What does the ads agent do?
We run an AI agent that helps manage Google Ads and Meta (Facebook and Instagram) Ads for the owner's own local service businesses. It does the repetitive analysis and preparation that eats an owner's evening: auditing accounts, drafting ad assets and producing reports. It never controls spend on its own.
This runs on our own businesses. It is not a client result, and we don't publish performance claims.What does an ads audit cover?
- Account structure: campaigns, ad groups and ad sets that are organised around services and locations.
- Search terms (Google): irrelevant queries that should become negative keywords.
- Targeting: locations, radius, schedules, audiences and devices that match how the business actually serves customers.
- Conversion tracking: whether calls, forms and WhatsApp clicks are measured correctly, because without this nothing else can be trusted.
- Landing pages: whether the ad promise matches the page (service, location, price).
- Wasted spend signals: campaigns or keywords spending without conversions, flagged for a decision.
- Policy issues: disapproved ads or limited assets.
What ad assets does it prepare?
Headlines and descriptions for responsive search ads, sitelinks, callouts and structured snippets on Google; primary text, headlines and creative briefs on Meta, often paired with our in-house brand visuals agent for images. Everything is drafted for review. Claims about prices, offers or guarantees must be approved by the owner before they go live.
What reporting does it produce?
A regular summary of spend, clicks, conversions and cost per conversion by campaign, with changes since the last report, plus a short list of recommended actions, each marked "needs approval" where it affects spend. Reports arrive in chat so the owner can approve or reject recommendations quickly.
Why is it built for local service businesses?
Local service businesses (taxi services, clinics, repair services, training institutes) have specific ads patterns: tight geographic targeting, call and WhatsApp conversions, seasonal demand, and small budgets where waste hurts. The agent's checks are tuned to those patterns rather than to e-commerce shopping campaigns.
What is the ads agent's stop rule?
- Alone: read account data, run audits, draft ad copy and asset ideas, prepare reports and recommendations.
- With approval: any change that affects spend (budgets, bids, new campaigns, enabling paused campaigns, new keywords), publishing new ads, and adding negative keywords in bulk.
- Hard stops: billing and payment settings, account access and user management, and claims about prices or guarantees that haven't been approved.
- Handover: recommendations arrive in chat with the data behind them and a clear approve or reject choice.
How does it work with our other agents?
Our watch routines check ads accounts on a schedule and raise alerts, for example a sudden spend spike or disapproved ads. The SEO bot team includes Google Ads and Facebook Ads bots that compare paid and organic performance, so we don't pay for clicks we'd get organically anyway.
Can you set this up for my business?
Yes, as a scoped pilot. Typically we start with an audit and weekly reporting, then add drafting of assets, with every spend change kept behind your approval. See AI agents or contact us.
What should you prepare before talking to us?
You don't need a technical brief. A useful first conversation needs only a few things, and gathering them is valuable even if you never work with us:
- The process in plain words: what triggers it, who does what, and where it usually goes wrong.
- Rough volumes: how many messages, orders, tickets or invoices per week. A one-week tally is enough.
- Your tools: WhatsApp app or API, CRM, sheets, accounting or helpdesk software, including versions or plans where you know them.
- Three real examples: typical messages or cases, plus one awkward one, with personal details removed.
- What must never happen: the mistakes that would hurt most. These become the first lines of your stop rule.
- An owner: the person who will review the workflow once it runs.
Send these on WhatsApp or by email, or run the pilot scorecard first.
How does a pilot with us work?
Every engagement follows the same four steps. Consult: you walk us through the process, the tools and where it breaks. Pick the pilot: we choose one workflow and write down its inputs, outputs, tools, stop rule and success measure. Ship: we build it into the tools you already use and test it on real cases. Review: your team checks what the agent did and what it escalated, then decides whether to tune it, expand it or stop. Read the full pilot process.