Trigger Best Practices for AI Agents (Macha)
Triggers are simple to set up — and easy to get subtly wrong in ways that cost you credits or send the wrong tickets to an agent. A few practices keep them efficient, predictable, and cheap.
Watch the tips
1. Don't overfire
This is the big one. The trigger you choose decides how often the agent runs, and every fire costs a credit. The classic mistake is using a broad trigger like Every Customer Ticket Message, which fires on every new customer comment — so a single chatty ticket can run your agent (and spend credits) a dozen times.
Pick the most specific trigger that matches your workflow. If the agent only needs to act once per ticket, use Ticket Created, not Comment Added. If it should react only when something specific happens, scope to that event. The narrower the trigger, the fewer wasted runs. (See how triggers and the credit model interact.)
2. Name your triggers clearly
When you have more than a couple of triggers, vague names become a maintenance headache. Name each one so it's obvious what tickets it receives and which agent it feeds — e.g., "New tickets → Bug Summary agent." A clear name tells you at a glance what the trigger does, which makes debugging and changes far easier later.
3. Use multiple triggers to be precise
You're not limited to one trigger per agent — and using several is often the cleaner way to control exactly which tickets reach an agent. Instead of one broad trigger that catches too much, create multiple narrow triggers that each send a specific slice of tickets to the same agent. You get precise control over the agent's input without writing complex conditions into a single trigger.
4. Scope, then test
Tie it together with a habit:
- Scope each trigger to the smallest set of events that does the job.
- Name it clearly.
- Test it (fire the event, check History) before relying on it.
- Watch the run volume in Agent Analytics — an agent firing far more than expected usually means a trigger that's too broad.
A quick checklist
- [ ] Is this the most specific trigger that does the job?
- [ ] Could it overfire (e.g., on every comment) and waste credits?
- [ ] Is the trigger named so I'll understand it in three months?
- [ ] Would two narrow triggers be cleaner than one broad one?
- [ ] Have I tested it and checked the run volume?
Frequently asked questions
What does "overfiring" mean? A trigger that fires more often than needed — like running on every customer comment instead of once per ticket — which wastes credits.
Does each trigger fire cost a credit? Each agent run costs a credit (one per response), so a trigger that fires a lot means more runs and more credits.
Why name triggers carefully? With several triggers, clear names ("new tickets → Bug agent") make it obvious what each does, which saves you when debugging.
Can I send multiple triggers to one agent? Yes — and using several narrow triggers is often cleaner than one broad one.
The bottom line
Good triggers are specific, clearly named, and tested. Avoid broad triggers that overfire and burn credits, name each so future-you understands it, and use multiple narrow triggers when you need precise control. Set them up this way and your automation stays cheap and predictable.
Tune your triggers: scope them tight and watch the run volume drop. 7-day free trial, no credit card required. Start free.
