Resolve AI, the production-operations startup backed by Greylock and Lightspeed Venture Partners, today announced a sweeping expansion of its platform that introduces always-on background agents, a redesigned investigation architecture, and a shared workspace where engineers and AI agents collaborate in real time on live incidents.
The centerpiece of the release is a new multi-agent investigation system developed by Resolve AI’s in-house research lab. Instead of deploying a single AI agent to diagnose a production failure — analogous to a lone engineer pulling an on-call shift — the platform now dispatches a coordinated team of specialized agents that pursue multiple hypotheses in parallel, independently verify each other’s conclusions, and construct complete causal chains from root cause to symptom. The company says the architecture delivers more than a twofold improvement in root cause accuracy on its internal evaluation benchmarks compared to earlier versions of its platform.
“Think of a single agent being on call, the way a human would be,” Resolve AI CEO and co-founder Spiros Xanthos told VentureBeat in an exclusive interview ahead of the announcement. “We now have a team of agents that all work together, almost like a team of humans debugging an issue, and that has improved quality by 2x.”
The announcement arrives at a moment of acute tension in the software industry. AI-powered code generation has exploded in adoption, enabling engineering teams to ship dramatically more software than they could two years ago. But keeping that software running in production — debugging it when it breaks, monitoring it after deployment, auditing its health — remains overwhelmingly manual. For a company that raised a $125 million Series A at a $1 billion valuation earlier this year, Resolve AI is making a direct bet that the operational side of the software lifecycle is the next major frontier for AI investment.
Any accuracy claim from a startup warrants scrutiny, and Xanthos was candid about both the scale and limitations of the evaluation. The 2x figure comes from internal benchmarks, not a third-party audit, though the evaluation set was built to mirror the complexity that Resolve AI’s enterprise customers encounter daily.
“These are very hard, complex evals that we built over time to represent real-world examples,” Xanthos explained. “This is not customer data, but these evals represent difficult cases similar to what we’ve seen at some of the largest tech companies we work with.” He described the set as comprising hundreds of cases that reflect the kinds of production failures encountered at companies like Coinbase, Salesforce, DoorDash, and Zscaler — all named Resolve AI customers.
The practical impact of that accuracy gain is significant. Resolve AI’s agents now act as first responders for every on-call alert, typically triaging within five minutes before a human engineer even becomes involved. In previous public disclosures, the company has cited DoorDash reducing time to root cause by up to 87 percent. When asked to contextualize that figure, Xanthos described the typical baseline.
“When something goes wrong, it might take five to 10 minutes for a human to even get their laptop and connect,” he said. “The typical MTTR is in the tens of minutes, sometimes hours, depending on severity. So an improvement of 80-plus percent — four to five times faster — is actually huge. It’s something we’ve never achieved before with AI, tools, data, or observability.”
One of the core challenges in applying large language models to high-stakes production environments is their tendency to generate plausible-sounding but incorrect answers — a failure mode that, in the context of a live outage, could send an engineering team chasing the wrong fix while a service stays down.
Xanthos acknowledged this directly. “This is a very common issue with models out of the box,” he said. “They always try to give you an answer, and if they don’t have enough evidence, they’ll give you the best possible answer — which is likely to be wrong.”
Resolve AI’s countermeasure is a system of layered verification among its agents. Each agent investigating a hypothesis must cite every piece of evidence it relies on and present that evidence to another agent for independent review. The investigating agent must construct the full causal chain — from root cause to symptom — and peer agents actively attempt to disprove the theory by identifying gaps in the logic.
“Often, agents actually disprove those theories because they find gaps,” Xanthos said. “There are many layers of defense and agentic checks that allow Resolve to be very accurate and not mislead.”
Equally important, he said, is the system’s willingness to say it does not know. “The bar to actually saying ‘I have the answer’ is very high. In those cases, it will say, ‘This is the evidence I found. Here are three or four paths you can take from here, but I wasn’t able to fully prove that this is the problem.’ A system like this that operates in production cannot be a black box.” In domains where wrong answers carry operational consequences, calibrated uncertainty can be more valuable than confident outputs. For an AI system integrated into an incident-response workflow, confidently pointing engineers in the wrong direction during a customer-facing outage could compound the very harm it was designed to prevent.
Beyond incident response, Resolve AI is introducing a new class of background agents designed to handle the continuous, often invisible operational work that engineering teams are expected to perform but struggle to sustain at scale.
These agents run on schedules or wake automatically in response to events — a new deployment, a fired alert, a merged pull request — and accumulate institutional knowledge from every investigation and human interaction over time. When an engineer opens the Resolve AI interface, agents have already been working: pre-investigating priority issues, monitoring deployments, auditing alert hygiene, flagging configuration drift, and surfacing cost anomalies.
Xanthos drew a distinction between background agents and the incident-response agents that have been Resolve AI’s primary offering. “You can now have these agents run in the background at all times — not only when a human asks an agent to debug a problem or when an alert fires,” he said. “A lot of our customers are now monitoring changes that land in production before they cause an issue. There’s an agent that monitors those all the time.”
He described these background agents as “general-purpose SRE agents that are available to every developer,” capable of handling tasks that range from monitoring infrastructure changes that might increase cloud costs to performing post-incident follow-up work like generating code fixes based on incident learnings. The concept addresses a structural problem in software operations: the daily tasks required to keep production systems healthy — monitoring deployments, investigating alerts, tracking changes across complex environments — are critical but reactive and manual. Engineering organizations know this work needs to happen, but it competes for attention with feature development. Automated agents that perform this work continuously could shift teams from reactive firefighting to proactive operational management.
The third major component of the release is what the company calls a shared investigation surface — a workspace where engineers and AI agents work from the same live evidence during an active incident. Reports update dynamically as investigations evolve. Every finding is inspectable. Engineers can explore side investigations without interrupting the primary workflow. Source queries are pullable and modifiable in place, evidence is embedded directly into the workspace, and remediation actions can be triggered from the same interface without switching tools.
“Think of it as an interface to all the production tools, but also an interface where humans and agents can collaborate with each other — or agents with agents,” Xanthos said. “That’s what gradually leads to more trust and more automation, because you work with the agent, you teach it, you see the results.”
The company is also making its platform available as a REST API and an MCP (Model Context Protocol) server, enabling engineering teams to integrate Resolve AI into broader agentic workflows and infrastructure. According to Xanthos, this is already happening in practice. “A general-purpose agent that a company has built — when it comes to debugging, that agent could invoke Resolve,” he said. “Or somebody works on their coding agent on the laptop, and Resolve shows up there as an MCP. If there is some production-related activity, the coding agent can invoke it.” The interoperability play signals that Resolve AI sees itself not as a closed system but as a specialized node in a broader ecosystem of AI agents that will increasingly hand off tasks to one another — a pattern Xanthos compared to the open architecture of the web rather than the walled-garden model of an app store.
The agentic operations space has become crowded in the past year. Datadog, PagerDuty, and major cloud providers have all announced AI-augmented operations capabilities. When asked what separates Resolve AI from these incumbents, Xanthos pointed to the depth of the company’s technical foundation.
“We’re operating at the frontier here. There’s no blueprint for how you build a system like Resolve,” he said. He noted that he and co-founder Mayank Agarwal co-created OpenTelemetry, the most widely adopted open-source project in observability, which now serves as the de facto standard for collecting metrics, logs, and traces from modern software systems.
Xanthos also highlighted the company’s recent AI Lab, led by a researcher he described as the former post-training lead for Meta’s Llama models. “He managed to combine deep expertise of production observability with AI and models, and I think that’s very unique,” Xanthos said. “I don’t believe any other company, whether it comes from an observability background or it’s a startup, has all of that together.”
The company’s structural defenses, according to Xanthos, include a full environment model that Resolve builds for each customer, a memory system that learns within the customer’s specific production environment, and its multi-agent architecture. The lab is now post-training frontier models on production-specific data — the kind of procedural knowledge that experienced engineers use to debug production issues but that does not appear in standard model training sets. This approach reflects an increasingly common pattern among AI application companies: using frontier foundation models as a base layer but investing heavily in domain-specific fine-tuning, retrieval, and agent architectures to achieve accuracy levels that general-purpose models cannot reach alone.
Resolve AI’s pricing model departs from traditional enterprise software licensing. The company sells credits that are consumed when agents perform work — an outcome-based approach that ties cost directly to value delivered.
“We’re not selling software,” Xanthos said. “The way you buy and use Resolve is by buying credits that are consumed when Resolve performs an action. It’s outcome-based. Only when Resolve troubleshoots an alert — that’s the only time that it consumes credits.”
He addressed the cost question head-on, arguing that Resolve AI is actually cheaper than the alternative of building a similar system from scratch using frontier models and MCP integrations. “If you were to take Opus or GPT-5.4 and try to build a solution like Resolve with MCPs, we measured — you actually end up consuming a lot more in tokens than what you have to pay Resolve, because our system is very optimized in terms of context, in terms of how it reads time-series data.”
As for the always-on background agents, Xanthos said their continuous nature does not inherently add to cost. “The background agent doesn’t mean it does intensive work all the time. It means that it can be there; you can give it any task you want. A lot of these tasks are triggered based on some action — an alert happens, somebody merges a PR, and you want to see if it has an impact on production.” For enterprise customers in regulated industries — the Coinbases and Zscalers of the world — data residency and security are non-negotiable. Resolve AI accommodates this with a flexible deployment model: the data plane sits wherever the customer’s existing tools already live, while the inference layer can run as a standard SaaS deployment or inside a customer-specific VPC. “We designed Resolve to work with the large enterprises where security standards are the highest,” Xanthos said. “There are many measures we take to ensure Resolve is secure, including not retaining data.”
The question of whether engineering teams will trust AI agents to take autonomous action in production — rolling back a deployment, adding capacity, generating a pull request — is one of the defining cultural challenges of this technology wave. Xanthos drew an analogy to autonomous vehicles.
“For us to allow a car to drive on its own on the street, we have to prove that it’s safer than a human. Agents in production is a very similar concept,” he said. He acknowledged that not every customer is comfortable with agents taking automated action, but described a gradient of trust that he expects to evolve rapidly.
“There is a set of actions that are relatively risk-free that most tech companies probably are comfortable having an agent take, and probably there is another set of actions for which the human has to approve,” he said. “But as quality keeps climbing the way we see at Resolve, I would say we’re going to cross the threshold this year where most of the actions will be taken by an agent automatically.”
He described the typical adoption arc: companies begin with agents providing recommendations, then a human decides whether to press the button. Over weeks or months, trust builds incrementally. “I don’t think this is a problem where we just let the agents run wild from the beginning,” Xanthos said. The incremental approach mirrors how enterprise technology adoption has always worked — from cloud migration to container orchestration, organizations move at the speed of trust, not the speed of capability.
Perhaps the most provocative argument in Resolve AI’s thesis is that the explosion of AI-generated code is actually intensifying the production-operations problem. In a recent LinkedIn post, Xanthos framed the dynamic in stark terms, arguing that engineering leaders who celebrate faster code shipping without investing in production operations are effectively having their senior engineers “subsidize velocity” through increased incident-response burden.
In his interview with VentureBeat, he returned to this theme. “Now that coding agents are producing code, we produce a lot more code that we’re less familiar with — humans are less familiar with — so you need the AI to be the defense,” he said.
This framing positions Resolve AI not merely as a productivity tool but as a necessary counterweight to the AI coding revolution. As organizations deploy more code, written by tools that their engineers may not fully understand, running against production systems those engineers did not build, the argument is that the operational complexity — and the consequences of failure — will grow proportionally. On the Stack Overflow Podcast last October, Xanthos put numbers to this claim, estimating that engineers spend upwards of 70 percent of their time maintaining and troubleshooting production systems rather than building new features. “We’re facing a new crisis where we’re building faster than we can operate,” he said in that conversation.
Resolve AI was founded in early 2024 by Xanthos and Agarwal, who first met during their PhD programs at the University of Illinois and have worked together for more than a decade. Xanthos previously co-founded Pattern Insight (acquired by VMware) and Omnition (acquired by Splunk), where the pair helped create OpenTelemetry. The company raised a $35 million seed round from Greylock in 2024, followed by the $125 million Series A led by Lightspeed at a $1 billion valuation earlier this year. Named customers include Coinbase, DoorDash, MSCI, Salesforce, MongoDB, and Zscaler.
Xanthos’s long-term vision is expansive. “Over the long run, once agent ability surpasses that of a human software engineer, the end result is a lot more technology and a lot more software,” he said. “It’s not actually fewer people working on it. It’s technology becoming cheaper, becoming more accessible, producing a lot more technology for the benefit of the world.”
That vision will take years to realize. But the more immediate promise of today’s announcement comes down to something every on-call engineer understands viscerally: the 2 a.m. page, the scramble for a laptop, the frantic search through dashboards and logs for an answer that might take minutes or might take hours. Resolve AI is betting that the next time that alert fires, a team of agents will have already investigated, verified, and documented the root cause before the engineer’s phone even lights up. For a profession that has long measured its nights by mean time to resolution, the question is no longer whether AI can help — it is whether engineers will let it.
Kore.ai on Wednesday launched what amounts to a ground-up reinvention of its core technology: the Artemis edition of its Agent Platform, a system designed to let enterprises build, govern, and optimize AI agents using AI itself — compressing what has traditionally been months of engineering work into days.
The platform arrives at a moment when every major technology vendor — from Microsoft and Salesforce to Google and ServiceNow — is racing to become the default infrastructure for enterprise AI agents. Kore.ai’s answer to that crowded field is a bet on neutrality, a proprietary intermediary language for defining agents, and a philosophy that AI, not human developers, should do most of the heavy lifting.
“We’re trying to change the paradigm about how people design, build, deploy and optimize agentic AI applications,” Raj Koneru, the company’s founder and CEO, told VentureBeat in an exclusive interview ahead of the launch. “The whole theme that we are now coming out with is you do AI with AI — you design with AI, you build with AI, you test with AI, you deploy with AI, manage with AI, and optimize with AI.”
At the technical core of the Artemis platform sits Agent Blueprint Language (ABL), a compiled, declarative language built on YAML that standardizes how AI agents, workflows, and multi-agent systems are defined, validated, and governed. Kore.ai describes it as an intermediary layer that sits between the natural-language instructions a business user might provide and the production infrastructure where agents actually run.
ABL comes with its own parser, compiler, and runtime. It supports six built-in orchestration patterns — supervisor, delegation, handoff, fan-out, escalation, and agent-to-agent federation — that govern how multiple agents coordinate on complex tasks.
Koneru framed ABL as addressing a fundamental gap in the current AI landscape. “There’s a lot of value in generating code, and that code is used by developers to build applications,” he said. “What we saw is a gap between generating code and actually running it on infrastructure — with the deployment, version management, governance, and observability that production requires.”
Because ABL artifacts are YAML-based, they can be stored in GitHub, version-controlled through CI/CD pipelines, and reviewed by both developers and business stakeholders — a design choice intended to bridge the divide between no-code platforms and traditional software engineering. “The final artifact is ABL, a YAML-based construct — you can put it in GitHub, you can version-control it,” Koneru said. “It gives business people, developers, and IT a single standard to build on.”
The second major innovation is Arch, an AI system that translates business requirements into production-ready ABL. Users provide specifications, data sources, and business rules in natural language. Arch then designs the multi-agent topology — selecting from the platform’s six orchestration patterns — generates the ABL code, produces test data, deploys the application, and monitors it in production.
Critically, Arch also handles optimization. It observes whether deployed agents are meeting their goals, identifies where and why they fall short, and automatically regenerates and redeploys refined ABL to improve performance.
“Think of it this way,” Koneru explained. “In the beginning, I wanted 50% automation for a particular use case. I’m getting 30%. Because of that cycle of optimization, it moves the needle to 50% by adjusting the application based on actual usage data.”
This closed-loop approach — design, build, test, deploy, manage, optimize — is Kore.ai’s bid to differentiate from both the no-code configuration platforms that dominated the previous era of chatbot development and the pro-code frameworks emerging from companies like Anthropic and OpenAI, which Koneru argues place too much burden on individual developers. “So that’s a paradigm shift in the way AI agents have been built up until now,” he said, “either with no code, configuration-based platforms — and we were one of them — or pro code capabilities that you get with Cloud code or a Codex or something else, which then puts the onus on the developer to build a platform for themselves.”
Perhaps the most architecturally significant element of the Artemis platform is what Kore.ai calls its Dual-Brain Architecture: two cognitive engines — one for agentic reasoning powered by large language models, the other for deterministic execution of business rules — operating in parallel through shared memory within a single runtime.
This design reflects a hard lesson Kore.ai has learned from more than a decade of deploying AI in banking, healthcare, insurance, and telecommunications. In those environments, leaving all decision-making to a language model is a non-starter.
“Enterprises are not going to completely relegate decision-making to a model,” Koneru said. He drew a sharp contrast with newer AI-native startups: “A number of the AI-native companies that have emerged recently, especially in Silicon Valley, are essentially frameworks built as a wrapper around an LLM. That means much of the decision-making is left to the model — you’re heavily reliant on it, and the model itself is the one implementing the guardrails.”
Kore.ai’s approach flips that. Guardrails — both input and output — are enforced at the platform layer, not by the model. Evaluations run inside the platform’s governance engine. Business rules can execute deterministically when precision matters, while the LLM handles conversational responses and reasoning where appropriate. In a healthcare scenario where an AI agent is processing prescription refills for millions of consumers, or in a banking environment where an agent is advising clients on portfolio management, the consequences of a hallucinated response or an improperly executed workflow are severe. Kore.ai is positioning the Dual-Brain Architecture as the engineering answer to a trust problem that has slowed enterprise AI adoption across regulated sectors.
Artemis launches initially on Microsoft Azure, integrating natively with Microsoft Foundry, Microsoft Agent 365, Entra ID, and the Microsoft Graph API. Kore.ai is a launch partner for Agent 365 and is working toward becoming a native Azure service within Azure Foundry.
The Microsoft partnership runs deep. Koneru described multiple co-build initiatives spanning the past year: agents built on Kore.ai’s platform can run on Azure Foundry using its models and infrastructure; Kore.ai’s AI for Work product integrates with Microsoft Copilot so that enterprise data and agentic workflows surface directly in the Copilot interface; and AI for Service integrates with Dynamics 365 as a joint go-to-market offering.
“There is a deep relationship,” Koneru said. “In fact, I’m at their CEO Summit, and then for the next three days.”
Stephen Boyle, CVP of Enterprise Partner Solutions at Microsoft, offered support for the partnership in the Artemis press release, noting that the platform “integrates with Microsoft Foundry and Microsoft Agent 365, giving customers a governed environment to build, deploy, and operate AI agents.”
Yet Kore.ai simultaneously pitches itself as the vendor-neutral alternative to Microsoft and its peers — a tension the company addresses head-on. “All of the vendors or tech companies that you mentioned have a legacy that they’re trying to protect,” Koneru said when asked why a CIO should choose Kore.ai over an incumbent. “There’s an inbuilt lock-in to their legacy, whether that’s a Salesforce application, ServiceNow application, Microsoft Azure cloud, or whatever.” The platform supports 175 different AI models — including those from OpenAI, Anthropic, and open-source providers — deploys across Azure, AWS, Google Cloud, and on-premises environments, connects to any data source via tool calling or MCP, and delivers across more than 40 voice and digital channels.
Kore.ai’s claims about enterprise readiness are backed by deployments that rank among the largest AI implementations in the world.
One of the largest pharmacy chains in the United States — which Koneru declined to name but described in enough detail to make identification straightforward — receives approximately 750 million calls from consumers annually. The chain signed with Kore.ai at the end of March 2025, deployed on its own infrastructure, had half of its 9,000 stores live within three months, and reached full deployment across all stores within six months.
“The speed at which they were able to build out very complex functionality — which requires understanding what the prescription is all about, being able to answer questions about them, then tying it to their backend systems to fill the prescription, refill it — all of those processes was done essentially,” Koneru said.
A second example involves the world’s second-largest investment bank, which deployed Kore.ai’s AI for Work product to 135,000 employees and contractors. The bank uses the platform to give more than 30,000 financial advisors access to proprietary research and client portfolio data through a conversational interface, with agentic workflows handling routine tasks. The deployment went from initial users to global rollout within a year. A third customer — a major semiconductor manufacturer with 35,000 employees across multiple countries and languages — deployed AI for Work starting with HR use cases like onboarding, benefits management, and performance reviews, with backend integration to Workday, and has since expanded into IT, legal, and facilities management workflows.
The Artemis launch lands in one of the most fiercely contested markets in enterprise technology. Microsoft’s Copilot Studio and Agent 365, Salesforce’s Agentforce, Google’s Vertex AI Agent Builder, and ServiceNow’s AI Agents all target the same CIO budget. Meanwhile, a wave of well-funded startups — from established players like UiPath to AI-native entrants — is flooding the market with agent-building frameworks and platforms.
Kore.ai’s competitive position rests on several pillars. The company has earned consistent recognition from major analyst firms: it has been named a Leader in the Gartner Magic Quadrant for Enterprise Conversational AI Platforms (positioned highest for Ability to Execute, according to the company), a Leader in the Forrester Wave for Cognitive Search Platforms with the highest ranking in the Strategy category, and an Emerging Leader in Gartner’s Emerging Market Quadrants for both Generative AI Engineering and GenAI Applications. Everest Group has also positioned Kore.ai as a Leader in its Agentic AI Products PEAK Matrix Assessment for 2026.
The company’s financial trajectory adds further credibility. In January 2024, Kore.ai raised $150 million in a round led by FTV Capital with participation from Nvidia, bringing total funding to approximately $223 million. TechCrunch reported at the time that the company’s annual recurring revenue exceeded $100 million, with the platform automating 450 million interactions daily. In January 2026, the company secured an additional strategic growth investment led by AllianceBernstein Private Credit Investors, with continued backing from Vistara Growth, Beedie Capital, and Sweetwater Private Equity. The company now claims more than 500 Global 2000 customers and partners, with 75% of its customer base in regulated industries and support for over 300 enterprise integrations.
The Artemis platform is available today at kore.ai, launching initially on Microsoft Azure with broader cloud availability to follow. Koneru said existing customers — many of whom built their current deployments on Kore.ai’s previous no-code platform — are planning migrations to the new architecture, while all new customers are starting on Artemis.
The portability question remains partially unresolved. While ABL itself is a YAML-based artifact that customers can store and manage in their own systems, the runtime required to execute it is not yet available as a standalone component. Koneru said a lighter version of the runtime will be made available in the future for customers who want to run ABL outside the full Kore.ai platform, but acknowledged that the initial release prioritizes the integrated enterprise experience.
For CIOs navigating an increasingly crowded and fast-moving market for enterprise AI agents, the Artemis launch poses a clear choice: bet on a hyperscaler’s native platform and accept the lock-in that comes with it, or adopt a neutral layer that promises to orchestrate and govern agents across any model, any cloud, and any vendor — but requires trust in a company that, for all its scale and analyst recognition, remains far smaller than the giants it competes against.
“If I’m going to go down the path of one hyperscaler or one SaaS company that provides an agentic platform, I’m getting locked in in some fashion or the other,” Koneru said. “We need standardization. We need a central way to build and deploy. We need a central way to govern.”
It is a bold claim from a company that has spent 12 years building the plumbing for enterprise AI while flashier names grabbed headlines. But if the next chapter of the AI revolution is defined not by which model is smartest but by which platform can be trusted to run agents safely at scale, then Kore.ai’s long apprenticeship in the unglamorous trenches of compliance, governance, and regulated industry deployment may turn out to be exactly the right résumé for the job.
Presented by Design.comGenerative AI has made design radically more accessible. A founder can now create a logo, launch a website, build social campaigns, generate presentations, and produce marketing collateral in a single afternoon — work that once r…
It’s time we started treating testing like the complex problem it is.
As AI eats the entry-level work across industries that used to train the next generation, accounting’s version of this problem is not like the others.
Using connected reporting and dynamic waterfall modeling to move funds forward requires turning insight into action.
Integration is no longer just a painful phase to complete and move past.
A small fraction of queries that are slow, expensive or cold-started will drive most of the user-facing latency that matters.
Executive personal cyber is a governance category, not an IT category. It runs adjacent to the enterprise cyber program, never nested inside it.
Even though AI leverage today is strongly associated with tokens, AI is much more than an infrastructure story.