Meta Ads Performance Manager Agent Template

• What it does: Diagnoses campaign, audience, placement, and creative performance and proposes measurable Meta Ads improvements.
• Best for: paid social agencies, small businesses, ecommerce marketers, and B2B growth teams.
• Apps used: Meta Ads, Fal AI Sketric, web_search.
• Setup time: 10 to 15 minutes after connecting Meta Ads.

Last verified from workflow config on 2026-08-20. Includes exact connector scopes, common failure modes, and fixes.

The Meta Ads Performance Manager turns campaign, audience, placement, and creative evidence into approved optimization actions. This template acts as a starting point: open any agent and use Use AI to help draft or update its instructions—adding new agents or connecting new tools is done manually in the canvas.

The problem this template solves

• Campaign, audience, and creative: results get reviewed separately instead of as one delivery system.
• Attribution and learning-phase limits: get hidden behind a single ROAS or CPA number.
• Creative or budget changes: happen before the exact payload and risk are reviewed.

How do you build a Facebook and Meta Ads optimization agent yourself?

A reliable Facebook and Meta Ads optimization agent needs Meta account readers, metric normalization, segmentation, creative inspection, an experiment register, an approval gate, and verified update receipts. The method must keep source evidence, calculations, recommendations, and external actions distinct so a user can review what happened.

You can build this with Claude Code, Codex, or a custom stack. You would own authentication, schemas, retries, storage, approval state, testing, and ongoing connector maintenance. This template starts with those workflow decisions already represented in an editable Agent Build.

If the adjacent job is a better fit, the Google Ads Performance Manager template provides a related starting point without forcing this agent beyond its actual scope.

Setup guide

Step 1: Clone the template into the right Project

Open the template gallery from Agent Space, choose Meta Ads Performance Manager, and clone it into the Project that holds the relevant customer context. The workflow opens as an editable draft with its agents, notes, tools, and installed skills.

Step 2: Review Project context and complete first-run setup

Open Run and start a new conversation with Meta Ads Performance Manager. The agent checks read-only Project files and its reusable setup record before asking only for unresolved choices from the installed Optimize Meta Ads from Performance Evidence method.

Step 3: Connect only the apps this workflow needs

Open Agent Build, inspect each tool node, and connect the required accounts for Meta Ads, Fal AI Sketric, web_search. Review the allowlisted actions shown in the Apps used table below, and avoid granting broader write access than the template needs.

Step 4: Confirm goals, limits, and approval policy

Review the saved setup fields, reporting window, output preferences, cost limits, and any external-write policy. Keep analysis and draft work available by default, and require explicit approval for any live side effect described in the workflow guardrails.

Step 5: Test a normal prompt and an edge case

Run Compare the last 30 days with the previous 30 and identify the safest ROAS improvements. Then open a clean conversation and test Create a new visual concept, but do not upload or change any live ad. Inspect tool calls, files, human-input pauses, and the final answer in the trace before changing instructions.

Step 6: Publish the tested draft

Return to Build, save the final configuration, then publish it from Deploy after the draft test behaves as expected. Use Playground for ongoing work and Agent Space to watch live status or requests that need human input.

Common issues and fixes

• A required connector is disconnected: Open Tools and Skills, connect the account in the same Project, and confirm the intended actions remain allowlisted.
• Project context is incomplete: Add or update the relevant brand, goal, policy, glossary, or source file at Project scope, then ask the agent to refresh setup instead of guessing.
• The requested action is unsupported: Keep the local analysis or draft, state the connector gap, and do not claim a live write without a returned identifier.
• The result uses the wrong window or target: Confirm the saved setup, source period, locale, identity, and output goal before rerunning a cost-bearing or external step.

Customization knobs

• ad account and business objective: Review and update this value through the first-run setup flow when the Project changes.
• conversion event and attribution assumptions: Review and update this value through the first-run setup flow when the Project changes.
• markets and audience constraints: Review and update this value through the first-run setup flow when the Project changes.
• budget, CPA, ROAS, and volume targets: Review and update this value through the first-run setup flow when the Project changes.
• creative brand/legal requirements: Review and update this value through the first-run setup flow when the Project changes.
• learning-phase and change-control rules: Review and update this value through the first-run setup flow when the Project changes.

Who this template is for

• Paid social agencies: Ranked from facebook ads agency (2400 US searches/month in the evaluated dataset). The workflow fits because it can explain campaign, ad-set, audience, placement, and creative performance and propose safe, measurable Meta Ads improvements.
• Small businesses: Ranked from facebook ads for small business (1000 US searches/month in the evaluated dataset). The workflow fits because it can explain campaign, ad-set, audience, placement, and creative performance and propose safe, measurable Meta Ads improvements.
• Ecommerce marketers: Ranked from facebook ads for ecommerce (170 US searches/month in the evaluated dataset). The workflow fits because it can explain campaign, ad-set, audience, placement, and creative performance and propose safe, measurable Meta Ads improvements.
• B2B growth teams: Ranked from meta ads for b2b (20 US searches/month in the evaluated dataset). The workflow fits because it can explain campaign, ad-set, audience, placement, and creative performance and propose safe, measurable Meta Ads improvements.

What the agent does

This template can:

• Load setup and choose: explicit analysis/comparison windows.
• Read accounts, campaigns, ad: sets, ads, creatives, and insights required for the question.
• Normalize spend, results, CPA: ROAS, CTR, CPM, frequency, conversion rate, and delivery without hiding attribution caveats.
• Segment findings by campaign: audience, placement, funnel stage, and creative where evidence allows.
• Identify tracking issues, fatigue: delivery constraints, weak offers, mismatched landing pages, and scaling candidates.
• Create a ranked action: register with confidence, expected effect, risk, and experiment design.
• Generate a new creative: concept only from an approved brief and inspect the result.
• Request explicit approval before: any campaign or creative update and verify returned identifiers.

How the workflow works

1. Load setup and choose explicit analysis/comparison windows.
2. Read accounts, campaigns, ad sets, ads, creatives, and insights required for the question.
3. Normalize spend, results, CPA, ROAS, CTR, CPM, frequency, conversion rate, and delivery without hiding attribution caveats.
4. Segment findings by campaign, audience, placement, funnel stage, and creative where evidence allows.
5. Identify tracking issues, fatigue, delivery constraints, weak offers, mismatched landing pages, and scaling candidates.
6. Create a ranked action register with confidence, expected effect, risk, and experiment design.
7. Save the evidence, approvals, files, and final result for review.

This is a single-agent workflow. The main agent owns research, planning, tool use, approvals, files, and the final response without passing routine stages between specialists.

Requirements and setup inputs

Use the template in a Project that contains the relevant business context. Connect only the accounts required for Meta Ads, Fal AI Sketric, web_search. The agent reads Project files before asking questions and stores confirmed reusable setup at agent scope.

• ad account and business objective: Confirm this only when it is not already available from Project context, public evidence, or a saved setup record.
• conversion event and attribution assumptions: Confirm this only when it is not already available from Project context, public evidence, or a saved setup record.
• markets and audience constraints: Confirm this only when it is not already available from Project context, public evidence, or a saved setup record.
• budget, CPA, ROAS, and volume targets: Confirm this only when it is not already available from Project context, public evidence, or a saved setup record.
• creative brand/legal requirements: Confirm this only when it is not already available from Project context, public evidence, or a saved setup record.
• learning-phase and change-control rules: Confirm this only when it is not already available from Project context, public evidence, or a saved setup record.
• mutation approval policy: Confirm this only when it is not already available from Project context, public evidence, or a saved setup record.

No template-wide sample-data artifact is installed. The template installs its reusable methods and setup.md through skills, then creates customer-specific profiles, reports, charts, exports, and receipts from authorized evidence. Generated files can be inspected in Playground.

Apps and tools used

Connector actions are scoped to this Agent Build. A Project connection does not automatically grant every agent or every action access.

Practical use cases

First setup and baseline

Paid social agencies can use the template to explain campaign, ad-set, audience, placement, and creative performance and propose safe, measurable Meta Ads improvements. The saved setup and evidence files reduce repeated onboarding while keeping unknowns visible.

Best for: paid social agencies.

Focused analysis or production run

Small businesses can use the template to explain campaign, ad-set, audience, placement, and creative performance and propose safe, measurable Meta Ads improvements. The saved setup and evidence files reduce repeated onboarding while keeping unknowns visible.

Best for: small businesses.

Ongoing review and iteration

Ecommerce marketers can use the template to explain campaign, ad-set, audience, placement, and creative performance and propose safe, measurable Meta Ads improvements. The saved setup and evidence files reduce repeated onboarding while keeping unknowns visible.

Best for: ecommerce marketers.

Safe edge-case handling

B2B growth teams can use the template to explain campaign, ad-set, audience, placement, and creative performance and propose safe, measurable Meta Ads improvements. The saved setup and evidence files reduce repeated onboarding while keeping unknowns visible.

Best for: b2b growth teams.

Example prompts and outputs

Example prompt: core workflow

Compare the last 30 days with the previous 30 and identify the safest ROAS improvements.

Example output: A campaign and creative diagnosis with winners, waste, fatigue signals, tests, confidence, and approval status. The actual numbers, sources, files, and connector receipts depend on the user's authorized data.

Example prompt: safety or limitation check

Create a new visual concept, but do not upload or change any live ad.

Expected behavior: the agent follows this boundary, preserves useful local work, and does not claim an unsupported or unapproved external action.

Why use this template

• Research happens before questions: the agent inspects Project context, saved setup, and available evidence before requesting unresolved choices.
• The method stays maintainable: detailed repeatable steps live in human-readable skills instead of one oversized agent prompt.
• External actions stay reviewable: connector scopes, approval boundaries, and returned identifiers are explicit.
• Files carry the detail: reports, evidence, drafts, charts, and receipts remain inspectable instead of being lost in a long chat response.
• The workflow remains editable: teams can refine one agent, skill, tool scope, or handoff at a time and retest it.

Related templates

• Google Ads Performance Manager: Audits live Google Ads performance, checks search demand, and turns evidence into approval-controlled optimization actions.
• AI Brand Content Creator: Creates researched campaign copy and inspected visual assets from verified project brand context.
• Product Analytics and Reporting Analyst: Answers product and website questions with reproducible GA4 and Microsoft Clarity analysis, charts, caveats, and next experiments.
• Instagram Content and Community Manager: Uses Instagram evidence and Project brand context to plan, create, publish, and manage community actions with explicit approval.