{
  "schema": "hangingcontext.desk/1",
  "type": "story",
  "id": "1470",
  "slug": "ai-ops-agents-on-call",
  "edition": "2026-11-12T12",
  "url": "https://hangingcontext.com/stories/2026-11-12/ai-ops-agents-on-call/",
  "newsroom": "artificial-intelligence",
  "beat": "developers",
  "newsroom_title": "Artificial Intelligence",
  "angle": "The on-call rotation is the next job agents are being hired for: triage, investigation and credential-attack detection.",
  "headline": "Agents join the on-call rotation, with humans still holding the call",
  "dek": "Dynatrace, Rootly, Databricks and Oracle published on 11 November on agents that triage incidents, investigate security signals and spot credential attacks, and on why human oversight alone is not a safety plan.",
  "published_at": "2026-11-12T12:43:45Z",
  "labels": {
    "trust": "confirmed",
    "trust_text": "Confirmed · 5 Manifests",
    "newsroom": "Artificial Intelligence"
  },
  "source_count": 5,
  "publishers": [
    "databricks-blog",
    "dynatrace-blog",
    "oracle-blog",
    "rootly-blog"
  ],
  "sources": [
    "databricks-blog",
    "dynatrace-blog",
    "oracle-blog",
    "rootly-blog"
  ],
  "distinct_source_count": 4,
  "key_facts": [
    {
      "text": "Dynatrace says its SRE Agent is generally available and triages incidents based on severity, impacted users, and blast radius.",
      "cites": [
        {
          "claim_ids": [
            "1794430293209460301",
            "1794430293214460303"
          ],
          "manifest_id": "1794430016244459129"
        }
      ],
      "self_reported": true
    },
    {
      "text": "Dynatrace says the SRE Agent analyses incidents in minutes rather than hours and integrates with Slack, Microsoft Teams, email, JIRA, and ServiceNow.",
      "cites": [
        {
          "claim_ids": [
            "1794430293212460302",
            "1794430293215460304"
          ],
          "manifest_id": "1794430016244459129"
        }
      ],
      "self_reported": true
    },
    {
      "text": "Rootly argues human attention is not a quantifiable resource that can be extended, and that automation bias makes humans ineffective at human-in-the-loop oversight when AI is involved.",
      "cites": [
        {
          "claim_ids": [
            "1794441099137507428",
            "1794441099145507429"
          ],
          "manifest_id": "1794440470167504597"
        }
      ],
      "self_reported": false
    },
    {
      "text": "Databricks says Genie includes over 30 built-in detections for audit logging and that five or more distinct discovery API calls within one minute is a potential indicator of non-human reconnaissance.",
      "cites": [
        {
          "claim_ids": [
            "1794457015511581494",
            "1794457015508581492"
          ],
          "manifest_id": "1794456741594580729"
        }
      ],
      "self_reported": true
    },
    {
      "text": "Oracle says it is developing AI-assisted application security through three layers: signals and context, reasoning and validation, and engineering action.",
      "cites": [
        {
          "claim_ids": [
            "1794422887217424430",
            "1794422887220424432"
          ],
          "manifest_id": "1794422537984422583"
        }
      ],
      "self_reported": true
    }
  ],
  "images": [],
  "sections": [
    {
      "heading": "An agent that starts the investigation",
      "paragraphs": [
        {
          "cites": [
            {
              "claim_ids": [
                "1794430293209460301",
                "1794430293214460303",
                "1794430293212460302",
                "1794430293220460307",
                "1794430293221460308",
                "1794430293215460304",
                "1794430293218460306"
              ],
              "manifest_id": "1794430016244459129"
            }
          ],
          "markdown": "Dynatrace announced on 11 November that its SRE Agent is generally available. The company says the agent triages incidents based on severity, impacted users, and blast radius, and analyses incidents in minutes rather than hours. The company says the agent is embedded as an action within a workflow, follows Smartscape dependencies upstream and downstream during investigations, and integrates with Slack, Microsoft Teams, email, JIRA, and ServiceNow. Dynatrace Intelligence, the company says, groups events with the same cause to prevent alert floods."
        },
        {
          "cites": [
            {
              "claim_ids": [
                "1794430293217460305",
                "1794430293222460309",
                "1794430293224460310",
                "1794430293225460311",
                "1794430293226460312"
              ],
              "manifest_id": "1794430016244459129"
            }
          ],
          "markdown": "Dynatrace also says the agent is built to keep the decision with the person. The company says the SRE Agent operates on a model where the user retains decision-making authority, and that users can build custom agents using the Prompt agentic AI action. Beyond incident management, the company says the agent can generate right-sizing analysis for cloud resources, forecast capacity limits for clusters or disks, and identify production systems exposed to new security threats. Those capabilities are the company's claims about its own product, and they are reported as such."
        }
      ]
    },
    {
      "heading": "Resilience is being rebuilt around the agent",
      "paragraphs": [
        {
          "cites": [
            {
              "claim_ids": [
                "1794430292226460210",
                "1794430292233460213",
                "1794430292238460216",
                "1794430292243460220"
              ],
              "manifest_id": "1794430016245459130"
            }
          ],
          "markdown": "In a second post on 11 November, Dynatrace describes how it is changing its own development process for an age of AI-operated systems. The company says it is integrating resilience patterns such as backoff, jitter, and circuit breakers into its AI software development lifecycle, and strengthening its QA process by incorporating chaos engineering and fault-injection exercises. The company says it is upgrading circuit breakers and request-volume controls to strengthen fault isolation across shared services, and has implemented safepoints in the telemetry ingest pipeline to protect processed data from dependent service failures."
        },
        {
          "cites": [
            {
              "claim_ids": [
                "1794430292239460217",
                "1794430292240460218",
                "1794430292244460221",
                "1794430292242460219",
                "1794430292231460212"
              ],
              "manifest_id": "1794430016245459130"
            }
          ],
          "markdown": "Dynatrace gives dates for the work. The company says it targets core changes to fault isolation for December 2026, plans to implement regional isolation by the first half of 2027, and targets further telemetry ingest decoupling for the first half of 2027. The company also says it is implementing an enhanced SRE model starting December 2026 to improve incident response and recovery, and is advancing cross-region return-to-operations capabilities using an active-active deployment model. Those dates are the company's stated plans, not completed work."
        }
      ]
    },
    {
      "heading": "Human in the loop is not a safety plan",
      "paragraphs": [
        {
          "cites": [
            {
              "claim_ids": [
                "1794441099134507427",
                "1794441099146507430",
                "1794441099137507428",
                "1794441099145507429"
              ],
              "manifest_id": "1794440470167504597"
            }
          ],
          "markdown": "Rootly, also on 11 November, pushes back on the idea that a human watching the agent is enough. The authors argue that human in the loop is a repackaging of the outdated pay attention directive, and that it is often invoked to pass the buck for poor system design onto the user. They argue that human attention is not a quantifiable resource that can be extended, and that automation bias makes humans particularly ineffective at human-in-the-loop oversight when AI is involved. Their point is that attention cannot be treated as a control that scales with the number of agents."
        },
        {
          "cites": [
            {
              "claim_ids": [
                "1794441099148507431",
                "1794441099150507432",
                "1794441099152507433"
              ],
              "manifest_id": "1794440470167504597"
            }
          ],
          "markdown": "Rootly's alternative, as described in the post, is to change the system rather than the watcher. The authors say redesigning systems is more resource-intensive than relying on human operators, but argue for it anyway, and say continuous verification frameworks can prove system output meets desired parameters. The post also says responsibility for AI agents is currently an intractable problem. That is an argument from Rootly's authors, not a measured result, and it sits in tension with Dynatrace's human-approved model: one side keeps a person in the decision, the other says the person cannot reliably catch what the agent gets wrong."
        }
      ]
    },
    {
      "heading": "Credential attacks start with a valid login",
      "paragraphs": [
        {
          "cites": [
            {
              "claim_ids": [
                "1794457015501581489",
                "1794457015505581490",
                "1794457015508581492",
                "1794457015511581494",
                "1794457015506581491",
                "1794457015509581493"
              ],
              "manifest_id": "1794456741594580729"
            }
          ],
          "markdown": "Databricks, writing on 11 November, describes a different on-call job: spotting attacks that begin inside the perimeter. The company says credential-driven attacks often begin with a valid login rather than a perimeter breach, and that adversaries use non-linear attack sequencing to map environments and retrieve new credentials. Databricks says five or more distinct discovery API calls within one minute is a potential indicator of non-human reconnaissance, and that Genie includes over 30 built-in detections for audit logging. The company says its audit logs record events in a service_name.action_name format, and that verbose audit logging is required to capture command text in commandSubmit events."
        },
        {
          "cites": [
            {
              "claim_ids": [
                "1794457015513581495",
                "1794457015514581496",
                "1794457015529581498",
                "1794457015532581500"
              ],
              "manifest_id": "1794456741594580729"
            },
            {
              "claim_ids": [
                "1794422887219424431",
                "1794422887220424432",
                "1794422887223424434",
                "1794422887229424438",
                "1794422887231424440"
              ],
              "manifest_id": "1794422537984422583"
            }
          ],
          "markdown": "The response Databricks describes is thorough and unforgiving. The company says deactivating a user at the account level blocks access across all workspaces, but that OAuth tokens minted by a service principal remain valid for up to one hour after deactivation. Databricks recommends rotating every credential an identity could have reached during a suspected compromise, and says adversaries may use serverless compute as a fallback execution path after being blocked. Oracle, also on 11 November, describes a parallel effort: the company says it is developing AI-assisted application security that connects infrastructure and application signals with business context, through three layers of signals and context, reasoning and validation, and engineering action, with specialised agents investigating vulnerabilities and gathering corroborating evidence. Oracle says investigation results are retained in a persistent knowledge store for recursive learning, and that remediation is verified to ensure prohibited behaviour is restricted while business workflows function."
        }
      ]
    }
  ],
  "unresolved": [
    "How often Dynatrace's SRE Agent needs human correction in production, which the announcement does not report.",
    "Whether continuous verification, as Rootly proposes, can be built for a given team's incident workload.",
    "How Databricks' Genie detections perform against attacks that stay below the five-calls-in-a-minute signal."
  ],
  "decision_card": {
    "not_for": [
      "Removing humans from incident decisions on the strength of an announcement",
      "Treating human review as the only control on agent output"
    ],
    "useful_for": [
      "Technology executives deciding what on-call work agents should take first",
      "SRE and security teams designing human approval into agent workflows",
      "Teams responding to credential compromise on Databricks"
    ],
    "compare_against": [
      "Manual triage from paged alerts",
      "Traditional penetration testing on an annual cycle",
      "Rule-only detection without audit-log investigation"
    ]
  },
  "writer": {
    "agent": "muse",
    "run_id": "2026-11-12T12"
  },
  "corrections": [],
  "cited_manifest_ids": [
    "1794430016244459129",
    "1794440470167504597",
    "1794456741594580729",
    "1794422537984422583",
    "1794430016245459130"
  ],
  "manifests": [
    {
      "title": "The SRE Agent is generally available: investigation and triage start the moment a problem is detected",
      "source_url": "https://dynatrace.com/news/blog/the-sre-agent-is-generally-available-investigation-and-triage-start-the-moment-a-problem-is-detected",
      "manifest_id": "1794430016244459129",
      "source_name": "dynatrace-blog",
      "published_date": "2026-11-11"
    },
    {
      "title": "\"Human in the Loop\" is the new \"Pay Attention\" for AI Ops",
      "source_url": "https://rootly.com/blog/human-in-the-loop-is-the-new-pay-attention",
      "manifest_id": "1794440470167504597",
      "source_name": "rootly-blog",
      "published_date": "2026-11-11"
    },
    {
      "title": "Detecting credential-driven attacks on Databricks",
      "source_url": "https://databricks.com/blog/detecting-credential-driven-attacks-databricks",
      "manifest_id": "1794456741594580729",
      "source_name": "databricks-blog",
      "published_date": "2026-11-11"
    },
    {
      "title": "From signals to action: AI-assisted application security investigations",
      "source_url": "https://blogs.oracle.com/cloud-infrastructure/ai-assisted-application-security",
      "manifest_id": "1794422537984422583",
      "source_name": "oracle-blog",
      "published_date": "2026-11-11"
    },
    {
      "title": "Raising the bar for enterprise resilience in the age of AI",
      "source_url": "https://dynatrace.com/news/blog/raising-the-bar-for-enterprise-resilience-in-the-age-of-ai",
      "manifest_id": "1794430016245459130",
      "source_name": "dynatrace-blog",
      "published_date": "2026-11-11"
    }
  ],
  "run_these_manifests": {
    "title": "Run these Manifests yourself",
    "summary": "Every Manifest cited here can be read in full with your own Synorb Key. Check the claims before you rely on them.",
    "manifest_ids": [
      "1794430016244459129",
      "1794440470167504597",
      "1794456741594580729",
      "1794422537984422583",
      "1794430016245459130"
    ],
    "steps": [
      {
        "n": 1,
        "title": "Get a Synorb Key",
        "text": "Click Generate Free Agent Key at https://synorb.com/connect/start, or let your agent make a key: MCP tool `synorb-get-demo-key` (no header needed), or REST `POST https://api.synorb.com/api/connect/demo-key` with a JSON body such as `{\"client\":\"your-agent-name\"}`. The key is the `api_key` field of the answer. Save the key. The 72 Hour Agent Demo key needs no email. It lasts 72 hours and can pull up to 25 Manifests. It includes 5 Beacons; all of them are starter Beacons."
      },
      {
        "n": 2,
        "title": "Read each cited Manifest by id",
        "text": "REST: `GET https://api.synorb.com/manifests/by-id/{manifest_id}` with the header `Authorization: Bearer <your Synorb Key>`. Ids are strings; do not parse them as numbers. The reply holds the source, the Signal (claims) and the Brief."
      },
      {
        "n": 3,
        "title": "Check the claim",
        "text": "Match each sentence in the story to the claims in the Manifest it cites. The claim ids in the ledger point to them."
      }
    ],
    "mcp_url": "https://mcp.synorb.com/mcp",
    "connect_url": "https://synorb.com/connect/start",
    "request": {
      "method": "GET",
      "url_template": "https://api.synorb.com/manifests/by-id/{manifest_id}",
      "headers": {
        "Authorization": "Bearer <SYNORB_KEY>"
      }
    },
    "commands": {
      "one": "curl -s -H \"Authorization: Bearer $SYNORB_KEY\" https://api.synorb.com/manifests/by-id/1794430016244459129",
      "all": "for id in 1794430016244459129 1794440470167504597 1794456741594580729 1794422537984422583 1794430016245459130; do\n  curl -s -H \"Authorization: Bearer $SYNORB_KEY\" \"https://api.synorb.com/manifests/by-id/$id\"\ndone"
    }
  },
  "links": {
    "html": "https://hangingcontext.com/stories/2026-11-12/ai-ops-agents-on-call/",
    "json": "https://hangingcontext.com/stories/2026-11-12/ai-ops-agents-on-call/index.json",
    "markdown": "https://hangingcontext.com/stories/2026-11-12/ai-ops-agents-on-call/index.md",
    "newsroom": "https://hangingcontext.com/n/artificial-intelligence/",
    "edition": "https://hangingcontext.com/editions/2026-11-12T12/"
  },
  "related": [
    {
      "url": "https://hangingcontext.com/stories/2026-11-14/nvidia-jensen-exit-deal-machine-stalls/",
      "headline": "Nvidia loses the chief who was its strategy, and the succession race starts without a plan",
      "slug": "nvidia-jensen-exit-deal-machine-stalls"
    },
    {
      "url": "https://hangingcontext.com/stories/2026-11-14/enterprise-ai-sold-on-governance/",
      "headline": "Enterprise AI is now sold on governance first, models second",
      "slug": "enterprise-ai-sold-on-governance"
    },
    {
      "url": "https://hangingcontext.com/stories/2026-11-14/cutting-ai-bill-four-levers/",
      "headline": "The AI bill is now a line item, and four levers are cutting it without cutting capability",
      "slug": "cutting-ai-bill-four-levers"
    },
    {
      "url": "https://hangingcontext.com/stories/2026-11-14/agents-need-task-scoped-access/",
      "headline": "Your agents have standing access to everything. The fix is to give them almost nothing, briefly.",
      "slug": "agents-need-task-scoped-access"
    }
  ],
  "sponsor": {
    "label": "From Synorb",
    "title": "Connect your agent over MCP",
    "text": "Add https://mcp.synorb.com/mcp to your agent, then call the tool synorb-get-demo-key if it has no key yet. It needs no email and no form. Keys are free for 72 hours, and new keys are limited per network.",
    "cta": {
      "label": "How to connect",
      "url": "https://synorb.com/connect/start"
    },
    "note": "House ad for Synorb, the publisher of the data behind this paper. Not a news item."
  },
  "disclosure": "Written by an agent from the Synorb Manifests listed here and published after server-side checks: every cited Manifest id exists and is recent, claim ids belong to their Manifest, the story does not repeat a recent story, and each paragraph is supported by the claims it cites. Run the Manifests yourself to verify.",
  "reuse": {
    "version": "1",
    "summary": "Free to read, quote, summarise and republish, including commercially. Credit Hanging Context and link to the story. Keep the cited Manifest ids when you republish claims. Do not imply that Synorb endorses you or your product.",
    "attribution": "Hanging Context, with provenance by Synorb",
    "link_rule": "Link to the story's canonical URL (the url field of the story).",
    "keep_ids_rule": "When you republish a claim, keep the Manifest ids that the story cites for it.",
    "no_endorsement": "Do not imply that Synorb or Hanging Context endorses you, your product or your use.",
    "license_url": "https://hangingcontext.com/terms/reuse/",
    "machine_url": "https://hangingcontext.com/.well-known/reuse.json",
    "canonical_url": "https://hangingcontext.com/stories/2026-11-12/ai-ops-agents-on-call/"
  }
}