Apify's community of creators earns about $2m a month by building tools for AI agents. Here is what the CEO says it takes to make tools agents will actually use.
Our senior support engineers take years to learn which of thousands of records actually matter when a client call drops. We tried to shortcut that with an AI agent, and the key was how we built its memory.
We make many mistakes with MCPs, but one of the biggest is treating them like a 1:1 REST API mapping - when in reality, an MCP tool should be a capability, not just another endpoint.
Anyone who’s clicked "always allow" on an agent knows the outcome: broad permissions, minimal oversight, and results that are correct on paper but strange in practice.
This team was shipping production code at the same time as the MCP specification was taking shape. That is the reality of working with a technology that was evolving in real time.
A CTO with 20 years of experience through multiple tech shifts sees layoffs not as an AI effect, but as a correction after an unsustainable hiring boom. He sees AI as a reset: an opportunity for strong junior engineers, and a wake-up call for senior developers facing an existential shift in how they stay relevant.
Production incidents are a context problem. By the time an engineers understand what's happening, they've already bounced across several different tools - and the incident is still ongoing. PagerDuty thinks MCP is the fix.
I spoke with developers from a golden member company who explained why AAIF membership is crucial for navigating the shift toward agentic AI.
> subscribe shift-mag --latest
Sarcastic headline, but funny enough for engineers to sign up
Get curated content twice a month
Written by people, not robots - at least not yet. May or may not contain traces of sarcasm, but never spam. We value your privacy and if you subscribe, we will use your e-mail address just to send you our marketing newsletter. Check all the details in ShiftMag’s Privacy Notice