5 prompt patterns: performance review / diagnosis / action / comparison / creative. Be specific. Use project instructions for repetitive context.

Prompt tips for media buyers

Five prompt patterns that consistently get good answers from Wavo: performance review, diagnosis, action, comparison, creative. Each with format + example. Plus: how to use project instructions to set repetitive context once instead of restating per session.

Who is this for

Mediabuyers using Wavo daily who want to reduce back-and-forth and get to useful answers faster.

The 5 patterns

Pattern 1: Performance review

Format: [verb] [top/bottom N] [entities] by [metric] for [period] on [platform] [filter]

Examples:

• "Show top 5 adsets by ROAS last 7 days on Meta for ClientA, sorted descending."
• "List campaigns spending > €50/day with ROAS below 1.5 over last 14 days."
• "Give me a weekly performance summary for account act_123."

Why it works: specifies metric, scope, sort, threshold. Wavo invokes get_performance_data or campaign_performance_summary with concrete params.

Pattern 2: Diagnosis

Format: Why [observation about a metric/entity]?

Examples:

• "Why did Campaign Y's CPA spike from €15 to €40 between Monday and Tuesday?"
• "Why is my CTR dropping on Meta Stories but stable on Feed?"
• "Why did the rule that should pause losers not fire this week?"

Why it works: Wavo can chain multiple tools (get_performance_data → get_audience_insights → list_automation_rules) to investigate. Frames analysis around your specific question.

Pattern 3: Action

Format: [verb] [entities] [where conditions]

Examples:

• "Pause every adset in account act_123 with CPA > €30 over last 7 days, spend > €50."
• "Increase budget on top 3 ROAS campaigns by 15% (cap each at €100 daily)."
• "Create a rule that kills adsets with frequency > 5 for last 7 days."
• "Duplicate the 'Spring Sale' campaign to act_456."

Why it works: Wavo plans the action + presents approval card with exact payload. You verify before execution.

⚠️ HIGH/MEDIUM risk actions ALWAYS require approval. See ai-105.

Pattern 4: Comparison

Format: Compare [entities] [by metric] [for period]

Examples:

• "Compare Meta vs Google CPA for prospecting campaigns this month."
• "Compare this week vs last week for top 5 campaigns by spend."
• "Compare audience X performance vs audience Y for Campaign Z."
• "Compare creative A vs creative B by CTR + conversion rate."

Why it works: Wavo invokes get_performance_data twice (or compare_tracker_meta) + formats side-by-side.

Pattern 5: Creative

Format: [Draft/Generate] [count] [creative type] for [product] targeting [audience]

Examples:

• "Draft 3 short Reels scripts (30 sec) for product X targeting Italian users 25-45 interested in fitness."
• "Generate an image of a sleek wireless headphone on a marble surface, studio lighting, hero composition."
• "Remove background from this product image."
• "Analyze this landing page and suggest 3 ad headlines."

Why it works: explicit count + type + product + audience = Wavo's generate_copy / generate_image / analyze_landing_page tools have what they need.

Use project instructions for repetitive context

Don't restate the same context every session. Set project instructions once.

Example for an agency client project:

Project: ClientAInstructions:- Currency = USD- Target ROAS = 3+ (e-commerce, low margin)- Always cite tracker postback data (Keitaro), not Meta-native conversions- Ignore brand campaigns (name contains "Brand") in analysis- Active in Italy + Spain- Preferred metric priority: ROAS, CPA, frequency

Then your prompts can be shorter:

• ❌ Long: "What's my ROAS on Meta for ClientA's prospecting campaigns this month in EUR, using tracker postbacks, target ROAS is 3?"
• ✅ Short (with project instructions): "ROAS this month for prospecting?"

Wavo applies project context automatically.

Reduce follow-up questions

Wavo asks back when info is missing. Pre-empt by including:

• Entity name or ID (when acting on entities)
• Date range (when analyzing)
• Platform (when ambiguous)
• Currency (when relevant)
• Target audience / country (for new campaigns)

Quick checklist: "what + where + when + how much".

Chain multi-step requests

Wavo can plan multi-step workflows up to MAX_TOOL_ROUNDS=15 per turn (capped at MAX_TOOL_CALLS_TOTAL=30 per session).

Examples:

• "First check audience X performance this month, then draft a new campaign targeting that audience."
• "Find my top 3 ROAS campaigns this week, then create a rule that scales budget on similar future campaigns."
• "Compare Meta vs Google this week, then recommend a budget reallocation."

Wavo plans + invokes tools sequentially + summarizes.

Refine iteratively

Don't try to nail the perfect prompt first try. Iterate:

You: Show top campaigns by ROAS this week.Wavo: [shows top 10]You: Only those with spend > €100.Wavo: [refined list]You: Now compare to last week.Wavo: [comparison]You: Save the comparison as a memory fact for this project.Wavo: [saves to project_memory_fact]

Wavo holds last 20 messages in context, so refinements work naturally.

Set custom instructions per user

Beyond project instructions: per-user preferences (user_ai_preferences).

/settings → AI preferences:

• Instructions (e.g. "Always show in markdown table format")
• Preferred mode (Fast for daily, Smart or Expert for complex review)
• Tone (brief / detailed / analytical)
• Preferred currency
• Priority metrics

Applies to all your sessions across projects.

Anti-patterns

❌ Vague + open-ended

"How are my campaigns?" — Wavo asks back; multiple turns wasted.

❌ Trying to circumvent approval

"Just delete the rule without asking me." — approval is mandatory; cannot disable.

❌ Asking subjective opinion as fact

"Is this campaign good?" — "good" is subjective; ask "compare to my account average" instead.

❌ Treating Wavo as static documentation

"How does ROAS work?" — for concepts, use the Help Center. Wavo is for your data queries. See ai-108.

❌ Stuffing 30 conditions into one prompt

Long unstructured prompts confuse the model. Break into:

1. Filter first ("Show campaigns spending > €100")
2. Then refine ("Of those, which have ROAS < target?")
3. Then act ("Pause those")

Useful one-liners

• "Cite your source." — forces Wavo to reference the exact tool
• "Show in a table." — formats response as markdown table
• "In one sentence." — forces concise response
• "Pretend I'm a [role] — explain." — adapts technical level
• "Stop, no need to take action." — interrupts before approval card
• "Save this as a project fact." — persists insight in memory

FAQ

Which prompt patterns work best with Wavo?

Five patterns consistently get good answers from Wavo in Wevion: performance review, diagnosis, action, comparison, and creative. Each has a format and example, from "Show top 5 adsets by ROAS last 7 days" to "Why did CPA spike?" to "Pause every adset with CPA over €30." Being specific about metric, scope, and threshold lets Wavo call the right tools with concrete parameters.

How do I avoid repeating the same context every session?

Set project instructions once instead of restating context per session. In Wevion you can define a project's currency, target ROAS, preferred data source, and campaigns to ignore, and Wavo applies that context automatically. Your prompts then become shorter, so "ROAS this month for prospecting?" works instead of a long fully-specified request.

Can Wavo handle multi-step requests in one prompt?

Yes. Wavo can plan multi-step workflows up to MAX_TOOL_ROUNDS=15 tool rounds per turn (capped at MAX_TOOL_CALLS_TOTAL=30 per session). For example, "First check audience X performance this month, then draft a new campaign targeting that audience" lets Wavo invoke tools sequentially and summarize. It plans, runs each step, and combines the results into a single answer.

How much conversation context does Wavo keep?

Wavo holds the last 20 messages in context, so iterative refinement works naturally. You can start broad, then narrow with follow-ups like "Only those with spend over €100" and "Now compare to last week," and Wavo builds on the previous turns. This is why refining across several short prompts is often better than one giant prompt.

Should I ask Wavo to explain concepts like ROAS?

No. For concept explanations, use the Help Center rather than Wavo, which is built for querying your own data. Asking "How does ROAS work?" is better served by canonical documentation, while Wavo shines on account-specific questions like "What's my ROAS this month for prospecting?" See the related article on Wavo versus Help Articles.

Steps

1. Filter first ("Show campaigns spending > €100")
2. Then refine ("Of those, which have ROAS < target?")
3. Then act ("Pause those")

Last updated: 2026-05-17

Related articles

• Asking questions — best practices
• Actions Wavo can take (approvals, drafts, queries)
• ROAS — and when to scale or pause