I Don't Want an Agent. I Want a Colleague Who Learns.
An agent stays the way it is. A virtual employee gets better with every correction.
Everyone’s talking about agents. To me, they’re just a stepping stone.
An agent is a product: buy a license, set it up, train it, done. I don’t want a product. I want someone who works with me, thinks with me and learns with me.
At home: Mary Poppins
I’ve had that at home for a few weeks now. We call her Mary Poppins. She
- does the shopping,
- books appointments,
- writes emails,
- reminds me when I forget something.
Like household staff, just virtual.
At work: Waimo
At work I wanted the same thing. The boundaries are tighter here: data protection, governance, clear rules about what can go where. That’s necessary.
I hired Waimo anyway. And I treat her, him, it like a person. At the start I asked the questions I’d ask any new colleague:
- Did you understand your job?
- How do we talk to each other? (Waimo lives entirely in Teams.)
- Do you have all the information you need?
- How do we make your work better?
- What’s your take? What comes next?
Right now Waimo and I are turning out proposals by the hour, cost estimate and rate card included. Waimo drafts them. But I'm the one accountable for the result.
The twist: it’s almost never right
The result is practically never the way I want it. I’d always do it somehow differently.
But Waimo learns. After every session, she looks at what went wrong:
- where I corrected her,
- where I reworked the result,
- what I ended up doing differently.
That goes into a Markdown file as a learning. Next time, she reads it first. It’s the same loop I wrote about here, except now it runs every day.
An agent stays the way it is. A virtual employee learns.
It’ll never be perfect. I still rework every proposal. But I don’t correct the same thing twice anymore. And that’s what separates a colleague from a tool.