AppsFlyer today announced a product release that deepens its agentic AI offering. The expanded Agent Hub and new MCP tools help marketing teams investigate and act on their AppsFlyer data. Moreover, these tools run through automated workflows built on high-quality, governed agentic AI infrastructure.
Automation now sits at the center of everyday workflows. Therefore, AppsFlyer Agent Hub sets up the architecture that AI needs to run reliably. The company designed it to empower marketers through 2027 and beyond.
Transparent decision-making appears in every workflow. As a result, teams can understand, evaluate, and trust the reasoning behind every AI recommendation. Marketers can then build their strategy on agent recommendations. For example, agents can investigate fraud spikes, spot creative fatigue, or recommend Apple Ads bid changes.
“Marketing teams are moving from manual campaign orchestration to agentic execution,” said Inna Weiner, VP Product at AppsFlyer. “With this release, AppsFlyer is giving marketers trusted, agentic tools that can analyze, recommend, and act on their data to deliver clear value for growth.”
What’s New in Agent Hub
Users can now create an agent of their own. They simply describe any marketing performance workflow. The agent then pulls data down to the event level and analyzes it. Next, it delivers insights to Slack or email on a schedule the user sets. It can also run root cause analysis and recommend the next action.
The Apple Ads Share of Voice Agent marks a first for AppsFlyer. It not only recommends but also takes action, with the user’s approval. The agent estimates the share of voice per keyword and geo. When a campaign drifts off target, it recommends a bid change. It then executes that change in Apple Ads directly from AppsFlyer. Marketers retain full control, since updates apply only upon approval. The agent is in closed beta and is available through a CSM.
New MCP Tools for Marketing Teams
Protect360 data is now available via the MCP. Marketers can access it directly from their own AI tools. For instance, they can break down fraud concentration by geo for the last 30 days. They can also find which custom validation rules drove the most blocks during a specific period.
Creative Performance Data exposes creative-level spend, reach, conversion, retention, and revenue cohorts to the AI tool. Consequently, teams can identify winning and fatiguing creatives faster. They can also build automation around those insights.
OneLink Link Creation turns a plain-language campaign description into a fully configured OneLink. However, nothing is created until the marketer approves it.
Partner Integration settings surface a partner integration’s configuration, attribution windows, postback rules, and event mappings. Any MCP client can view them. Thus, marketers and support teams can diagnose setup issues in conversation. Finally, all MCP capabilities are available in the AI assistant.
Want more marketing excellence stories? Visit MarTech News for insights, trends, and expert updates.
News Source: Businesswire.com
