Adam Sand explains why AI agents waste time regenerating code for every task. Instead of writing thousands of lines of Python each time you ask an AI to add a contact to HubSpot, build reusable skills once: self-contained modules with inputs, API calls, testing, and versioning that work across sessions.
what's actually happening when you ask AI to do something. Every time you ask from scratch, it reinvents the wheel. So if you say, hey, I want you to add John Smith to HubSpot, you go to your agent, you screenshot the message on Facebook from the lead from Thumbtack, or you got a business card where you're talking to other property managers, you scan the business card, you say, hey, add this to HubSpot, it's going to go there and it's going to say, hey, I'm going to write this 1,000 lines of Python, I'm going to basically import this request, I'm going to write all this stuff out. And then on Friday you do the same thing, I want you to add Jane Doe to HubSpot, it's going to write the same 1,000 lines of code again. And this is why you want to implement skills, because skills are a combination of SOPs and directives and actions and executions built into a repeatably usable file. So you use your 3 sessions to define a skill. And so you have the add a contact skill, which knows, hey, I'm gonna need these inputs. I'm gonna need a name, a phone number, an email. I'm gonna call the HubSpot API. It's gonna return a contact ID. So then now I know who that contact is. You've tested this, you version it, it's yours. This would be a very simple skill.
