Agent overview
VibeAds' agent is the optimization engine that checks every campaign and finds the small adjustments an agency would make for you. On Free it lists issues once a week. On Pro it runs every 12 hours and 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 5.5 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
| Job | Cadence | Tier |
|---|---|---|
| Metrics sync | Every 6 hours | All plans |
| GA4 sync | Daily 05:00 UTC | All paid |
| Funnel sync | Daily 05:30 UTC | All paid |
| Benchmarks aggregation | Nightly 03:00 UTC | All paid |
| Diagnose + recommend (Max hands-free also applies low-risk changes) | Every 12 hours | All paid |
| Outcome measurement | Every 6 hours (T+24h/T+7d/T+14d) | All paid |
| Weekly digest email | Sunday 13:00 UTC | Pro, Max |
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: block a wasted search term, a keyword bid change of up to 30%. Auto-execute on Max, unless the change touches budget, pauses or ads, which always ask.
- Meaningful: $50 to $500 over 14 days if wrong. Examples: a location bid modifier of 16 to 30%, a bidding target change of up to 25%. Auto-execute on Max only when the rule has a track record in your category: at least 8 decisive outcomes and a cautious success rate of 80% or more. Budget, bidding strategy and bidding target changes in this class still ask.
- 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, Max hands-free gated on the agent's confidence ("low risk" recommendations ran on Max without asking). 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.
The trust loop
Every state transition is observable and rolls back if needed:
- Diagnose → identify issue from snapshot data.
- Classify → assign blast radius + rule success rate.
- Decide → apply it (Max hands-free, low-risk only) or queue for your approval.
- Execute → mutate Google Ads, capture pre-execution state.
- Notify → in-app notification + (on Pro and Max) weekly digest.
- Measure → check metrics at T+24h, T+7d, T+14d windows.
- Verdict → improved, unchanged, or worsened.
- Rollback on worsened → restore pre-execution state, notify user.
- Aggregate → feed verdict into fleet-wide rule success rate.