By InfraZen Engineering · 2026-09-01 · 24 min read

Twelve AI SRE agents compared.
Which ones can you let near production?

Between December 2025 and August 2026, every major cloud, every observability incumbent and every incident-management platform shipped an AI SRE agent, and a startup selling one raised at a billion-dollar valuation. That is not a trend piece. It is a procurement problem landing on your desk this quarter, and the vendor pages are written to make twelve different products sound identical. This is the comparison we wanted when clients started asking which one to turn on: what each agent actually does as of 1 September 2026, how far up the autonomy ladder it goes, where it needs your data to live, and what the bill looks like, sourced to each vendor's own documentation.

Key takeaways

  • Twelve products, one shape. As of 1 September 2026 every agent here investigates first; whether it executes is decided by the policy you write, not by the vendor.
  • Only AWS prints a dollar price ($0.0083 per agent-second). Azure meters in Agent Units without a public rate, Datadog bills in AI Credits, PagerDuty bundles "AI Actions" into its plans, and everyone else is bundled or undisclosed.
  • Buy where your telemetry already lives. An agent can only reason over what it can query; MCP connectors keep the choice reversible.
  • The vendor ships the engine. The runbook allowlist, the approval workflow and the spend cap are still your design problem, and that is SRE work.

What is an AI SRE agent?

An AI SRE agent is software that, when an alert fires, investigates on its own: it pulls telemetry, deployment history and code, proposes a root cause and a fix, and, depending on the product and your policy, carries the fix out. In 2026 every major cloud, observability and incident-management vendor ships one. They differ in where they can act, how much you must approve, and how they are billed.

The category went from demo to product in nine months. Datadog made Bits AI SRE generally available in December 2025. New Relic announced its SRE Agent on 24 February 2026, Resolve AI closed a $125 million round at a $1 billion valuation on 4 February, Microsoft took Azure SRE Agent to GA on 10 March, AWS DevOps Agent went GA on 31 March, PagerDuty's virtual responder entered early access in the second quarter and its connectors and tools went GA on 5 August, Grafana's Assistant Investigations reached GA on 29 July, and Dynatrace announced its Autonomous SRE Agent on 27 July for August availability. Gartner's projection that agentic IT operations will reach 70% of enterprises by 2029, from under 5% in 2025, which we quoted in April, no longer looks aggressive.

What has not changed is the underlying mechanics. An agent is an LLM in a loop with tools: it reads an alert, queries the systems it has been connected to, forms a hypothesis, queries again, and either writes up what it found or proposes an action. Every product on this page is a variation on that loop. The variations that matter to a buyer are the four columns in the table below.

The autonomy ladder: where each agent stops today

We use the same four rungs we set out in the Azure SRE Agent playbook, because the vendors do not share a vocabulary and "autonomous" on a landing page can mean anything from "writes a summary" to "restarts your database".

  • Rung 0, investigate. The agent reads and reports. It touches nothing.
  • Rung 1, advised. The agent proposes a specific change; a human approves each one.
  • Rung 2, approved. The agent executes from a library of playbooks that humans wrote, reviewed and signed off in advance.
  • Rung 3, guardrailed-autonomous. The agent decides and executes within hard limits: an allowlist of action verbs, a blast-radius cap, a budget.

As of 1 September 2026, most products ship at rung 0 or rung 1 by default. The ones that go further do it through policy objects you configure: Azure's permission gate and agent hooks, Dynatrace's policy-driven approvals, PagerDuty's incident workflows. Nobody sells rung 3 as a checkbox, and you should be suspicious of anyone who does.

The comparison

AI SRE agents as of 1 September 2026, from each vendor's own documentation and announcements. Rungs are our reading of the documented default and the policy options.
Agent What it does today Ships at rung Reads your data from Pricing model Status
Azure SRE Agent (Microsoft)Investigates alerts from Azure Monitor, PagerDuty or ServiceNow, correlates with GitHub and Azure DevOps deploys, proposes mitigations, files the ticket; scheduled tasks; extensible with skills, subagents, Python tools, MCP servers and hooks1 by default; 2–3 via the permission gate and hooksAzure Monitor, Application Insights, Log Analytics, Grafana; 40+ MCP connectors incl. Datadog, New Relic, Splunk, DynatraceAzure Agent Units: always-on 4 AAU/agent-hour plus token-metered active flow; no public currency rateGA 10 Mar 2026; AAU billing since 15 Apr
AWS DevOps AgentCorrelates telemetry, code and deployment data to triage incidents; investigates AWS, Azure and on-prem applications; evaluations; custom skills; chat0–1AWS observability plus connected observability tools, runbooks, repos and CI/CD$0.0083 per agent-second; monthly credits for Business+, Enterprise and Unified Operations support plansPreview 2 Dec 2025; GA 31 Mar 2026
Gemini Cloud Assist investigations (Google Cloud)Root-cause observations and recommended next steps for Google Cloud resources; hands the investigation into a support case0Google CloudRequires a Premium Support contract or account-team accessRestricted to Premium Support since 10 Apr 2026
Datadog Bits AI SREAutonomous investigation: forms hypotheses, gathers telemetry, reasons its way to a probable root cause for the on-call engineer0–1DatadogDatadog AI Credits, usage-billed on top of the platformGA Dec 2025
New Relic SRE AgentDiagnoses before an engineer acknowledges the page; Slack and Zoom triage rooms; Intelligent RCA over the topology graph; automated post-incident reports; workflow automation0–1; workflows you defineNew RelicPlatform pricing; not itemised publiclyAnnounced 24 Feb 2026; iRCA, Performance Risks Inbox and Smart Alerts in preview as of March
Dynatrace Autonomous SRE AgentTriggers on newly detected problems, checks whether they belong to an existing investigation and enriches it; Agent Builder for your own agents; policy-driven approvals1–2 by policyDynatraceNot disclosedAnnounced 27 Jul 2026 for August availability
PagerDuty SRE AgentVirtual responder on schedules and escalation policies; automated triage via Incident Workflows; Connectors (GA, via MCP or API) to Grafana, New Relic, Datadog and others; Tools for Confluence and GitHub; team-level permissions0–1; a fully autonomous responder was announced for early access in H2 2026PagerDuty plus its connectorsRequires PagerDuty Advance (and AIOps for the Operations Console); plans bundle one-time "AI Actions"Virtual responder in early access from Q2 2026; Connectors, Tools and Incident Workflows GA 5 Aug 2026
Grafana Assistant InvestigationsPointed at an alert or incident, explores metrics, logs, traces and profiles, builds hypotheses and produces a structured report; launches from alert enrichment or webhooks0Grafana CloudNot stated on the GA noteGA 29 Jul 2026
Resolve AIAgents join the on-call rotation, triage and investigate alerts, co-work incidents to root cause, run scheduled operational work; engineers direct and take action1Your stack, via integrationsNot public$125M Series A at $1B, 4 Feb 2026
incident.io InvestigationsRoot-cause analysis over logs, code and incident context with confidence-scored hypotheses and evidence; blast-radius mapping; fixes proposed as pull requests1incident.io plus connected tools and MCPNot publicLive
Rootly AI SREInvestigates the moment an alert fires; correlates telemetry, deploys, commits, config changes and similar past incidents; confidence-scored root causes and suggested fixes1Rootly plus repositories; MCP into IDEsNot publicLive
TraversalCausal root-cause search over a dependency map of your production estate; alert triage; "Workers" that act unprompted0–1Your telemetry, at the scale it claimsNot publicOut of stealth Jun 2025 with $48M

The hyperscalers: Azure, AWS and Google

Azure SRE Agent

The most complete product on the list, and the only one whose documentation describes a full extension model. An alert from Azure Monitor, PagerDuty or ServiceNow starts an investigation; the agent correlates the symptom with a deployment from GitHub or Azure DevOps, proposes mitigations and files the ticket with the write-up prefilled. Everything it might do passes through a permission gate that evaluates each proposed tool call, so rung 1 is the default and rungs 2 and 3 are choices you make per action with hooks. It reaches beyond Azure through more than forty managed MCP connectors, Datadog, New Relic, Splunk and Dynatrace among them. The same page carries the honest caveat that it "might occasionally produce incorrect conclusions", which is the right thing for a vendor to print. Our production playbook covers the 90-day rollout.

AWS DevOps Agent

Previewed at re:Invent on 2 December 2025 and generally available since 31 March 2026, built on Amazon Bedrock AgentCore. It learns application relationships, correlates telemetry with code and deployment data, and at GA gained the ability to investigate applications running in Azure and on-premises, custom skills, and reporting. It is the only agent on this page with a published dollar price: $0.0083 per agent-second, billed per second of active work, with a two-month trial and monthly credits for Business+, Enterprise and Unified Operations support plans worth 30%, 75% and 100% of the prior month's support charge. AWS's preview customers reported up to 75% lower MTTR and 94% root-cause accuracy; those are AWS's numbers, not ours.

Gemini Cloud Assist investigations

Google's entry is a root-cause tool rather than an agent that acts: investigations produce observations about your environment, a probable cause and recommended next steps, and can hand the whole thread into a Google Cloud support case. The gating is the story. Since 10 April 2026, creating, running and editing investigations requires a Premium Support contract or access requested through your account team. If you run on Google Cloud without Premium Support, the practical options are a third-party agent reading your telemetry, or waiting.

The observability incumbents: Datadog, New Relic, Dynatrace, Grafana

Datadog Bits AI SRE

First of the incumbents to reach general availability, in December 2025. Bits investigates end to end: it forms hypotheses, gathers the telemetry that would confirm or kill each one, and reasons toward a probable root cause so the on-call engineer opens a conclusion rather than a dashboard. It is billed in Datadog's AI Credits on top of the platform subscription. Its advantage is the obvious one: if Datadog already holds your metrics, logs, traces and deploy markers, the agent starts with everything it needs.

New Relic SRE Agent

Announced at New Relic Advance on 24 February 2026 as an "always on" teammate that diagnoses incidents and recommends next steps, often before an engineer has acknowledged the page. Responders query it from Slack and Zoom triage rooms; it captures the human context, runs fact-finding, impact assessment and root-cause analysis, and writes the post-incident report. The March update added Intelligent RCA, which searches the entity topology graph and applies probabilistic causal models, plus workflow automation (generally available), and a Performance Risks Inbox and Smart Alerts in preview. Pricing is the platform's, not itemised. New Relic's own report claims 25% faster resolution for users of its AI capabilities; treat that as a vendor figure.

Dynatrace Autonomous SRE Agent

Dynatrace introduced domain-specific agents for SRE, development and security teams, with policy-driven controls and approvals, on 28 January 2026, then on 27 July announced the Autonomous SRE Agent and an Agent Builder for August availability, alongside a Cloud SRE Agent and an enhanced Dynatrace Assist available immediately. The Autonomous SRE Agent triggers itself on newly detected problems, works out whether they belong to an investigation already under way, and enriches it. The pitch is determinism: Dynatrace's causal engine supplies the facts and the agentic layer acts on them, "not guesses". Pricing is not disclosed. If Dynatrace is your observability platform this is the one to trial; if it is not, the agent's value is bounded by what Dynatrace sees.

Grafana Assistant Investigations

In preview since October 2025 and generally available in Grafana Cloud since 29 July 2026. Point it at an alert or an incident and it explores metrics, logs, traces and profiles, builds hypotheses as it learns more, and produces a structured report with findings, evidence and recommended next steps; investigations can launch automatically from alert enrichment or a webhook. It stays at rung 0: the GA note describes a report with findings, supporting evidence and recommended next steps and lists no remediation capability; humans turn the findings into incident updates or follow-up tasks. For teams on the Prometheus and Loki stack that is precisely the shape they want, and it pairs naturally with an incident platform's agent for the execution half.

The incident platforms: PagerDuty, incident.io, Rootly

PagerDuty SRE Agent

PagerDuty's Spring 2026 release put the SRE Agent on the on-call schedule itself: the virtual responder can be added to schedules and escalation policies and begins investigating the moment an incident triggers, in parallel with the humans. The May enhancements added automated triage through Incident Workflows and connectors to Grafana, New Relic, Honeycomb, Splunk, Dynatrace, Confluence and GitHub. On 5 August PagerDuty took Connectors and Tools to general availability, wiring the agent to Grafana, New Relic and Datadog through MCP or API, made Incident Workflows for the agent GA, put escalation-policy membership and Skills into early access, and added team-level permissions so administrators can scope the AI to specific teams. The documentation is clear that remediation stays with the human, and it lists the limits you will hit: only the first 2,000 characters of custom details and notes are analysed, and conversations take up to 25 files of 100 KB. A fully autonomous responder was announced for early access in the second half of 2026. Packaging: PagerDuty Advance is required, plus AIOps to use it in the Operations Console.

incident.io Investigations

incident.io's Investigations run on a production-intelligence model it calls Nexus, reasoning across telemetry, deployments, code and incident history to produce root-cause hypotheses with confidence levels and cited evidence, a blast-radius map of affected services, and, where a code fix is the answer, a pull request. It states plainly that it never takes action without you: the change happens when a human reviews and merges. A detail we like: an adversarial agent challenges the conclusions before they are shown. The customer quotes on the page are the vendor's; the one from turbopuffer's CTO, that it found in minutes what took a human 30 to 60 minutes, is the shape of benefit we see in practice.

Rootly AI SRE

Rootly's agent is built into its incident platform rather than layered on top, so it starts with service ownership, on-call schedules and incident history already loaded. It begins investigating when the alert fires, correlates live telemetry with recent deploys, commits and config changes and with similar past incidents, and proposes probable root causes with confidence scores, suggested fixes and drafted updates. Every change requires explicit human sign-off before execution. It also reaches into engineers' editors through an MCP server, which is a sensible place for a fix to land. Pricing for the AI SRE is not published separately.

The specialists: Resolve AI and Traversal

Resolve AI

The category's unicorn: a $125 million Series A at a $1 billion valuation, led by Lightspeed, announced on 4 February 2026 with Coinbase, DoorDash, MongoDB, MSCI, Salesforce and Zscaler named as customers. Its agents join the on-call rotation, triage and investigate alerts, co-work incidents to root cause and run scheduled operational work, with engineers stepping in to direct and take action. The company claims up to 5x faster MTTR and 75% higher productivity; those are its numbers. What the round tells you is that large engineering organisations are paying for a standalone agent that reads across whatever stack they have, rather than waiting for their observability vendor's.

Traversal

Traversal came out of stealth in June 2025 with $48 million and positions itself as the AI SRE for complex systems: it builds a dependency map of the production estate, which it calls a Production World Model, and runs a causal search across services to isolate root cause, at what it describes as petabyte scale. Its published customer figures include a 38% MTTR reduction at DigitalOcean and root-cause accuracy of 75% to 82% at unnamed large enterprises; again, vendor-published. It is the most explicitly "acts unprompted" product on this list, so if you trial it, the evaluation questions in the next section matter more, not less.

What does an AI SRE agent cost?

Three pricing models exist as of 1 September 2026, and most vendors publish none of them. AWS meters agent time at a published $0.0083 per agent-second. Azure meters in Agent Units, a fixed always-on charge plus token-based active flow, without a public currency rate. Datadog and PagerDuty sell credits and actions bundled onto their platforms. Everyone else prices the agent inside the platform deal, which means the answer is whatever your renewal negotiation says it is.

What the bill looks like, using only figures the vendors print.
Agent Unit The vendor's own example Cap or offset
AWS DevOps Agent$0.0083 per agent-second of active work10 investigations of 8 minutes: $39.84/month. 80 investigations + 100 chats: $343.62. 500 incidents + 40 evaluations + 30 custom agents: $2,365.502-month trial; monthly credits worth 30% / 75% / 100% of the prior month's Business+ / Enterprise / Unified Operations support charge
Azure SRE AgentAzure Agent Units: 4 AAU per agent-hour always-on, plus active flow metered per token (Claude Opus 4.6: 100 / 500 / 10 / 125 AAU per million input / output / cache-read / cache-write tokens; GPT 5.3 Codex: 35 / 280 / 3.5 / 0)Quick question about 3.8 AAU; incident investigation about 35.3 AAU; full remediation about 86.5 AAU (Opus 4.6). Always-on alone is 4 × 730 = 2,920 AAU for a full month. No public currency rate: the pricing page directs you to a sales quoteMonthly active-flow cap you set, 500 to 1,000,000 AAU; evaluation waives always-on
Datadog Bits AI SREAI Credits, usage-billedNot published as a per-investigation figureSits on top of host, APM, logs and RUM licensing
PagerDuty SRE AgentIncluded with PagerDuty Advance; plans bundle one-time "AI Actions"Professional $21 and Business $41 per user per month billed annually, with 1,000 and 5,000 AI Actions; Enterprise 20,000 AI Actions, custom price; AIOps add-on quote-onlyAI Actions are a one-time allocation, so the cap is built in
Gemini Cloud Assist investigationsPremium Support contractNo per-investigation priceGated by contract rather than metered
New Relic, Dynatrace, Grafana, Resolve AI, incident.io, Rootly, TraversalBundled or undisclosedNone publishedNegotiated at renewal

The FinOps point is that the agent's own bill is a new line item that grows with your incident count, which is exactly the month you least want a surprise. Azure's monthly AAU cap and AWS's support credits are the two mechanisms that bound it today; for everyone else, ask for the metering model in writing before the pilot. We cover the broader pattern of agents as a runtime cost in FinOps for AI.

Should you buy the agent from your cloud, your observability vendor or your incident platform?

Buy the one that already has read access to the signals your incidents are made of. An agent is only as good as what it can query, so the vendor holding your metrics, logs, traces, deploy markers and incident history starts with a structural advantage no model can overcome. Everything else, autonomy, pricing, polish, is secondary to that, and MCP connectors now make the choice reversible.

In practice that produces three honest answers. Single-cloud, native-observability shops should start with the cloud's agent: Azure SRE Agent and AWS DevOps Agent both read across clouds now, Azure through MCP and AWS by investigating Azure and on-prem applications directly, so the choice does not trap you. Teams whose telemetry lives in Datadog, New Relic, Dynatrace or Grafana Cloud should trial that vendor's agent first, because a second copy of the data is the expensive part. And teams whose incident process is the strongest asset, with real ownership data, schedules and retrospectives in PagerDuty, incident.io or Rootly, often end up with two agents and a division of labour: the incident platform's agent triages and coordinates, the observability agent investigates, and MCP is the seam between them.

The wrong answer is to buy the one with the best demo. Demos run on the vendor's data, and the vendor's data is complete.

How do you evaluate an AI SRE agent before letting it near production?

Run it at rung 0 against your own last twenty incidents and measure how often its root cause matched the one your engineers found, then check six things before you let it propose a single action: the audit trail, the permission model, the blast-radius cap, the spend cap, the data-residency exclusions, and what leaves with you if you switch it off.

  1. Audit trail per action. Every proposed and executed action logged with the agent's reasoning, routed to your own log store. Azure routes audit telemetry to your Application Insights; ask each vendor where theirs goes.
  2. Permission model. Can you require approval per action class, allowlist verbs, and block the rest? A product without this cannot be run above rung 1 safely, whatever its marketing says.
  3. Blast-radius cap. A limit expressed in your terms: n pods or n%, one region, one service, and never the database.
  4. Spend cap. A hard monthly limit on the agent's own consumption. Azure has one; AWS bounds it with credits and trial hours; for credit-based products, ask what happens at zero.
  5. Residency and exclusions. Google's investigations require Premium Support; several agents are not offered in every region or government cloud. Regulated teams should get the exclusions list in writing before the pilot.
  6. Exit. Most agents accumulate "institutional knowledge" from each investigation. Ask whether that knowledge is exportable, or whether it is the lock-in.

The rung-0 trial is the part teams skip, and it is the part that matters. Twenty past incidents, replayed, give you a precision number for the agent on your system rather than the vendor's. If it finds the real cause in fewer than half, it is a summariser, and you should pay for it as one. If it clears that bar, the 90-day rollout from our Azure playbook works for any of the twelve: advised mode on the top twenty runbooks, then three pre-approved playbooks, then a data-driven decision about rung 3 on a single allowlisted runbook.

What none of them do yet

None of the twelve sets your SLOs, writes your error-budget policy or decides what reliability your users actually need; they optimise inside a definition of "good" that a human still has to supply. All of them are bounded by alert quality: an agent that starts from a noisy page starts from noise, and 44% of 2025's outages began with an alert someone had learned to ignore. Microsoft's documentation says the agent "might occasionally produce incorrect conclusions or propose mitigations that don't apply to your environment"; assume the same of the other eleven, because the mechanism is the same. The knowledge every vendor promises to accumulate is also the stickiest form of lock-in yet invented for operations tooling. And none of them carries the pager's accountability. When the agent is wrong at 3 a.m., the name on the incident is still a person's.

Our take

In 2026 the model stopped being the differentiator. Every vendor on this page can investigate an alert competently when it holds the data, and by next year the ones that cannot will have bought a startup that can. The differentiator is now the policy your team writes around the agent: which runbooks it may touch, at what blast radius, under what budget, with what evidence required before it acts. That is SRE work, not procurement, and it is the same work whether the logo on the agent is Microsoft's or a startup's.

Our recommendation to clients this quarter is unglamorous. Pick the agent that already reads your telemetry. Run it at rung 0 for thirty days and measure it. Promote it to advised mode on the runbooks you already trust. Write the allowlist and the spend cap before anyone asks for rung 2. If your team does not have the time to do that policy work, that is the engagement to buy, before the agent, not after; it is what SRE consulting looks like in 2026, and it is why the honest answer to "is AI replacing SRE?" is still no.


Related: Azure SRE Agent: the production playbook · The alert fatigue trap · SRE consulting services · How to choose an SRE consultancy · Uptime & SLA calculator

Turning one on this quarter?

A 30-minute agent-readiness review: we look at your alert quality, your runbooks and your approval model and tell you honestly which rung you can run today.

Back to Blog Book the Review
IZ
InfraZen Engineering
DevOps, SRE & Cloud Consulting · Bangalore, India

Written by the InfraZen engineering team, consultants who run production DevOps, SRE and cloud platforms for fintech, SaaS and enterprise clients across the US, UK, Middle East and APAC. Posts are reviewed for technical accuracy by Bangalore-based SREs before publication.

About InfraZen → Talk to an engineer → LinkedIn →

Frequently asked questions

What is the best AI SRE agent in 2026?

There is no single best one. The agent that already has read access to the telemetry, deploy history and incident record your outages are made of will out-investigate a smarter model that has to guess. Azure SRE Agent and AWS DevOps Agent are the strongest choices inside their own clouds; Datadog, New Relic, Dynatrace and Grafana win where they already hold the observability data; PagerDuty, incident.io and Rootly win where the incident process lives. The comparison table on this page puts all twelve on one ladder.

Can AI SRE agents fix incidents without a human?

Most of them ship at the advised rung: they investigate, propose a specific change and wait for a human to approve it. Azure SRE Agent can execute under a permission gate you configure, Dynatrace runs on policy-driven approvals, and PagerDuty has said a fully autonomous responder mode would reach early access in the second half of 2026. Treat autonomous execution as a per-runbook decision with an allowlist and a blast-radius cap, not a product setting.

How much does Azure SRE Agent cost?

Azure SRE Agent is metered in Azure Agent Units: a fixed always-on charge of 4 AAU per agent-hour for as long as the agent exists, plus an active-flow charge computed from the LLM tokens each task consumes. Microsoft's own examples put a quick question at about 3.8 AAU, an incident investigation at about 35 AAU and a full remediation at about 87 AAU on Claude Opus 4.6. The public pricing page does not print a currency rate per AAU; you get that from an Azure sales quote, and you can cap monthly active-flow spend in the agent settings.

How much does AWS DevOps Agent cost?

AWS DevOps Agent is billed per second of agent time at $0.0083 per agent-second for investigations, evaluations and on-demand tasks. AWS's published examples work out to $39.84 a month for ten eight-minute investigations, $343.62 for eighty investigations plus a hundred chats, and $2,365.50 for an enterprise pattern of five hundred incidents, forty evaluations and thirty custom agents. New customers get a two-month trial, and Business+, Enterprise and Unified Operations support plans receive monthly credits worth 30%, 75% and 100% of the prior month's support charge.

Do AI SRE agents replace SREs?

No. They replace the first twenty minutes of an investigation and a good share of the toil around it. What remains is the work the agents cannot do: deciding what reliability your users actually need, writing the SLOs and error-budget policy, choosing which runbooks an agent may execute and with what blast radius, and owning the outcome when the agent is wrong. The role shifts toward supervisor: policy, guardrails and the exceptions.