“Every morning I was burning hours browsing freelance platforms and writing tailored applications before I could touch billable work. Cortension set up an agent that knows my portfolio, filters for real fit, and drafts proposals the client wants to read. I got my mornings back and my win rate went up.”
What our clients say
“Cortension helped us run AI entirely on our own infrastructure. Local models, fine tuned for our use case, no data leaving the building. Full control, full compliance.”
“Cortension set me up with Hermes Agent and it completely changed how I work. It remembers my projects across sessions, auto generates skills the more I use it, and I can reach it from Telegram, Slack, wherever I am. One coaching session and the thing just runs.”
“With Claude Code and one cloud provider, Cortension helped us replace everything. Calendly, Shopify, analytics, email automation. All of it, built and owned by us. No more monthly fees stacking up, no more depending on tools that can change their pricing overnight.”
“Cortension showed me how to use Claude Code to build my own website, set up fully automated cold email outreach, and get everything running. I went from paying for a dozen SaaS tools every month to handling it all myself. No Calendly, no Mailchimp, no Webflow. Just Claude Code and one cloud account.”
Meet the Founder
Benito Exner
Founder & CEO
Cloud DevOps Engineer turned Agentic AI specialist. I built Cortension because I saw teams struggling with tools that should be making them faster.
Sound Familiar?
OpenAI Is Strong. The Right Implementation Is Not Obvious.
A ticket, a repository, a handover, a website, a content workflow, or an internal process do not all need the same OpenAI setup. The real decision is what belongs in ChatGPT, Codex, project instructions, a script, a tool connection, memory, browser use, or a simpler workflow.
The OpenAI Ecosystem Has Too Many Choices
ChatGPT, Codex, GPT models, Projects, memory, browser use, files, API keys, scripts, and automations all sound useful. The hard part is knowing what your work actually needs and what you can ignore.
Useful AI Needs a Clear Review Step
AI becomes valuable when it prepares real work, shows what changed, and gives you a clean way to check the result. Without that flow, people either trust it too much or keep redoing the work by hand.
What We Actually Do in a Session
Whether you are just starting, already have a concrete task, or want to improve your existing setup: we meet you where you are. We help you set the tool up sensibly, understand current best practices, and avoid unnecessary detours.
We Find Your Best Starting Point
You do not need to bring a perfect task. If you have one, we use it. If not, we look at your work, your tooling, and your goals, then choose the first useful use case.
We Do Not Just Set It Up. We Explain Why.
Installation alone is not the value. We show you which decisions matter: model, Skills, scripts, tool access, project rules, memory, review steps, and what you can leave out at the beginning.
We Bring Current Expert Knowledge
We know the new patterns, plugins, Skills, MCP servers, memory approaches, provider options, and common mistakes. You do not have to test everything yourself to get a good start.
We Build or Improve Your Real Setup
Fresh installation, existing setup, concrete task, or review of your workflow. We work directly on your case, not on a generic tutorial.
After One Session, You Know What Makes Sense and What You Can Skip
We set up, check, explain, and test as much as is realistically useful in 60 minutes. Afterwards, you know better which parts of your AI setup really matter and which ones you can ignore for now.
One Session. Real Progress.
Flat rate, no surprises.
ChatGPT and Codex Setup Session
1 hour · Remote · 1 on 1
€149 per session
- Questionnaire before the session and a plan built around your work
- Live hands on setup for 60 minutes
- One real task or repeated workflow as the base
- ChatGPT, Codex, instructions, Skills, scripts, tool access, browser use, memory, or review flow where useful
- Custom setup notes, commands, prompts, and instructions for your work
- Session recording and written action plan
- 30 day follow up by email
- Discount for 3 or more sessions
Frequently Asked Questions
What people ask before booking their first ChatGPT and Codex session.
Do you help with ChatGPT, Codex, or both?
Both. We treat it as one OpenAI setup around your work. ChatGPT is often right for thinking, writing, research, and planning. Codex is useful when the work touches files, code, commands, project structure, or repeatable technical steps. We help you understand what belongs in chat, what belongs in Codex, what needs a Skill, script, tool connection, memory, or review step.
Are you just teaching prompt tips?
No. Prompting is only a small part. The real value is the setup around ChatGPT and Codex: project instructions, reusable tasks, scripts, tool access, memory, permissions, and review steps. We show you what makes sense, set it up with you, and explain how to keep using it.
What should I bring to the session?
Bring one real thing you want AI to help with: repeated work, a ticket flow, writing, research, code, documents, handovers, a tool setup, scripts, customer replies, or an internal process. We use that as the base instead of showing random features.
What do you actually set up?
The useful parts only. That can mean ChatGPT Projects, Codex, project instructions, reusable prompts, scripts, file context, browser use, tool access, memory, permissions, review steps, or a simpler workflow. Not everything needs automation. Not everything needs Codex. We show you the right path.
Can this replace tools I currently pay for?
Sometimes. Some subscriptions can be replaced with self-built, open source, or cloud based solutions that you control. We first look at what the tool actually does for you, then decide what should stay, what can be replaced, and where replacing it would add more complexity than value.
Do I need to be technical?
Only as technical as your goal requires. If you bring a business workflow, we stay close to that workflow. If you bring a codebase, we can go deeper into files, commands, instructions, checks, and review.
How does this compare to Claude?
Claude, ChatGPT, and Codex all have places where they are strong. We do not force everything into the OpenAI stack. We help you decide where ChatGPT is enough, where Codex makes sense, where Claude is better, and where a simple script or automation is the cleaner answer.
What do I leave with?
A working OpenAI setup around your real work, written notes, a recording, and clear next steps. You leave knowing when to use ChatGPT, when to use Codex, when to create a Skill or script, and where a human review step should stay.
How long is the session?
The setup session is 60 minutes via video call with screen sharing. It is hands on, not a lecture. You get a recording, written notes, and a follow up action plan after the session.
Make ChatGPT and Codex Useful for Your Real Work.
Bring one task you want AI to help with. We show you the right path, set it up with you, and explain how to keep using it.
Keep Up. Without the Noise.
New tools, skills, and breaking changes drop faster than anyone can keep up with. We cut through it and send you what actually matters, when it matters. No hype, no fluff. Subscribe now and get our free guide: 16 Best Practices for Agentic AI.
Something went wrong. Please try again.
Almost there. Check your inbox for a confirmation link and your free guide. (Check spam if you don't see it.)
No spam. Unsubscribe anytime.