AI marketing operations — multi-agent, human-approved

Ad automation that
waits for your go-ahead.

An orchestrator plans the work, specialist agents execute it, and every mutation pauses at an approval gate. Search, PMax, Demand Gen, BigQuery joins, weekly digests — across all your Google Ads, GA4, and BigQuery accounts.

No credit card required · invite your team in seconds
Features

Built for marketing ops that move fast — without breaking accounts

Ads automation

Search, PMax, Demand Gen end-to-end: create campaigns, build asset groups, bulk negatives, geo cleanup, bid-modifier experiments — all from a goal in plain English.

  • Auto-generated GAQL with v22 guardrails
  • Bid + budget micros sanity-checked before write
  • Stale-state guard re-validates state at execute time
Workflow approval

Every mutation pauses at a per-step gate. Approve in the app, by email link, or pre-approve. Reject a single step and the rest of the plan keeps running.

  • Dual channel — UI + magic-link email
  • Single-step reject = skip, not abort
  • Approver delegation + change history audit
Context management

Per-account memory, per-org cross-task memory, and recent-action history are injected into every plan. The agent remembers what it shipped yesterday.

  • Account memory: target CPA, protected campaigns, notes
  • Per-account audit log (success-only, last 30d)
  • Hard caps on prompt size keep context lean at scale
Plan history & versioning

Every run produces a versioned plan with timestamped marker, replay-able artifacts, and one-click restore to any prior version.

  • Deep-link to any plan version (?run=<id>)
  • Restore an old plan into the workspace as the new run
  • Hard-restart for any task that gets wedged
Schedules

Turn any task into a cron schedule with per-IANA timezone. Re-evaluates against live data — never proposes yesterday's actions twice.

  • Per-schedule approver email + failure alerts
  • Run-now button for ad-hoc fires
  • Last 3 fires injected as priors (bounded at 1.2 KB)
Organizations & teams

Clerk-powered orgs with admin gating. Share skills / assets cross-org with one toggle. Per-org audit, integrations, and notification prefs.

  • Admin-only org switch + create
  • Cross-org skill / asset sharing (opt-in)
  • Per-org Composio + AI-gateway keys
Skills library

Curated playbooks the orchestrator auto-picks based on your goal. Bring your own — markdown editor, instant publish, optional cross-org share.

  • Built-in: PMax, Demand Gen, GAQL best practices, BigQuery patterns
  • Author custom skills with target thresholds + decision rules
  • Auto-loaded reference skills (always-on guardrails)
BigQuery + Python sandbox

First-class BQ context picker, NUMERIC auto-coercion, and a Vercel Python sandbox for matplotlib charts, video, and stats — rendered inline.

  • Pin specific tables in the context picker
  • Charts → result.artifacts → inline in the chat
  • Top-level `return` auto-rewritten to `print(json.dumps)`
Auditable + reversible

Every action — successful or failed — lands in the audit log keyed by actor, account, and resource. Spot duplicate work before it ships.

  • Who/when/where/what for compliance review
  • Per-account filter + export
  • Approval decided-by attribution
Use cases

One agent. Many workflows.

Weekly performance review with action items

Pull last 7 days of account metrics, top 10 campaigns by cost, top 10 search terms, and flag every campaign whose CPA shifted >25% WoW — with 3 ranked action items.

Search terms → semantic negatives

Audit search terms across all selected accounts. Identify wasteful terms by semantic match ("login", "download", "alternative to X", competitor names) — not by Google's unreliable conversion column.

PMax asset-group strength audit

Count current headlines / long_headlines / descriptions / images / videos against Google's "Excellent" rating targets. Auto-generate the missing assets, upload them, link via setup_pmax_asset_group.

Bid-modifier optimization with A/B experiment

Pull 30 days of device / geo / ad_schedule data → flag wasteful segments → create a campaign_draft → propose bid_modifier deltas → convert to a 50/50 traffic-split experiment for 14 days.

Bulk MCC operations (1 manager → N children)

Exclude a country across every ENABLED campaign in every connected sub-account. dryRun=true first to see the blast radius, then approve, then run for real.

Daily KPI watchdog

ROAS<1 or CTR<3% campaigns flagged with root-cause analysis. Auto-email a Resend-rendered digest to your approver list every weekday morning.

Affiliate brand-search optimization (BigQuery-backed)

Use a BigQuery mart joining Google Ads cost with the affiliate network's backend conversions as the single source of truth — campaign-level pause/budget decisions are driven by mart ROAS, not unreliable Google Ads tracking.

Cross-account disapproval monitor

Across every selected account, find disapproved / area-of-interest-only / site-suspended ads. Email the full list to your team. Or auto-skip when there's nothing to report.

Integrations

Connect what you already use

We start with Google Ads — the rest of the Google marketing surface is on the roadmap.

Google Ads
Live
Google Analytics 4
Coming soon
Google Search Console
Coming soon
BigQuery
Coming soon
Google Sheets
Coming soon
Google Drive
Coming soon
Google Ads Manager (MCC)
Coming soon
Display & Video 360
Coming soon
Google AdSense
Coming soon
More to come

Ready to put a human-gated agent in your ad ops?

Bring an account, write a goal in plain English, and watch the orchestrator plan out the work step by step.