> ## Documentation Index > Fetch the complete documentation index at: https://docs.revbridge.ai/llms.txt > Use this file to discover all available pages before exploring further. # What you can ask > Example questions for analyzing performance, building audiences, and preparing campaigns with Claude. You don't need to learn commands — describe what you want. These examples show the range, and are good starting points to adapt. Everything falls into three levels: | Level | What happens | | --------- | --------------------------------------------------------------------------------- | | **Ask** | Claude reads your data and answers. Nothing changes. | | **Build** | Claude creates a draft — an audience, a campaign, a template. Still nothing sent. | | **Send** | Real messages go out. Always preceded by a preview and **your** confirmation. | ## Understand performance ``` How did we do last month? Give me the funnel and the headline numbers. Compare this month to last month — what actually changed? Which campaigns drove the most revenue in the last 90 days? What's our ROAS by channel? Where are we losing money? ``` ``` Break down the [campaign name] funnel by channel. Which creative won in [campaign name], and by how much? Did [campaign name] actually lift conversions versus the holdout? How much did [campaign name] spend, and what did it bring back? ``` ``` Run a cohort analysis and tell me where retention breaks. What's our average order value and customer lifetime value? Are we growing? Break it into new, returning, and churned customers. Who actually converts — how long have they been around, and how many messages did it take? Are we sending too much? Show me engagement by message number. ``` Ask "why" as a follow-up. The assistant can drill from a headline number into segments, channels, and cohorts without you rebuilding the question. ## Build audiences Ask for a size first — it's instant and changes nothing. Save it only when the number looks right. ``` How many people bought in the last 30 days? How many added to cart but never purchased? People who bought twice or more in the last 6 months — how many? Save that as an audience called "Repeat buyers – H1". ``` ``` How many people opened an email in the last 30 days but never purchased? Who clicked a message from [campaign name] and didn't convert? People we delivered to in the last 60 days who never opened anything — how many? ``` When you exclude people who *didn't* engage, ask Claude to also require that they were actually messaged — otherwise the audience fills up with people who never received anything in the first place. ``` People who added to cart and didn't purchase within an hour. Visitors who viewed a product then never came back within 7 days. Customers who bought and then opened a message in the following week. ``` ``` Here's a list of contacts — check it for problems before importing. Import these 2,300 contacts as an audience called "Trade show leads". Is that import finished? ``` Contacts can carry email, phone, first and last name, plus any extra columns you want to keep as attributes. ``` Find the audience with "seed" in the name. How big is "Repeat buyers – H1" right now? Size that rule again with refunders excluded. ``` A saved audience is a rule, not a frozen list — it is recounted against today's data every time you ask. An imported list is the exception: it reports the size it was imported with, and says so. ## Prepare campaigns ``` Draft a win-back campaign for customers who haven't purchased in 90 days. Create a campaign targeting "Repeat buyers – H1" across email and WhatsApp. Generate creative variants for that campaign in our brand voice. Show me the creatives and drop the ones that are off-brand. Is the creative generation finished yet? ``` Creative generation runs in the background — asking whether it finished is a real question, and you'll get the status rather than an empty list. ``` Which of our templates can carry a product feed? Find an email template that mentions free shipping. Show me what "Summer Drop" actually says. ``` Templates can be searched by what they *say*, not just by name. Reading one back gives you the copy a recipient would see, so you can judge tone and brand fit without opening the editor. A shopping campaign's template must contain a product-feed block — that's what gets filled with products at send time. Ask for feed-carrying templates and you only see the ones that qualify. ``` Change the audience on that draft to "Repeat buyers – H1". Rename it and push the start date to Monday. Raise the budget to R$500. ``` A draft is correctable, not disposable — you don't have to recreate it to change your mind. Only what you name changes; everything else stays put. Once a campaign is **running**, only its name, description, budget, schedule and sending limits can change, and you'll be asked to confirm first — moving a schedule or raising a budget on a live campaign takes effect immediately. A finished or cancelled campaign can't be edited at all. ``` How many people will this actually reach, and what will it cost? How long will it take to go out? Do I have enough balance to run this? Is anything blocking this from going out? ``` This is the step that produces the preview: resolved audience, cost per channel, wallet balance, any blockers — an unverified sending domain or missing creatives, for example — and how many days delivery will take at your daily sending cap. The days matter more than people expect. A 100,000-person audience on a channel capped at 5,000/day is a **20-day** send, not a Tuesday morning. Nothing is wrong with it — but it changes what "launch on Monday" means. ``` Go ahead and launch it. ← you'll get a confirmation prompt first Pause the [campaign name] campaign. Resume it. When does [campaign name] next run? ``` Launching a campaign, sending a blast, adding people to a running campaign, or firing a scheduled run immediately all send real messages and spend real budget. Each one requires a fresh preview plus your explicit approval. ## When something looks wrong Before concluding a campaign underperformed, check that it ran at all. ``` Did [campaign name] ever actually run? Why did [campaign name] fail? What went wrong on its last run? ``` A campaign that failed outright looks exactly like a campaign with low volume — both show small numbers — and a campaign that never started looks the same again. The difference only appears when you ask for its errors and its run history, so ask before you rewrite the creative. ## Guided methods The assistant carries a set of growth playbooks. Ask for one by name when you want a rigorous pass rather than a quick answer: | Method | Ask for it when you want to | | ------------------------ | ---------------------------------------------------------------- | | **Diagnose sweep** | Get a full read of the account before deciding anything. | | **Converter profile** | Learn who converts, when, and after how many touches. | | **Channel economics** | Compare what each channel returns before scaling spend. | | **Retention drilldown** | Find where repeat purchase breaks, cohort by cohort. | | **Cohort analysis** | Read a retention matrix correctly, avoiding the usual traps. | | **Hypothesis generator** | Turn findings into a few prioritized, ready-to-launch bets. | | **Weekly briefing** | Prepare the week: what changed, what's pending, what to discuss. | ``` Run the diagnose sweep on my account. Use the channel economics method before I decide where next month's budget goes. ``` ## Tips for better answers * **Give a time range.** "Last 90 days" beats "recently". * **Name the campaign or audience.** Ask Claude to list them first if you're unsure. * **Ask for the size before saving** an audience — it costs nothing and avoids surprises. * **Ask why.** Follow-ups are cheap; the assistant keeps the context of what it just showed you. * **Say when to stop.** "Draft it but don't send" makes the boundary explicit — though the confirmation step protects you either way. * **Check who a number counts.** Every answer states its population — buyers, contacts we've messaged, tracked visitors. Two correct numbers from two questions can still be about different people, so read that line before comparing them. Under the hood the assistant has a fixed set of capabilities. You never call these directly, but this is the complete boundary of what it can do: **Reading** — account and campaign listings; a campaign's configuration, its errors and its run history; funnel, attribution, per-channel, variant, lift, spend/ROAS and creative reports; creative generation status; data overview and event catalog; cohort catalog and cohort matrices; retention buckets; growth equation; LTV and AOV; product coverage and product search; converter profile; touch fatigue; audience sizing (saved, by rule, or ad hoc); segment listings with name search; template listings searchable by content, and reading one template's copy back; campaign schedules; send previews and cost estimates. **Creating and editing drafts** — campaigns (autonomous, shopping, triggered), AI creatives, shopping subject lines, audiences (rule-based or imported) and templates; editing an autonomous or shopping campaign; pausing, resuming and cancelling campaigns; updating, pausing and deleting schedules. **Sending — confirmation required** — launching a campaign, sending a one-shot blast, dispatching a shopping campaign, adding recipients to a running campaign, and firing a scheduled run immediately. Not included: moving money, changing billing or account settings, or sending raw messages outside a campaign.