Agentic Examples

​

Diagnose a traffic drop

“Affiliate 142 had significantly fewer clicks yesterday compared to the day before. Can you figure out what happened?”

1. Calls run_performance_report with dimensions=date, filters=affiliate:142, from the day before yesterday and to yesterday, which returns one row per day (or dimensions=affiliate with comparison=previous_period and sort_by=revenue_delta for a single ranked delta, since comparison mode refuses a call without sort_by; comparison mode cannot be combined with a date dimension)
2. Calls get_affiliate with include=activity to check portal login recency and API usage
3. Calls get_offer with include=caps for the affiliate’s top offer to check whether a daily click cap is at its limit (current against limit, dated by usage_as_of)
4. Summarizes the findings: volume drop confirmed, daily click cap reached (current equals limit as of the usage snapshot date), suggests raising the cap or splitting traffic across offers

​

Partner health check

“Give me a health summary for my top 5 affiliates by revenue this month. Flag anyone with declining performance or low portal activity.”

1. Calls run_performance_report with dimensions=affiliate, date range = current month, comparison=previous_period (the equal-length window just before the range; pass compare_from/compare_to for the whole of last month), sort_by=revenue, page_size=5 — one call returns the top 5 affiliates by revenue, each metric carrying { current, prior, delta, pct_change } vs. the prior window
2. For each affiliate, calls get_affiliate with include=activity to fetch last login date, login frequency, and API call volume
3. Returns a table: affiliate name, revenue.current vs. revenue.prior, revenue.pct_change, last login date — flagging any with a revenue decline over 20% (revenue.pct_change < -20) or no login in 14+ days

​

Compare a specific set of offers

“Compare clicks, conversions, and revenue for offers 12, 45, and 78 this month.”

1. Calls run_performance_report once with dimensions=offer and filters=offer:12|45|78 — the pipe-separated values match all three offers in a single query
2. Returns a per-offer table of clicks, conversions, and revenue

​

Investigate a disputed conversion

“Advertiser says conversion a1b2c3d4e5f6a7b8c9d0e1f2a3b4c5d6 is fraudulent. Can you pull the full picture?”

1. Calls get_entity with type="conversion", id=a1b2c3d4e5f6a7b8c9d0e1f2a3b4c5d6 — retrieves payout, affiliate, sub parameters, adv parameters, geo, device, order ID, and the originating transaction ID
2. Calls get_entity with type="transaction" and the transaction ID from step 1 — pulls the whole chain in one call: the originating click (IP, device, referrer, timestamp, unique flag), sibling conversions with their attribution_method, pixel-fire logs, and any on-hold conversions
3. Calls search_activity with type="conversion" filtered to the same affiliate and order ID to check for duplicate conversions on the same order
4. Returns a consolidated timeline: click at 09:14 UTC from IP 203.x.x.x (US, Chrome/iOS), conversion fired 4 minutes later, no duplicate order IDs found, no is_scrub flag on the conversion — suggests legitimate attribution

​

Payout audit for a period

“Summarize total payouts by affiliate for March 2026, and flag anyone whose payout exceeded $10,000.”

1. Calls run_performance_report with dimensions=affiliate, date range = March 2026, sorted by payout descending
2. Flags affiliates where payout > 10000 (the agent can also pass metric_filters="payout>10000" to the report)
3. For each flagged affiliate, calls get_affiliate to retrieve their name and account manager, and list_affiliates for their tier
4. Returns a ranked table with affiliate name, total payout, account manager, and a flag indicator — ready to paste into a finance report

​

Offer readiness check

“Is offer 88 ready to launch? Check caps, targeting, and whether any affiliates are set up to run it.”

1. Calls get_offer with include=caps,targeting,payout,affiliates for offer 88
2. Checks: at least one payout event in payout, global click cap is set, at least one country is targeted, and, for a require_approval or private offer, at least one entry in affiliates (for a public offer that list holds only blocked partners, so count active partners with count_entities type="affiliate" filters={"status":"active"} and subtract the blocked total)
3. Calls get_affiliate on the first approved affiliate with include=activity to confirm they’re an active partner
4. Returns a readiness checklist: payout configured ✓, targeting set to US/CA ✓, 3 approved affiliates ✓, primary affiliate last active 2 days ago ✓ — offer is ready to activate

​

Full trace: diagnose a blocked click

“Transaction abc123def456abc123def456abc123de is showing error code 1004 for affiliate 142. What happened?”

{
  "type": "click",
  "id": "abc123def456abc123def456abc123de"
}

{
  "transaction_id": "abc123def456abc123def456abc123de",
  "timestamp": "2026-05-20 14:23:11",
  "offer_id": 88,
  "offer_name": "Spring Sale — US",
  "affiliate_id": 142,
  "affiliate_name": "MediaPartner Inc.",
  "error_code": 1004,
  "error_message": "The affiliate was not approved to run the offer",
  "is_unique": false,
  "country": "US"
}

{
  "type": "click_error_code",
  "id": "1004"
}

{
  "offer_id": 88,
  "affiliate_id": 142,
  "include": "affiliate,targeting"
}

{
  "offer_id": 88,
  "name": "Spring Sale — US",
  "status": "active",
  "visibility": "require_approval",
  "affiliate": {
    "approval_status": "pending"
  },
  "targeting": {
    "countries": [
      { "code": "US", "name": "United States", "type": "include" },
      { "code": "CA", "name": "Canada", "type": "include" }
    ]
  }
}