The workflow before
True Interactive runs paid campaigns for clients across Google, Meta, LinkedIn and TikTok. Analysts pulled performance by hand, mostly at the campaign level, and wrote up why numbers moved themselves. Problems like an ad group dropping to zero impressions surfaced only when someone noticed, and reporting effort grew with every client the agency added.
What we built
We expanded the agency's Rivery pipelines to bring granular data, down to ad groups and keywords, from all four ad networks into Google BigQuery, with a semantic layer so every report uses the same metric definitions.
We built real-time anomaly alerts that post to Slack when a critical issue appears, such as a campaign or ad group dropping to zero impressions, so account teams act within hours instead of finding it in the next report.
We also designed generative AI narratives that draft the explanation behind each KPI shift for analysts to review, the next step for the reporting workflow.
Before and after
| Measure | Before | After |
|---|---|---|
| Reporting granularity | Campaign level | Ad group and keyword level |
| Finding a zero-impression issue | Whenever someone checked | Slack alert in real time |
| Analyst time on manual reporting | Baseline | 40% less |
| Analyst headcount per new client | Grew with each client | New clients onboarded without adding analysts at the same rate |
What's next
The next step is putting the AI-written KPI narratives into production. That moves the agency to Level 2 (Connected Intelligence): a model that reads the BigQuery data and drafts the 'why' for an analyst to approve.
