Rootly announced it has acquired ThinkHive, an AI agent reliability platform.
The move advances Rootly's broader goal of bringing reliability engineering to LLM workloads.
ThinkHive traces every step an agent takes and evaluates whether it did its job, not just whether it returned a response. It correlates multiple signals, including metrics, traces, and evaluations, to catch the two failures that matter most in production, hallucination and drift. It clusters those failures into patterns instead of a wall of individual complaints, proposes fixes, and validates them with shadow testing before they reach a user.
For Rootly, ThinkHive serves a strategic dual purpose. First, it solves a critical customer blind spot, as companies put AI agents into production, they create new incidents that legacy monitoring simply cannot see. Second, it fortifies Rootly’s own technology. Because Rootly relies on AI during high-stakes incident response, it now leverages ThinkHive's rigorous framework, including groundedness scoring, hallucination detection, and shadow testing, to guarantee its agents are production-grade-tested before they ever touch a real incident.
"When an agent gives a wrong answer at scale, that is an incident, and most teams cannot see it yet," said JJ Tang, co-founder and CEO of Rootly. "ThinkHive is the team that worked out how to. We are not going to put AI into incident response and ask anyone to trust it on faith, ourselves included. That is the engineering bar we want to set for this category, and this is exactly the team we want setting it."
"Most teams think an automated eval pipeline means they have solved quality," said Nour Alkhatib, co-founder of ThinkHive. "Using AI to judge AI is like asking the same student to mark their own exam. Real reliability means tracing what actually happened and catching the failure a score hides. Rootly already brings that discipline to incident response, and already believes AI should assist the people responsible for reliability rather than replace them. That is why it is the right home for what we built."
For Rootly customers, the result is a stronger agentic AI capabilities. The same rigor ThinkHive brings to understanding agent behavior is what makes Rootly's agents better at the work that matters most during an incident: pinpointing root cause and proposing fixes a responder can act on with confidence. It deepens Rootly's proactive work too, scoring the risk of a code change against a service's incident history and live telemetry before that change ever pages someone, and determining probable incidents based on incident history and similarities. With ThinkHive's evaluation engine underneath them, Rootly's agents reason from evidence, and they do it earlier in the lifecycle.
The Latest
For decades, enterprise networks were designed around a simple assumption: work happened inside the office. Applications lived in centralized data centers, employees connected through internal infrastructure, and security focused on protecting the perimeter that surrounded everything ... But the way organizations operate today bears little resemblance to that environment. Cloud platforms host critical applications, employees connect from homes and airports as often as they do from offices, and partners collaborate through shared systems that exist far beyond corporate walls. In short, the corporate network no longer resembles the environment it was designed to protect ...
As an analyst who researches how IT organizations design, build, and operate their networks, I find that network data is a constant source of pain. Network teams struggle with data quality, fragmentation, authority, access, and trust. And these issues undermine everything they try to do. Here are the numbers: Only 45% of network teams are completely confident in the accuracy of their network source of truth, which documents the intent of their network ...
The 2026 Global Data Center Survey from Uptime Institute reveals an industry navigating workforce constraints, escalating outage expenses, even as rising costs remain the top concern for management teams ...
The next observability gap may not be in the code. It may be under the rack. That sounds strange until you think about how AI incidents actually feel in the middle of an investigation ... The application dashboard may be accurate. It may also be stopping at the wrong boundary. AI systems depend on software, but they also depend on a dense physical stack: racks, power paths, thermal margin, maintenance activity and, in many environments, liquid cooling. Those physical dependencies can change slowly before they look like a software incident ...
Certificate expiration is the rare outage you can see coming. Every TLS certificate carries the date it stops working, so the moment it will begin breaking connections is knowable in advance. That's what makes an expired certificate such a frustrating way to lose a service. What's changing now is how often that date comes around ...
Enterprises operate different combinations of workloads across cloud, hybrid and multicloud environments. For business-critical workloads, teams need to consider monitoring and observability early so they can detect health issues, investigate failures, and understand operational impact. Organizations place workloads on cloud platforms based on a combination of technical requirements, economics, existing dependencies, organizational standards, and business priorities. Their monitoring priorities therefore depend on what they operate and where those systems run. Those priorities will not look the same for every organization ...
Top-performing businesses prioritize data-driven decision making, enabling leaders to move from intuition and gut feel towards evidence-based judgment. But that judgment is only sound when the data underpinning decisions is accurate. With incident management, data accuracy is particularly important. Long-term revenue, customer trust, and operational stability depend on high-quality data that enables teams to quickly identify and address the root cause of major incidents. Against this backdrop, governance becomes a critical endeavor to ensure the right data drives the right action ...
In MEAN TIME TO INSIGHT Episode 26, Shamus McGillicuddy, VP of Research, Network Infrastructure and Operations, at EMA discusses network compliance ...
Most production autonomous agents do not run in a vacuum. They run inside cloud infrastructure: virtual machines, containers, pods, managed clusters or private servers. That is where most operations teams start monitoring. Is the VM alive? Is the container running? Did the pod restart? Is memory stable? Is CPU too high? Did the health check pass? Those signals are useful. They tell you whether the shell around the agent is alive. They do not tell you whether the agent inside is actually operational ...
Enterprise IT environments have never been more observable ... Yet many organizations still grapple with outages, lengthy incident resolution cycles, and increasing complexity. Most teams do not suffer from a shortage of data. They struggle to determine what deserves attention and what action to take next ... Enterprise IT operations must move beyond monitoring and visibility. The next stage of maturity is decision operations, an approach that helps teams make faster, better-informed decisions ...