Lately, I’ve been spending more time just building.
Right now I’m focused on:
→ AI automations that replace repetitive business tasks
→ Custom web apps (not templates) that actually solve workflows
→ Simple internal tools that save hours every week
I’m trying to move beyond just “making websites”
and more towards building things that actually solve problems.
Even in small ways — like saving time on repetitive tasks
or making everyday workflows a bit smoother.
Still experimenting, still learning —
but really enjoying this shift and where it’s heading.
If you're exploring something similar, would love to connect.
Clients often start with the same request: "Let's build an AI agent."
My counter-question is always: which manual process actually costs you time, errors, or money right now?
My selection rule: remove it first. If it can't be removed, simplify it. If it's still needed, automate it with a plain script. Only then add an integration or an agent. Often the best result is the process that no longer exists.
Safe automation means real scenarios, error handling, and alerts. Without alerts, a workflow can silently lose data for weeks. I always define what stays with a human and what goes to the system.
Question for you: which process would you automate first, and why is it still manual?
Service for audit and implementation: https://contra.com/s/BmWLbgFU-ai-automation-from-your-dream-to-working-implementation?r=auto_booster
Alerts are the part I'd underline. In my Linux deploy demo I killed the service on purpose and systemd restarted it, but without an alert nobody would know it happened. For small workflows, where do you send alerts: email, Slack, or something else?
The 30–60 minute delay then 24-hour follow-up is a sensible cadence. The part I would harden next is the stop conditions: once the cart converts or the customer replies, every channel should cancel, and WhatsApp especially needs a clear opt-in trail before the first send....