docs to the GitHub repo so it is safe to share publicly.
2
1
6
135
Aakash retweeted
Few days ago I built a LinkedIn outreach automation in n8n using Unipile and Google Sheets for database I also used codex and claude code to plan and design the architecture. The flow creates campaign rows, sends connection requests, checks if people accepted, sends message 1 and follow-ups after 48 hours if there is no reply, stops when a reply comes, and tracks everything in the sheet. I split it into six workflows so each part is easier to debug and maintain: campaign setup, connection sending, acceptance polling, message sending, reply webhook, and daily counter reset. - First it creates campaign rows from prospects. - Then it sends connection requests. - Another workflow checks if those requests are accepted. - Once accepted, the message sender sends message 1 and follow-ups after 48 hours if there is no reply. - A webhook listens for replies and updates the sheet. - A reset workflow clears daily counters. I used Google Sheets as the operating database but for production scale, I would move state, counters, and logs to Postgres or Supabase because Sheets is not atomic.
1
1
4
126
Aakash retweeted
Got 14th sale today and this one is from Pakistan Found out the user paid but did not get the lifetime access because of the backend issues, fixed it with new build and also granted her manual access via supabase.
Got 13th sale today and this one is from Malaysia :) got my first Malaysian user for PDF Editor & AI: Anti-Gravity
2
1
8
165
Aakash retweeted
Two times these humanoid robots made an eye contact and nod before starting a task together? even though they communicate instantly over WiFi, engineers program these human like gestures for a reason. tried to find out what it is - it is called as an expressing intent - a visual handshake that makes their sudden, autonomous movements predictable and safe for the humans working around them. this does looks cool and amazing at the same time.
We taught two F.03 robots to clean a room and make a bed in under 2 minutes - fully autonomous.
1
3
78
Built a RAG Pipeline & Chatbot with n8n, Google Gemini, Pinecone, and Google Drive. The workflow takes a PDF from Google Drive, extracts and chunks the content, creates embeddings with Gemini, stores them in Pinecone, and lets a chatbot answer questions using only the document context. This was a solid practical project to learn about n8n because I had to debug real issues around PDF parsing, embedding dimensions, and retriever/tool-calling behavior inside the AI agent. Potential use cases: - Customer support from help docs - Internal knowledge bots - Sales/product documentation assistants - Company policy Q&A I also added a sanitized workflow, architecture notes, and setup docs to the GitHub repo so it is safe to share publicly.
2
1
6
135
Few days ago I built a LinkedIn outreach automation in n8n using Unipile and Google Sheets for database I also used codex and claude code to plan and design the architecture. The flow creates campaign rows, sends connection requests, checks if people accepted, sends message 1 and follow-ups after 48 hours if there is no reply, stops when a reply comes, and tracks everything in the sheet. I split it into six workflows so each part is easier to debug and maintain: campaign setup, connection sending, acceptance polling, message sending, reply webhook, and daily counter reset. - First it creates campaign rows from prospects. - Then it sends connection requests. - Another workflow checks if those requests are accepted. - Once accepted, the message sender sends message 1 and follow-ups after 48 hours if there is no reply. - A webhook listens for replies and updates the sheet. - A reset workflow clears daily counters. I used Google Sheets as the operating database but for production scale, I would move state, counters, and logs to Postgres or Supabase because Sheets is not atomic.
1
1
4
126
Aakash retweeted
Claude Code limits have doubled: If you're on a Pro, Max, or Team plan, your 5-hour rate limits just got a 2x boost. They’ve scrapped the limit reductions during busy hours for Pro and Max users. There’s a substantial raise in rate limits for Opus models, making it much easier to scale projects without hitting a wall. It’s pretty clear they’re feeling the heat from the competition and are finally opening the taps on compute.
We’ve agreed to a partnership with @SpaceX that will substantially increase our compute capacity. This, along with our other recent compute deals, means that we’ve been able to increase our usage limits for Claude Code and the Claude API.
1
2
99
Aakash retweeted
GPT 5.5 is faster and better than Claude Code's any model right now.
1
4
50
Aakash retweeted
Got 13th sale today and this one is from Malaysia :) got my first Malaysian user for PDF Editor & AI: Anti-Gravity
Update on - PDF Editor & AI: Anti-Gravity Got my 12th sale today from USA and crossed 1000 installs on play store.
2
1
4
299