The three things that make an agent
Chatbot vs agent, one task
Task: "handle the unpaid invoices." A chatbot returns tips on writing payment reminders. An agent queries your invoicing tool, finds the three that are overdue, drafts a chase email for each in your tone, and pauses: "ready to send these?" One gave you homework; one handed you finished work. (Sound familiar? It's the whole idea behind Yasmine.)
What agents are genuinely good at — and not
Good: multi-step digital chores with a clear goal — reporting, triage, drafting, research, code changes. Bad: tasks needing taste-based final calls, anything you can't verify, and work you'd never delegate to a sharp intern without review. The honest framing is delegation, not replacement — which is why the next section matters more than the demo.
The checklist before you trust one
- What policy governs each tool? Look for explicit Allow, Ask, and Block behavior, including fail-closed unattended Ask.
- Where does it run? Check tenant-scoped identity, encrypted state and credentials, shared-host disclosure, and dedicated-compute claims.
- Which model route? Confirm whether the route is included/platform-priced or a provider-billed eligible connection and whose terms apply.
- Can you see what it did? Every action should leave a visible trail you can audit.
- Where does memory live, and can you wipe it?
Yasmine is our answer to that checklist: an agent in Slack with per-channel memory, explicit Allow / Ask / Block tool policy, tenant-scoped encrypted state and credentials, and dedicated Fargate compute on Dev. Free and Starter use separate containers on shared AWS hosts. Here's what that looks like day to day.