> For the complete documentation index, see [llms.txt](https://docs.sellermagnet.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.sellermagnet.com/ppc-management-beta/ppc-manager-overview/ppc-ai-optimizer.md). # PPC AI Optimizer Let SellerMagnet's AI continuously monitor and optimize your Amazon PPC campaigns from a single 8-tab cockpit, from bid adjustments and keyword management to budget allocation, coverage audits and ano {% hint style="info" %} **Difficulty:** 🔴 Advanced · **Reading time:** \~15 min {% endhint %} {% hint style="success" icon="rocket" %} **Open this page in your dashboard:** [**Go to PPC AI Optimizer \[BETA\] →**](https://dashboard.sellermagnet.com/ppc/ai-optimizer) {% endhint %} {% hint style="warning" icon="triangle-exclamation" %} **BETA:** The PPC Manager is currently in beta. Some features may behave unexpectedly or change based on user feedback. Please report any issues at . {% endhint %} ## 📋 Overview The **AI Optimizer** - shown in the dashboard as the **AI Campaign Autopilot Command Center** - is SellerMagnet's most advanced PPC feature. It continuously analyzes your campaign data and turns it into smart, ranked recommendations: from keyword-level bid adjustments to keyword harvesting, negatives, placement tuning, budget reallocation, cross-campaign coverage audits and anomaly detection. Depending on your Autopilot mode, these changes are applied automatically or queued for review in your **Approval Center**. The AI Optimizer is not a black box. Every recommendation comes with a **confidence score**, a **human-readable explanation**, and a **projected impact estimate** so you always understand *why* a change is suggested and *what* to expect if you approve it. The whole feature is organized as a **cockpit with eight tabs** - Overview, Wins, Issues, Recommendations, Coverage Audit, Diagnostics, Intelligence and Automation. A persistent trust strip sits under the header, and each tab carries a dismissable **"First time here?"** onboarding guide plus a persistent best-practice tip rail, so you can learn a surface the first time you open it. {% hint style="info" icon="circle-info" %} **What "Autopilot" means here.** Your **Autopilot mode** decides what the AI is allowed to do on its own. In **Suggestions Only** the AI surfaces recommendations and you decide whether to apply each one. In **Semi-Auto (Approve)** changes are queued in the [Approval Center](/ppc-management-beta/ppc-manager-overview/ppc-approval-center.md) for batch approval. In **Full Autopilot** high-confidence changes apply automatically - every one is logged and reversible. The mode lives in the **governance card at the bottom of the Overview tab** (see [Overview tab](#overview-tab)). Whichever mode you choose, every change still passes through your safety caps (Max Bid Cap and Min Spend Threshold) on its way to Amazon, and auto-applied changes are recorded in the [Activity Log](/ppc-management-beta/ppc-manager-overview/ppc-activity-log.md). {% endhint %} {% hint style="success" icon="shield-halved" %} **Nothing applies without your approval.** The trust strip under the header states the core promise: every recommendation is reversible, runs through the Approval Center, and respects a 7-day rollback window. Sandbox mode is on by default for new accounts. {% endhint %} > **Prerequisites:** Before relying on the AI Optimizer, set up your guardrails in the governance card (Target ACoS or ROAS, Max Bid Cap, Min Spend Threshold, and Autopilot mode). The AI uses those values as hard limits for every recommendation it generates. *** ## 🎥 Video Walkthrough {% hint style="warning" %} **Video tutorial coming soon.** A full guided walkthrough of this feature will be available here shortly. {% endhint %} *** ## 🧭 The Cockpit Hero At the top of the page sits the command hero. It carries the page title, the **Analysis Workspace** control card, and a row of headline stats. * **Analysis Window** - the lookback the on-demand analysis uses: **Last 7 / 14 / 30 / 60 / 90 days** (default 30). Changing the window re-scores the portfolio. * **Profile / Marketplace** - scope the analysis to a single Amazon Ads profile. * **Run Full Analysis** - the workspace stays empty until you press this. A full run takes roughly 20-60 seconds and fills every tab; the AI scans every campaign, ad group, keyword, search term, placement and budget rule, then ranks opportunities by currency impact. The headline stats update after each run: | Stat | What it shows | | ---------------------------------------- | -------------------------------------------------------------------------- | | **Portfolio Health** (`ai-health-score`) | A single 0-100 score for the whole account (detailed on the Overview tab) | | **Open Actions** | Recommendations plus anomalies awaiting your review | | **Projected Upside** | Estimated savings plus growth opportunity from the current recommendations | Below the hero, the **AI Pulse** panel gives a live sense of what the optimizer is watching right now - today's bid moves, harvests, negations and estimated monthly savings, plus a "watching right now" list and the latest applied moves. {% hint style="warning" %} **Mixed currencies are not directly comparable.** If your account spans multiple marketplace currencies, the savings and upside totals are summed across currencies and flagged as not directly comparable. Use the "Show per-marketplace breakdown" link, or select a single marketplace, for an accurate figure. {% endhint %} *** ## The Eight Tabs The cockpit splits the work into eight tabs. Each tab button can show a count chip when it has open items. | Tab | Purpose | | ------------------- | ---------------------------------------------------------------------------------------------------------------- | | **Overview** | Your daily cockpit - health, wins, issues, next-best actions, trust score, and the Autopilot governance controls | | **Wins** | What your AI saved you this week | | **Issues** | Every active issue, severity-ranked - drill in to fix | | **Recommendations** | The AI's proposed changes, harvesting, bids, placements and budget execution | | **Coverage Audit** | Cross-campaign coverage audit - the leaks single-campaign analysis misses | | **Diagnostics** | Conflict detection, waste control and structural diagnostics | | **Intelligence** | Pattern mining, momentum and share capture | | **Automation** | Dayparting, rule engines and profit engineering (PRO) | *** ### Overview tab The Overview tab is the **Executive cockpit** - "Command, health and active automation." It is designed as your daily check-in before drilling into any other tab. ![PPC AI Optimizer - Automated campaign optimization](https://4139654583-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2Fih2knSvVpBcq5rIeXVjM%2Fuploads%2Fgit-blob-c04560a917be2784c9fd3c91411de62245bffa3b%2Fppc-ai-optimizer.png?alt=media) **Cockpit highlight cards.** Four cards summarize the account at a glance. Click any card to jump to its dedicated tab: * **Wins this week** - recovered spend and uplifts (opens the Wins tab) * **Issues this week** - open problems (opens the Issues tab) * **Next-best actions** - the top recommendations to work now * **Trust score** - how much autonomy the Autopilot has earned with you {% hint style="info" icon="circle-info" %} **Trust score.** Starts at 50; rises with applied recommendations that pay off, falls with rollbacks. **Under 60 keeps the AI in suggest-only safe-mode** and it will not auto-apply until the score climbs. The score updates after every Autopilot run. {% endhint %} #### Portfolio Health score The cockpit summarizes your account's overall PPC health as a single **0-100 score**, shown as a color-coded ring. It is a composite across four areas: | Component | What it measures | | -------------- | ---------------------------------------------------- | | **Efficiency** | Your achieved ACoS versus your Target ACoS | | **Waste** | Zombie keywords and other spend that returns nothing | | **Structure** | Duplicates and conflicts across your campaigns | | **Momentum** | The direction your key metrics are trending | As a rule of thumb: **80+** is strong, **60-79** is healthy with fixable issues, and **under 60** needs attention. {% hint style="danger" %} **A low score is not always bad - check your Target ACoS first.** Because the efficiency component is graded against your Target ACoS (not an absolute benchmark), a genuinely profitable account can read low purely because its Target ACoS is set far below what it actually achieves. Before reacting to a low score, confirm your Target ACoS reflects your real margins. {% endhint %} #### AI Analysis Summary Alongside the health ring, the summary reports what the latest run found: **Keywords Scored**, **Bid Changes** proposed, **Anomalies**, **Est. Savings**, **Est. Growth**, and the portfolio **Avg Score**. Each keyword gets a 0-100 profitability score blending clicks, conversion rate, ACoS and statistical confidence. #### Briefing, recent actions and smart recommendations Further down the Overview tab you get the **AI Daily Briefing** (summary, wins, problems and an action plan), a **Recent AI Actions** feed (last changes applied or suggested, linking into the Activity Log), and a **Smart Recommendations** list that can be filtered by **All / Critical / High / Auto-Fixable**. The **Autopilot Activity Log** and **Optimization Impact** panels show what past automation has done to your numbers. #### Governance: Autopilot mode, goals and guardrails The **Campaign Autopilot** governance card lives at the bottom of the Overview tab. This is where you configure how aggressively the optimizer acts, and it is the single source of truth for the settings the AI runs on. Defaults work for most accounts - adjust only when you have a clear reason. | Control | Options / meaning | | ----------------------- | --------------------------------------------------------------------------------------------------------- | | **Mode** | Suggestions Only · Semi-Auto (Approve) · Full Autopilot | | **Optimization Goal** | Target ACoS · Target ROAS · Maximize Profit · Maximize Revenue · Maximize Impressions | | **Target ACoS %** | Your ACoS target (shown when the goal is Target ACoS) | | **Target ROAS** | Your ROAS target (shown when the goal is Target ROAS) | | **Max Bid Cap** | A hard ceiling - the AI never bids above this, even on Full Autopilot | | **Min Spend Threshold** | Minimum cost a keyword must have accumulated before the AI will adjust it (filters out statistical noise) | Press **Save Configuration** to store the settings, then **Run Cycle** to run the optimizer once now. In Full Autopilot, eligible bid and budget changes apply to your live campaigns immediately (destructive actions are still held for approval); in Suggestions Only / Semi-Auto it only queues recommendations. > **Pro Tip:** Your **Optimization Goal** is the modern equivalent of a "strategy" choice - it tells the AI what to prioritize when trading off impressions, sales volume, ACoS and profit. Start in **Suggestions Only** for the first 7 days so you can see the proposed changes in the Approval Center before letting anything auto-apply; the trust score climbs as you accept good suggestions. *** ### Wins tab "What your AI saved you this week." Every win is a real action Autopilot (or a rule) applied - a bid cut, a negation, a harvest graduation, a budget shift - and everything is reversible from the Activity Log. * A hero figure sums the savings and uplift the AI has unlocked. * **Recovered spend & uplifts** and **Recently applied actions** cards list the individual moves. Recovered spend is the money that would have leaked without the action. * **Scale winners - your next moves** flips to the offensive: opportunities to scale proven winners (raise bids on under-impressioned converters, lift budgets on capped-but-profitable campaigns, expand match types, graduate auto-campaign winners, lean into top-of-search, lock in brand defense). {% hint style="info" icon="lightbulb" %} **Use this with stakeholders.** Wins are immutable, recorded actions with an audit trail - ideal for defending the AI's value in a monthly report. Filter by month or campaign to build a clean ROI summary. Wins update hourly, with bigger jumps after the daily Amazon report sync (around 04:00 UTC). {% endhint %} *** ### Issues tab "Every active issue - drill in to fix." Issues are ranked by severity (**critical → warning → info**) and each card links to the dedicated fix tool in Recommendations or Coverage Audit. * **Critical** = active spend bleed. **Warning** = inefficiency. **Info** = something to keep an eye on. * A 7-day severity heatmap lets you filter the list to a specific day and type. * **Snooze** hides a row for 7 days without resolving it. {% hint style="info" %} **Work the queue weekly.** Sort by impact and clear the top five each week. The impact column quantifies what each unresolved critical issue is costing you. {% endhint %} *** ### Recommendations tab The action queue - "Recommendations, harvesting and budget execution." This is where detection turns into execution. Recommendations are ranked by **Expected Impact** (currency saved or earned over the next 30 days), and only recommendations with **at least 80% statistical confidence** appear here. ![PPC Approval Center: review AI suggestions before applying](https://4139654583-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2Fih2knSvVpBcq5rIeXVjM%2Fuploads%2Fgit-blob-7a47d384c8e124d378c4397f9f3d84c016613e03%2Fppc-approval-center.png?alt=media) {% hint style="info" icon="circle-info" %} **Approvals flow through the Approval Center.** In Suggestions Only and Semi-Auto (Approve) modes, nothing changes until you act. Approved changes are pushed to Amazon Ads; in Full Autopilot high-confidence changes apply on their own. Sandbox mode previews without touching Amazon. See the [PPC Approval Center](/ppc-management-beta/ppc-manager-overview/ppc-approval-center.md) guide. {% endhint %} The tab bundles several execution surfaces: | Surface | What it does | | -------------------------------- | ---------------------------------------------------------------------------------------------------------------------- | | **AI Recommendations** | The ranked action cards - each shows the change, the projected outcome, the confidence, and the reasoning trail | | **Keyword Harvesting** | Scan for converting search terms and graduate them into their own exact-match keywords for bid control | | **Negative Keywords** | Scan for wasteful search terms (zero conversions or extreme ACoS) and negate them (NEGATIVE\_EXACT / NEGATIVE\_PHRASE) | | **Smart Bid Suggestions** | Per-keyword bid moves based on Thompson Sampling (a Bayesian explore/exploit policy) | | **Profit Forecast (30 Days)** | A projected profit chart with supporting KPIs | | **Placement Optimizer** | Top of Search / Product Pages bid-modifier suggestions from placement-level data | | **Budget Allocation** | Suggested daily-budget shifts toward the highest marginal-ROAS campaigns | | **Portfolio Matrix** | A campaign-level matrix view of your portfolio | | **Campaign Structure** | Funnel-structure analysis and recommendations | | **Anomalies Detected** | Statistical outliers versus your baseline (spend spikes, CVR drops, impression cliffs) | | **Keyword Profitability Scores** | A sortable table of every scored keyword - Score, Grade, Clicks, Orders, Spend, Sales and ACoS | Harvesting and negatives support **Scan → select → Apply Selected**; bid and placement lists support **Apply All**. > **Best Practice:** Sort by Expected Impact and clear the top 10 weekly - recommendations decay (a "harvest" today may already be in a sibling campaign tomorrow). Treat rows below 80% confidence with extra care, and read the reasoning before approving. *** ### Coverage Audit tab "Cross-campaign coverage audit." When the same ASIN runs in multiple campaigns, single-campaign analysis misses portfolio-wide leaks. This tab pivots on the **campaign-to-ASIN map** to surface three classes of leak: | Section | The leak it finds | | --------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | **Negative-coverage gaps** | A wasteful term is negated in one campaign but still bleeds in a sibling running the same product. Bulk-apply a NEGATIVE\_EXACT across every uncovered sibling to stop it portfolio-wide | | **Cross-campaign contradictions** | You bid on a keyword in campaign A while blocking it as a negative in campaign B for the same ASIN - decide one direction | | **Harvest consolidation** | A search term you are about to harvest already exists as a positive keyword elsewhere - bid up there instead of creating a duplicate | {% hint style="info" icon="lightbulb" %} **Order of attack:** negative gaps first (instant savings), then contradictions (pick a direction), then consolidations (avoid duplicating winners). Single-campaign tools miss the large share of leaks that only show up when you pivot on the campaign-to-ASIN map. {% endhint %} *** ### Diagnostics tab "Conflict detection, waste control and structural diagnostics." Diagnostics is **read-only** - it explains *why* a campaign drifted so you can fix the structure before scaling budget. Apply the actual fix from the linked Recommendation card so the change is logged and reversible. | Panel | What it detects | | ------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | **Duplicate Keywords** | The same keyword active in multiple campaigns - bidding against yourself drives up CPC and wastes budget. Scan, then consolidate to the highest-converting campaign | | **ASIN Cannibalization** | Campaigns where multiple products compete for the same budget | | **Budget Waste Analyzer** | Forensic waste analysis: zombie keywords, black holes, diminishing returns, budget-burn campaigns and Pareto violations | | **Keyword Conflicts** | Negative keywords blocking profitable terms, match-type cannibalization, and bid disparity across campaigns | {% hint style="info" icon="lightbulb" %} **Diagnose before bidding.** Structural problems cap how much Autopilot can improve. Fix duplicates and conflicts first, then watch ACoS settle within 7-14 days. These scans run hourly and refresh after each Amazon report sync (\~04:00 UTC). {% endhint %} *** ### Intelligence tab "Pattern mining, momentum and share capture." These are strategic, mostly read-monthly modules - they need roughly 28+ days of data to be statistically reliable, so treat earlier runs as directional. | Module | What it tells you | | ------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------- | | **Search Term N-Gram Analysis** | Breaks search terms into 1-, 2- and 3-word patterns and flags which combinations convert versus waste | | **Performance Trends** | Period-over-period comparison with a momentum score | | **Share of Voice** | Estimated impression share per keyword - the closer to 100%, the less headroom to scale | | **TACoS Tracker** | Total ACoS (ad spend over organic + ad sales) - tracks ad dependency and the organic/paid split | | **ASIN Performance Matrix** | Cross-campaign, per-ASIN P\&L with a classification of Star / Strong / Average / Underperformer | | **Keyword Gap Finder** | Converting search terms not yet targeted as manual keywords | | **Brand vs Generic Spend** | What share of spend defends your own brand versus hunts new customers (needs brand terms set in PPC Settings → Enterprise Features) | | **Seasonality Insights** | Day-of-week patterns, weekly cycles and monthly drift in your daily sales | | **Day-of-Week Bid Multipliers** | The per-weekday bid multiplier the autopilot applies, computed from the last 8 weeks of conversion data | {% hint style="info" icon="lightbulb" %} **Read this monthly, not daily.** N-gram patterns answer "what language do customers really use?"; Share of Voice answers "how much headroom is left?"; the TACoS trend answers "is growth healthy or paid-only?" TACoS rising while ACoS falls is healthy; both rising means ads are propping up flat organic sales. {% endhint %} *** ### Automation tab "Dayparting, rule engines and profit engineering." This is hands-off, advanced orchestration. Every automation has a kill-switch and a reversal window - but set sensible caps before flipping anything on. These modules carry a **PRO** badge (available on all plans during beta). | Module | What it does | | ------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | **Dayparting Intelligence** | A 24x7 hourly bid schedule - automatically adjust bids by hour and day of week based on historical conversion patterns. The **Hourly Bid Schedule** lets you set per-hour modifiers per campaign; the worker re-applies them every hour as Amazon placement adjustments | | **AI Budget Rules Engine** | Custom IF/THEN rules, for example "IF ACoS > 40% for 7 days THEN reduce bid by 20%," evaluated hourly against live data | | **Competitor Benchmark Intelligence** | A SWOT view comparing your PPC metrics against industry and **Category Benchmarks** (weekly peer percentiles for your Amazon browse categories) | | **Profit Waterfall Analysis** | True per-campaign P\&L: Revenue → COGS → FBA Fees → Referral Fees → Ad Spend → Net Profit | | **Search Term Clusters** | Groups search terms into semantic clusters so you can scale profitable themes and negate wasteful ones in bulk | {% hint style="info" icon="circle-info" %} **Mode is set on the Overview tab.** The Autopilot **mode and guardrails** that govern these rules live in the governance card on the [Overview tab](#overview-tab), not here. Dayparting needs 21+ days of hourly data to be reliable, and the Profit Waterfall uses your COGS / FBA / referral inputs (defaults are category medians, not your real costs). {% endhint %} *** ## Where Settings Live The AI Optimizer does not have a single standalone "Configuration" panel. Its controls are split across three places: | Setting | Where it lives | | -------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------- | | **Analysis Window** (7-90 days) and Profile/Marketplace scope | The cockpit hero, next to Run Full Analysis | | **Autopilot mode, Optimization Goal, Target ACoS/ROAS, Max Bid Cap, Min Spend Threshold** | The **governance card** at the bottom of the **Overview tab** | | **Run schedule / cadence, brand terms, enterprise features and other account-level options** | The [**PPC Settings**](/ppc-management-beta/ppc-manager-overview/ppc-settings.md) page | {% hint style="info" %} **Set the Min Spend Threshold sensibly.** It filters out statistical noise by requiring a keyword to accumulate a minimum cost before the optimizer will touch it. Too low and you risk acting on 2-3 clicks of data; the default is a safe starting point. {% endhint %} ***
⚠️ Common Mistakes to Avoid | Mistake | Why It Hurts | How to Fix | | --------------------------------------------------------- | ---------------------------------------------------------------------- | ----------------------------------------------------------------- | | Never reviewing AI suggestions (leaving hundreds pending) | The AI cannot learn your preferences; suggestions become stale | Set a daily or weekly cadence; approve or reject every suggestion | | Raising bids on a leaky funnel | Duplicates, conflicts and zombie keywords cap how much the AI can help | Clear the Diagnostics and Coverage Audit tabs first, then scale | | Ignoring anomaly alerts | A spend surge or CTR drop can waste hundreds in hours | Respond to Critical / High anomalies within 24 hours | | Approving everything without reading the reasoning | Teaches the AI that all suggestions are good, even thin ones | Read the confidence and reasoning; treat sub-80% rows with care | | Enabling Full Autopilot without setting caps | Bids and budgets can swing before you notice | Set Max Bid Cap and Min Spend Threshold before switching modes | | Expecting results in 48 hours | The AI needs at least 1-2 cycles and enough history to be meaningful | Give it at least 14 days of data and 2-3 cycles before judging |
## 🔧 Troubleshooting ### AI Not Generating Recommendations | Symptom | Likely Cause | Solution | | --------------------------------------- | --------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------ | | "Insufficient data" or empty tabs | Less than \~14 days of campaign data, or no analysis has been run | Press Run Full Analysis; wait for more data to accumulate and ensure sync is running | | Zero pending actions | Autopilot mode is Suggestions Only and you have not reviewed the queue, or the account is genuinely clean | Open the Recommendations tab and work the queue | | Recommendations only for some campaigns | Other campaigns have too few clicks to clear the Min Spend Threshold | Lower the threshold or wait for more traffic | | Nothing applies on its own | Trust score is under 60, keeping the AI in suggest-only safe-mode | Accept good suggestions to raise the score, or review your Autopilot mode | ### Unexpected AI Behavior | Symptom | Likely Cause | Solution | | ------------------------------------------- | --------------------------------------- | ----------------------------------------------------------------- | | AI suggesting bids above your comfort level | Max Bid Cap is too high | Lower the Max Bid Cap in the governance card | | AI pausing keywords you want to keep | Keywords sit far above your Target ACoS | Raise your Target ACoS, or reject the suggestion so the AI learns | | Projected impact seems too optimistic | Projections assume stable competition | Treat projections as directional estimates, not guarantees | | Savings and upside totals look off | Your account spans multiple currencies | Select a single marketplace, or use the per-marketplace breakdown | *** ## ❓ FAQ
How long does it take for the AI Optimizer to show results? Most sellers see meaningful impact within 2-4 weeks. The AI needs at least 14 days of historical data to generate reliable suggestions, and the Intelligence modules want roughly 28+ days. The first 1-2 weeks are a learning phase where the AI calibrates to your campaigns.
Can the AI Optimizer make things worse? The guardrails (Max Bid Cap, Min Spend Threshold, the 7-day rollback window, sandbox mode) let you prevent destructive changes. In Suggestions Only and Semi-Auto modes, nothing changes without your approval. In Full Autopilot only high-confidence changes apply, and every one is logged and reversible. That said, no optimization tool is perfect - monitor the Optimization Impact panel regularly.
Does the AI learn from my approve/reject decisions? Yes. Every approve or reject decision feeds back into the AI, and it also raises or lowers your trust score, which governs how much autonomy the Autopilot earns. Consistent feedback accelerates this.
How is the "strategy" set now? Rather than a separate strategy picker, the current cockpit expresses strategy through the **Optimization Goal** in the governance card (Target ACoS, Target ROAS, Maximize Profit, Maximize Revenue, Maximize Impressions) together with your Target ACoS/ROAS and Autopilot mode. Pick the goal that matches your priority - visibility, efficiency or absolute profit - and the AI adjusts its bid and keyword behavior accordingly.
Can I undo a change the AI made? Yes. Every applied change is recorded in the [Activity Log](/ppc-management-beta/ppc-manager-overview/ppc-activity-log.md) and is reversible within the 7-day rollback window. Note that reverting does not undo the market impact - if a bid was raised for 3 days before reverting, the impressions and spend from those days are not refundable.
How does keyword harvesting work? The AI monitors search terms in your auto (and broad/phrase) campaigns that are converting well. From the Recommendations tab it suggests graduating those terms into their own exact-match keywords in your manual campaigns, giving you bid control over proven performers. The Coverage Audit tab additionally warns when a harvest candidate already exists elsewhere, so you consolidate instead of duplicating.
Is there a limit to how many recommendations the AI generates per cycle? There is no hard limit, but the AI prioritizes by expected impact and only surfaces recommendations at 80%+ confidence. A typical account with 20 campaigns and 500 keywords might see 10-50 suggestions per cycle; larger accounts see more.
*** ## Use Case Scenarios ### Scenario 1: Managing 500 Keywords Across 3 EU Marketplaces You sell kitchen accessories on Amazon DE, FR and IT with 500 active keywords across 12 campaigns. **Challenge:** Reviewing bids for 500 keywords across 3 markets by hand is a full-time job. **Solution:** {% stepper %} {% step %} ### Set the goal In the governance card, set **Optimization Goal** to Target ACoS (a solid all-round default) with a realistic Target ACoS. {% endstep %} {% step %} ### 14-day window Set the **Analysis Window** to 14 days and run a full analysis per marketplace. {% endstep %} {% step %} ### Full Autopilot with caps Switch to **Full Autopilot** only after setting a sensible **Max Bid Cap** and **Min Spend Threshold**. {% endstep %} {% step %} ### Watch the impact Check **Optimization Impact** and the **Wins** tab weekly to confirm ACoS is trending the right way. {% endstep %} {% step %} ### Coverage Audit Run the **Coverage Audit** to catch cross-marketplace negative gaps and contradictions. {% endstep %} {% endstepper %} **Expected Outcome:** The AI handles the 500-keyword bid management across all three markets. You spend minutes per week reviewing Wins and anomalies instead of hours adjusting bids. ### Scenario 2: Launching a New Product with Zero History You are launching in the US with one auto campaign and one manual campaign of 30 seed keywords. **Challenge:** No historical data means the AI has little to analyze. You need traffic fast to build keyword data and organic ranking. **Solution:** {% stepper %} {% step %} ### Goal for visibility Set the **Optimization Goal** to Maximize Impressions (or Maximize Revenue) with a higher Target ACoS - you are investing in visibility, not profit yet. {% endstep %} {% step %} ### 7-day window Set the **Analysis Window** to 7 days to react quickly to early data. {% endstep %} {% step %} ### Suggestions Only Keep **Suggestions Only** for the first two weeks so you see every suggestion while data is thin. {% endstep %} {% step %} ### Harvest early Watch the Recommendations tab's **Keyword Harvesting** to graduate converting auto-campaign terms into exact match. {% endstep %} {% endstepper %} **Expected Outcome:** Within 30 days the AI has harvested new keywords from your auto campaign, identified top performers, and flagged unprofitable seed keywords. You then switch the goal toward Target ACoS for the next phase. ### Scenario 3: Agency Onboarding a New Client You are onboarding a client running Amazon PPC for a year with no optimization tooling. Their ACoS is 45% against a 25% target. **Challenge:** Accumulated inefficiency - wasteful keywords, outdated bids, no negative strategy. You need results within 30 days. **Solution:** {% stepper %} {% step %} ### Sync data Connect the client's account and let 14 days of data sync. {% endstep %} {% step %} ### Goal for efficiency Set the **Optimization Goal** to Target ACoS (or Maximize Profit) - the priority is cutting waste. {% endstep %} {% step %} ### Semi-Auto (Approve) Use **Semi-Auto (Approve)** so every change queues in the Approval Center for your sign-off. {% endstep %} {% step %} ### Clear structure first Work the **Diagnostics** and **Coverage Audit** tabs, then the Recommendations tab's negatives and bid decreases. {% endstep %} {% step %} ### Report the wins Present the **Wins** tab and Optimization Impact to the client weekly. {% endstep %} {% endstepper %} **Expected Outcome:** Within 30 days ACoS drops from 45% toward the high-20s/low-30s through waste elimination, with a clean audit trail in the Wins tab to show the client. *** ## ➡️ What's Next? {% content-ref url="/pages/xUaJFWbcCTCya95L64xQ" %} [PPC Approval Center](/ppc-management-beta/ppc-manager-overview/ppc-approval-center.md) {% endcontent-ref %} {% content-ref url="/pages/pQTsyjXdDCQAMg0Eueka" %} [PPC Analytics](/ppc-management-beta/ppc-manager-overview/ppc-analytics.md) {% endcontent-ref %}