{"id":37,"date":"2026-05-22T07:38:45","date_gmt":"2026-05-22T07:38:45","guid":{"rendered":"https:\/\/inhochoi.com\/index.php\/2026\/05\/22\/who-watches-the-ai-agents-ciscos-case-for-agentic-observability\/"},"modified":"2026-05-22T07:38:45","modified_gmt":"2026-05-22T07:38:45","slug":"who-watches-the-ai-agents-ciscos-case-for-agentic-observability","status":"publish","type":"post","link":"https:\/\/inhochoi.com\/index.php\/2026\/05\/22\/who-watches-the-ai-agents-ciscos-case-for-agentic-observability\/","title":{"rendered":"Who Watches the AI Agents? \u2014 Cisco&#8217;s Case for Agentic Observability"},"content":{"rendered":"<h2>Who Watches the AI Agents? Cisco\u2019s Case for Agentic Observability<\/h2>\n<p>The enterprise AI conversation has quietly shifted from &#8220;can we build an agent&#8221; to &#8220;can we trust the agents we\u2019ve already built.&#8221; This Cisco Live EMEA 2026 session, run by the Outshift by Cisco team, digs straight into that gap \u2014 and it\u2019s been rattling around my head since I watched it.<\/p>\n<p><iframe loading=\"lazy\" title=\"Agentic Observability and Evaluation | Cisco Live EMEA 2026\" width=\"500\" height=\"281\" src=\"https:\/\/www.youtube.com\/embed\/QN_s0ssUkcs?feature=oembed\" frameborder=\"0\" allow=\"accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share\" referrerpolicy=\"strict-origin-when-cross-origin\" allowfullscreen><\/iframe><\/p>\n<h3>From a single chatbot to an Internet of Agents<\/h3>\n<p>The premise is that enterprises aren\u2019t deploying one tidy AI assistant anymore. They\u2019re standing up multi-agent systems \u2014 what the session calls MAS \u2014 where distributed, interconnected agents hand work to each other. Cisco even has a phrase for it: the &#8220;Internet of Agents.&#8221; A single chatbot was something you could reason about. A mesh of agents calling other agents, tools, and models is a different animal, and the moment something goes wrong, &#8220;which agent, doing what, and why&#8221; becomes a genuinely hard question.<\/p>\n<h3>Why traditional observability falls short<\/h3>\n<p>If you\u2019ve run APM tooling before, you know the usual signals: requests, latency, error rates. Agentic applications break that model. The session argues you also have to track quality \u2014 did the agent actually produce a good answer? \u2014 along with cost, since tokens add up fast across a multi-agent workflow, and behavior that isn\u2019t deterministic from one run to the next. On top of raw telemetry, the team frames the real goals as explainability, evaluation, predictability, and control: four words that don\u2019t show up on a classic monitoring dashboard.<\/p>\n<h3>A new charter for &#8220;agentic APM&#8221;<\/h3>\n<p>The most concrete idea here is a proposed charter for agentic APM \u2014 application performance monitoring rebuilt for agents. That means agentic quality and cost tracking, impact assessment when an agent\u2019s behavior shifts, and anomaly detection tuned to agentic patterns rather than HTTP error spikes. The session spends real time on evaluation, too: approaches like LLM-as-a-Judge, where one model grades another\u2019s output, alongside active testing to keep agent performance honest across different deployment scenarios. That evaluation piece is what stuck with me \u2014 monitoring tells you something changed, evaluation tells you whether it actually got worse.<\/p>\n<h3>Doing it in the open<\/h3>\n<p>What makes this more than a product pitch is that Cisco is pushing it as an open standard rather than a closed feature. The work is happening in an open-source collective called Agncty, as an industry collaboration that includes Cisco and Splunk, and it\u2019s being brought to the OpenTelemetry GenAI community for standardization. The session closes with a live demo of end-to-end agentic observability built on Agncty\u2019s open-source components. For anyone who has been burned by monitoring lock-in, an interoperable standard that works across agent frameworks is the right instinct \u2014 your observability layer shouldn\u2019t depend on which vendor\u2019s agents you happened to deploy.<\/p>\n<h3>Where it fits in Cisco\u2019s AI direction<\/h3>\n<p>This lines up neatly with Cisco\u2019s broader AgenticOps story and its Splunk pairing. Cisco clearly wants to own the operational layer of enterprise AI \u2014 not just the network and infrastructure underneath the agents, but the tooling that tells you whether those agents are behaving. Observability is an unglamorous place to plant a flag, but it is a sticky one.<\/p>\n<p>My take: this is the part of the agentic AI wave that doesn\u2019t get enough airtime. Everyone is racing to ship agents, and far fewer people are asking how they\u2019ll debug, cost-control, and trust them at scale. Betting on an open standard instead of a proprietary dashboard is a smart move \u2014 though standards only matter if the rest of the industry actually shows up, so it is worth watching whether OpenTelemetry adoption follows.<\/p>\n<p><em>Source: <a href=\"https:\/\/www.youtube.com\/watch?v=QN_s0ssUkcs\">Agentic Observability and Evaluation | Cisco Live EMEA 2026<\/a> on YouTube.<\/em><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Who Watches the AI Agents? Cisco\u2019s Case for Agentic Observability The enterprise AI conversation has quietly shifted from &#8220;can we build an agent&#8221; to &#8220;can we trust the agents we\u2019ve already built.&#8221; This Cisco Live EMEA 2026 session, run by the Outshift by Cisco team, digs straight into that gap \u2014 and it\u2019s been rattling [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[5],"tags":[],"class_list":["post-37","post","type-post","status-publish","format-standard","hentry","category-networking"],"_links":{"self":[{"href":"https:\/\/inhochoi.com\/index.php\/wp-json\/wp\/v2\/posts\/37","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/inhochoi.com\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/inhochoi.com\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/inhochoi.com\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/inhochoi.com\/index.php\/wp-json\/wp\/v2\/comments?post=37"}],"version-history":[{"count":0,"href":"https:\/\/inhochoi.com\/index.php\/wp-json\/wp\/v2\/posts\/37\/revisions"}],"wp:attachment":[{"href":"https:\/\/inhochoi.com\/index.php\/wp-json\/wp\/v2\/media?parent=37"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/inhochoi.com\/index.php\/wp-json\/wp\/v2\/categories?post=37"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/inhochoi.com\/index.php\/wp-json\/wp\/v2\/tags?post=37"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}