Agent overview

VibeAds' agent is the always-on optimization engine that watches every campaign and makes the small adjustments an agency would make for you. On Pro it surfaces recommendations you approve. On Max with hands-free on, it acts on its own with safety gates.

What it is

Not a single chatbot. A pipeline of cron-driven background jobs and event-driven webhooks running across several Edge Functions:

  • agent-sync: pulls 30 days of metrics from Google Ads every 6 hours. Detects external changes (you edited something in Google Ads UI). Reverse-syncs bidding strategy and budget mismatches.
  • agent-aggregate: runs nightly. Computes category benchmarks, funnel patterns, fleet-wide diagnostic rule success rates.
  • agent-optimize: runs every 12 hours. 35+ diagnostic rules across keywords, bids, geo, device, schedule, ad copy, landing pages, bidding strategy.
  • agent-reason: Claude Opus 4.6 reasoning loop for complex multi-step diagnoses. Credit-gated to Pro and Max.
  • measure-outcomes: every 6 hours, verifies that previously-executed agent changes actually helped. Auto-rolls back changes that hurt metrics.

What runs on what cadence

JobCadenceTier
Metrics syncEvery 6 hoursAll paid
GA4 syncDaily 05:00 UTCAll paid
Funnel syncDaily 05:30 UTCAll paid
Benchmarks aggregationNightly 03:00 UTCAll paid
Diagnose + recommend + executeEvery 12 hoursAll paid
Outcome measurementEvery 6 hours (T+24h/T+7d/T+14d)All paid
Weekly digest emailSunday 13:00 UTCMax

Blast-radius gating

Every recommendation is classified by what it would cost in dollars if the agent is wrong, not by what it would gain. Four classes:

  • Surgical: less than $50 over 7 days if wrong. Examples: add a negative keyword, ±15% keyword bid, exclude a low-spend location. Auto-execute on Max.
  • Meaningful: $50 to $500 over 14 days if wrong. Examples: device bid ±20%, budget shift 5 to 20%, promote revenue conversion. Auto-execute on Max only when the rule has fleet-wide success rate over 80% across at least 10 samples in your category.
  • Large: $500+ over 14 days if wrong. Examples: pause a campaign, budget shift over 20%, target ROAS change over 25%. Human approval always.
  • Legally dicey: Restricted categories (locksmith, garage door), unverified accounts, conversion action changes. Human approval always, regardless of tier.

Decision framework

Pre-Phase-38, hands-free gated on the agent's confidence ("low risk" recommendations auto-fired). That assumed users could evaluate the recommendations.

We changed it because a plumber cannot evaluate "+20% mobile bid modifier." The only thing that justifies interrupting them is a decision whose downside exceeds the cost of ignoring it. Blast-radius gates on user downside, not agent confidence.

Read it like this: surgical = pocket change, meaningful = a weekly Google Ads budget, large = a month of Google Ads spend, legally dicey = compliance + brand risk regardless of dollar amount.

The trust loop

Every state transition is observable and rolls back if needed:

  1. Diagnose → identify issue from snapshot data.
  2. Classify → assign blast radius + rule success rate.
  3. Decide → auto-execute or queue for human approval.
  4. Execute → mutate Google Ads, capture pre-execution state.
  5. Notify → in-app notification + (on Max) weekly digest.
  6. Measure → check metrics at T+24h, T+7d, T+14d windows.
  7. Verdict → improved, unchanged, or worsened.
  8. Rollback on worsened → restore pre-execution state, notify user.
  9. Aggregate → feed verdict into fleet-wide rule success rate.