# Fin three-mode QA before AI agent go-live

> Use Preview, Batch tests, and Simulations together before an AI support workflow goes live so you catch both local mistakes and system-level failures.

- Canonical HTML: https://growth.iangoh.com/growth-ideas/fin-three-mode-qa-before-ai-agent-go-live/
- Source: [intercom.com](https://www.intercom.com/help/en/articles/14077180-simulations-vs-batch-tests-vs-previews)
- GrowthDex source hub: [Intercom Help: Simulations vs. Batch tests vs. Previews](/sources/intercom-help-simulations-vs-batch-tests-vs-previews-intercom-com/)
- Last checked: 2026-05-30
- Rarity: rare
- Budget: free
- Channels: AI Support, Support, Product
- Stages: qa, ai agent, support automation, pre-launch


## Why this can grow

AI support flows usually fail in two places: the answer quality and the workflow around the answer. Intercom's testing stack is useful because each mode catches a different class of mistake. Preview is fast for spot checks while building. Batch tests are broad enough to expose coverage gaps across many questions. Simulations check whether a Procedure actually survives end-to-end logic before customers touch it. Running only one mode leaves blind spots that show up later as confused handoffs, wrong escalations, and support debt.

## Ian's take

From scaling consumer platforms across MENA and Southeast Asia, my default is to distrust growth work that only looks good in a slide. My bias is to treat this as a small market test first. Make the audience narrow, make the promise concrete, and let the first real response decide whether it deserves more work. I would run it small enough to learn quickly, then only scale the parts that real users repeat, save, reply to, or buy from. For this tactic, I would watch one clear growth signal before putting more time or budget behind it.

## Action plan

1. Define one narrow startup segment where fin three-mode qa before ai agent go-live can create a measurable lift.
2. Turn the tactic into one offer, page, campaign, or workflow for the AI Support and Support channel.
3. Use the evidence from intercom.com to set the first version of the message, format, and audience.
4. Launch a small test for 7 to 14 days with one success metric: one measurable growth signal.
5. Review the result, keep the winning message, remove weak variants, and turn the learning into a repeatable growth playbook.

## Source-backed example

Intercom's March 16, 2026 help guidance says teams should use all three tools in combination before go-live: Preview for quick manual checks, Simulations for end-to-end Procedure validation, and Batch tests to confirm answers across real customer questions.

## Adjacent tactics in the same lane

- [Customer Advocacy design-brief pass before build](/growth-ideas/customer-advocacy-design-brief-pass-before-build/) - 2 shared channels, 1 shared stage
- [Trigger review queue before chat-to-messaging launch](/growth-ideas/trigger-review-queue-before-chat-to-messaging-launch/) - 2 shared channels, 1 shared stage
- [Hide unreleased docs until the version is real](/growth-ideas/hide-unreleased-docs-until-the-version-is-real/) - 2 shared channels
- [Public comment update emails every voter](/growth-ideas/public-comment-update-emails-every-voter/) - 2 shared channels

## Read GrowthDex essays

Browse the plain-English essay index at [GrowthDex Blog](/blog/).

## Related GrowthDex essays

- [Support starts paying off before the ticket exists](/blog/support-starts-paying-off-before-the-ticket-exists/) - support, activation, brand trust

## Advisory

If you want help turning this into a working growth system, Ian Goh offers advisory at https://iangoh.com/advisory.