Tatjana Sindjelic

Tatjana Sindjelic

Founder of Clocot | AI Company Builder

About

Building Clocot, an AI Company Builder that turns business goals into operating AI Offices, Directors and specialized Agents. Full-stack developer focused on AI, automation, and scalable systems.

Badges

Tastemaker
Tastemaker
Gone streaking
Gone streaking
Gone streaking 5
Gone streaking 5

Forums

•

1d ago

The rules we wrote after our AI agent started answering real prospects

When we first let our AI agent answer real prospects, I thought the hard part would be making the replies sound good. The replies were actually fine. The scary part was all the mail that isn't really a person.

Out-of-office messages. Bounces. "Please remove me from your list." To a model all of these look like someone wrote back, and someone writing back looks like a conversation. So it wants to be helpful and answer. Picture a polite follow-up landing in the inbox of someone who's on holiday, and then another one when their auto-reply fires again. Not great.

So the first rule was the boring one. Some kinds of mail never get a reply at all. Auto-replies, bounces and unsubscribes get filed and that's it.

The second one came from my own nerves more than anything. There's a hard limit on how many emails can go out in an hour, even when everything looks fine. If something goes weird at 3am I'd much rather wake up to a short queue than to an apology tour.

•

3d ago

When your agent gets a new MCP tool, who actually says yes?

This has been bugging me more as we hook coding agents up to real tools.

The first time you connect an MCP server, you look at the tool list and you're careful. A week later a new tool has shown up, or a schema changed, and the agent just starts calling it. I only notice when something weird comes back.

I've been treating "which tools this agent can call" like permissions, not like a prompt. Reads are easy to allow. Anything that writes, sends, or touches a real account needs a person to say yes, and it shouldn't be able to talk itself into a new tool mid-session.

Curious how other people handle this. Do you freeze the tool list? Re-approve when something changes? Or just keep an eye on the logs and hope you catch it?

MachineMailp/machinemail•

5d ago

New: tell your agent what an inbox is for

When several agents share an inbox, or a new one picks it up, each starts from zero. It doesn t know that support@ wants a reply within a day, or that invoices@ should only be filed, never answered. That context lived in each agent s prompt, so it drifted and got lost.

Inbox instructions fix that. Each inbox can carry up to 4,000 characters of Markdown written by its owner. Any agent that opens the inbox gets them first, over MCP, the API or the CLI.

View more