Activity
Mon
Wed
Fri
Sun
Dec
Jan
Feb
Mar
Apr
May
Jun
Jul
Aug
Sep
Oct
Nov
What is this?
Less
More
11 contributions to AI Accelerator
Application support - need help
Hi All Am seeking for some ideas in application support domain to automate. As a support associate I am aiming to automate the real world problems. Do drop in your suggestions Regards
0 likes • 4d
Start with ticket triage: auto-tag and route incoming tickets by issue type, so the urgent ones reach the right person first. Next, a small bot that drafts replies from your past solved tickets — you review before sending.
Is Codex worth learning to reach $10k/mo with an AI agency?
Hey everyone! 👋 I’m planning to start an AI agency with a goal of hitting $10k/month. I’m considering learning OpenAI Codex as my primary skill to build solutions for clients, but I want to make sure it's the right choice. For those running an agency or offering AI services: Is learning Codex worth the investment to reach this revenue goal, or should I prioritize other skills first? Any advice would be greatly appreciated!
0 likes • 4d
Codex is fine, but it won't be what gets you to $10k — clients and outreach will. If you pick one tool to go deep on, Claude Code has the bigger ecosystem for agency work right now.
Hermes Desktop and Ollama
Has anyone connected an Ollama LLM with hermes desktop? Could you explain how?
1 like • 4d
Yeah, it works — run Ollama locally first, then in Hermes add it as a local/custom model provider pointing at localhost:11434 and pick one of your pulled models. Just make sure the model is actually pulled in Ollama before you connect, or Hermes won't show anything to select.
Website Delivery
Hi, a few days ago I got my first client. They only wanted me to create a website for their business. After a couple of calls, we agreed on the price and everything, but now I’m not really sure how I’m supposed to deliver the website to them. The website is on my GitHub, the backend is on Supabase, and it’s deployed on Vercel. I want to transfer everything to the client, but I also want to keep access so I can fix any problems or make changes, since they’re also going to pay me for maintenance. What different ways are there to do this? I’m honestly pretty lost. Thanks!
1 like • 5d
Easiest clean way: transfer the GitHub repo, the Vercel project and the Supabase project to the client's accounts. Keep yourself added as a collaborator/admin on all three, so you can still fix things without owning them.
How do you stop untrusted data from influencing an n8n workflow?
One security concern I've been thinking about in n8n is how much trust we give to incoming data. Imagine a workflow receives a webhook from an external source, passes the payload to an AI agent, and allows that agent to use tools connected to the workflow. The problem is that the incoming payload isn't necessarily trustworthy. It could contain unexpected fields, malicious instructions, or values designed to trigger actions the workflow wasn't supposed to perform. Prompt instructions alone don't seem like a reliable security boundary. I'm curious how experienced n8n builders approach this: Do you isolate untrusted input before it reaches the agent, validate every tool parameter against a strict schema, or enforce permissions at the individual node level? I'd particularly like to understand how you prevent untrusted input from influencing actions outside the intended scope of a workflow.
1 like • 10d
Don't let raw webhook data reach the agent. Validate it first — whitelist only the fields you expect, drop everything else, and pass just the cleaned values in. Then keep the agent's tools narrow, so it can only do the one job with fixed parameters. That way a weird payload can't trigger anything outside the scope.
1-10 of 11
Elhabib Elhab
2
11 points to level up
@elhabib-elhab-3687
I help businesses automate work & get more bookings 🤖AI Agents • n8n • Automation👉 elhabib.dev

Active 2h ago
Joined Jun 11, 2025
Marrakech, Morocco
Powered by