Your account, scored on demand.
Campaign Health Analyzer runs 17 rule-based diagnostic checks on a connected Google Ads account when you ask for it in chat. You get a 0–100 health score, findings grouped by severity with a next step on each, and 5–7 suggestions from the Lyra Agent — usually in under 30 seconds. Read-only — nothing in your account changes.
One account, every check, every run.
Each run is scoped to one connected Google Ads account. The analyzer reads Lyra's synced campaign, keyword and Quality Score data — no writes — and returns a structured report. These are the numbers behind one illustrative run.
Out: a health readout you can read in a minute.
Below is an illustrative readout from the run above. Overall health score, severity-banded findings count, and the individual findings — each with the affected campaign, a one-line explanation, and the next step written into its rule.
Each check is a rule , not an opinion.
The check library is rule-based, not ML. Each finding has a predicate you can read, hardcoded thresholds, and a deterministic outcome — same inputs, same findings, same severity. The Lyra Agent only enters at the suggestion layer; it never decides whether something is a finding.
Campaign shape and organisation.
A single campaign, more than 5 campaigns for the budget, no Search campaign, and no Shopping on an ecommerce account (unless a Performance Max with a product feed already covers it).
Where the money is going.
Budget concentration (one campaign holding more than 80% of the enabled daily budgets) and budget under-utilisation (less than 50% of daily budget used over 7 days).
Are clicks landing?
Low CTR (below 1% on campaigns with more than 100 impressions in the window) and CTR-improvement opportunities (between 1% and 2%).
Quality Score, broken into pieces.
Account-level QS (critical < 4.0, low < 6.0), QS spread (>40% of keywords below 5), three component checks (Ad Relevance, Expected CTR, Landing Page) at the >30% BELOW_AVERAGE threshold, plus a per-keyword quick-wins check on the top 10 affected.
Whether you can measure anything.
More than 50 clicks with zero conversions in the 7-day window. The silent break where spend continues after conversions stop reporting.
A next step on every finding.
Every finding carries the next step written into its rule. On top, the Lyra Agent reads the structured findings and writes 5–7 suggestions for the account. The Agent never invents findings; it only works from what the rules surfaced.
The honest answers about Analyzer.
Is this AI?
Detection is rule-based — same inputs, same findings, same severity. Each check is a predicate with hardcoded thresholds (e.g. "more than 50 clicks with zero conversions in 7 days"). The Lyra Agent only enters at the suggestion layer: it reads the structured findings and writes 5–7 account-level suggestions. The numbers and the severities are deterministic; only the suggestion language is generated.
How often does the run happen?
On-demand. You ask for it in chat; the analyzer returns a scored report in about 25 seconds. There's no overnight cron. If you want a sweep across multiple accounts, run it on each account in turn.
Does it modify my Google Ads account?
Never. Analyzer reads Lyra's synced copy of your account and writes nothing to Google Ads. The output is a scored report with suggestions; applying anything is a separate step you take in Lyra or in Google Ads directly.
Can I run it through the chat?
Yes — that is how it runs. analyze_campaign_health is one of the Lyra Agent's tools in AI Advisor. Ask in chat — "run a health check on basalt-dtc" — and the Agent runs it and summarises the findings.
Run the audit.
Keep the findings.
Connect your account and let Lyra run its 8 tools for 14 days. If the projected waste recovery isn't worth at least 10× the $49, don't pay. You keep every insight either way.
Read-only connect · write access opt-in per tool · GDPR compliant