{"id":68156,"date":"2025-12-02T13:45:30","date_gmt":"2025-12-02T02:45:30","guid":{"rendered":"https:\/\/www.salesforce.com\/?p=68156"},"modified":"2025-12-02T13:46:22","modified_gmt":"2025-12-02T02:46:22","slug":"command-center","status":"publish","type":"post","link":"https:\/\/www.salesforce.com\/au\/blog\/command-center\/","title":{"rendered":"As AI Agent Usage Surges, Companies Need a Complete Observability Solution"},"content":{"rendered":"\n

Update: <\/strong>Agentforce Observability within Agentforce Studio has evolved since this blog post was published. Get updates in our November 2025 press release<\/a> and on this Observability page<\/a>.<\/em><\/p>\n\n\n\n

Our forward-looking statement<\/a> applies to this blog.<\/em><\/p>\n\n\n\n

Back in March, we posed a simple question: How do you know if your agent is production ready?<\/a> The post resonated with our Agentblazer community as practitioners sought to bring more predictability to agentic responses and better understand why agents behave the way they do. Now, less than three months later, we\u2019re posing a decidedly bigger question: How do you manage a burgeoning digital labour force at scale?<\/p>\n\n\n\n

If the delta between these two conversations creates a bit of whiplash, you\u2019re probably not alone. It\u2019s hard to overstate just how quickly the agentic lifecycle has evolved. Simply put, AI agents are no longer experimental. In the last 6 months, AI agent usage is up 233%, with 96% of employees reporting that AI helps them complete tasks they couldn\u2019t before, according to new Slack research. But as a new hybrid workforce begins to emerge, most agent platforms still lack the necessary tooling, governance and observability to scale beyond POCs.<\/p>\n\n\n\n

After thousands of Agentforce implementations \u2014 from Goodyear<\/a> to Finnair<\/a> \u2014 it\u2019s clear that customers need better visibility, more granular metrics, and actionable recommendations to improve the accuracy, quality, cost, and latency of their agents. To equip our customers with the tools to tackle this challenge, we\u2019re introducing deep observability within Agentforce Studio<\/a>.<\/p>\n\n\n\n

Agentforce\u00a0Observability<\/a><\/strong>, formerly called Command Centre, is a first-of-its-kind tool designed to measure AI agent activity, manage the partnership between humans and agents, and drive continuous improvement.<\/p>\n\n\n\n

Flying blind<\/strong><\/h2>\n\n\n\n

Many startups today offer agents that are easy to spin up, but difficult to optimise and scale. As we\u2019re learning together with our customers, building a great agent that can reliably and efficiently deliver results at 95% accuracy takes time and iteration. But iterating can be hard when you don\u2019t know where to start. Many customers understand that their agents need work, but struggle to define where to focus their efforts. In essence, they\u2019re flying blind. \u201cIs my agent delivering bad results because of a configuration mistake or is there something wrong with the data I\u2019m feeding it?\u201d <\/p>\n\n\n\n

Agentforce provides a range of tools to address this challenge. Customers can troubleshoot individual utterances and observe how an agent identifies topics and executes actions using the Session Trace Data Model<\/a>. They can test agent responses at scale with Testing Centre<\/a>. These tools provide powerful insights, but as organisations go from making sure their agents are production ready to managing an entire workforce of agents working alongside humans, the need for a unified observability solution spanning the breadth of the hybrid workforce becomes increasingly acute.        <\/p>\n\n\n\n

Managing your hybrid workforce<\/strong><\/h2>\n\n\n\n

Agentforce Observability is the single source of truth for your digital labour force, enabling complete visibility across all of your production AI agents. Observability rolls up all your agent activity, metrics and telemetry into a single unified dashboard, delivering a new observability layer for monitoring agent health, measuring outcomes and optimising collaboration between humans and AI.<\/p>\n\n\n\n

Going beyond basic metrics like total number of sessions, Observability provides deep insight into agent performance, with detailed analytics for error rates, escalation frequency, agent latency and much more. Users can tailor their view to their unique use cases, surfacing only the metrics that are most helpful and relevant. <\/p>\n\n\n\n

Agentforce Observability is designed to answer your most burning Agentforce questions, such as:<\/p>\n\n\n\n