ArmorCode targets runaway AI costs with four new remediation agents

UPDATED 09:00 EDT / AUGUST 04 2026 SECURITY ArmorCode targets runaway AI costs with four new remediation agents by Duncan Riley Exposure management startup ArmorCode Inc. today used Black Hat USA 2026 in Las Vegas to detail an expansion of its agentic artificial intelligence platform, adding four planned agents and three new sources of context aimed at narrowing what security teams remediate and capping what they spend doing it. The additions extend the company’s Context Risk Graph, a data model that links security findings to asset inventory, ownership, business context, threat intelligence and remediation records. ArmorCode is feeding it network topology and reachability data, an integration with patch management systems and connections to compensating controls such as web application firewalls and endpoint detection and response tools. The point of the three feeds is to let an agent establish whether a given flaw can actually be reached, whether a patch exists for it and whether a control the organization already owns is holding the line in the meantime. ArmorCode is also expanding its attack path analysis, which correlates findings with environmental context and renders the result as attack path visualizations. “Finding vulnerabilities was never the hard part,” said Mark Lambert, chief product officer at ArmorCode. “What is challenging is that attackers can cheaply chain the findings teams deprioritized into real attack paths, while defenders find that AI without context is both wrong and expensive. The expanded ArmorCode Context Risk Graph gives AI the context to fix what actually matters and do it economically.” The four agents run on that enriched context. A Cloud Security Engineer agent weighs cloud misconfigurations against the wider environment to work out which ones carry business impact. A Vulnerability Researcher agent investigates whether a specific CVE is exploitable inside a customer’s environment and explains how. A Mitigation Engineer agent reaches into existing web application firewall rules and endpoint detection policies to contain risk while a permanent fix is built. A Patch Orchestrator agent sequences rollouts across affected systems. They join four agents ArmorCode announced in May: a remediation agent, a zero-day exposure hunting agent, a finding overview agent and a risk analyzer. Customers that want something more specific to their own processes can build agents through what ArmorCode calls the Anya harness. Cost is the second argument the company is making. Chandra Sekar, chief marketing officer at ArmorCode, framed the release as bringing financial discipline to agentic remediation, pointing to security teams under pressure to adopt AI while finance leaders watch the bill climb. Because the agents draw on findings already unified in the platform, ArmorCode argues, teams stop paying repeatedly for separate agents to analyze the same issue. The company says it processes more than 300 billion findings a year across more than 375 integrations, and that correlating security and business context isolates the roughly 3% of findings responsible for about 80% of an organization’s actual risk. All four agents were announced as planned additions. ArmorCode has not said when they will reach general availability. ArmorCode is a venture capital-backed startup that has raised $81 million since it was founded in 2020. Cheyenne Ventures led the most recent round of $16 million in March. Image: ArmorCode A message from John Furrier, co-founder of SiliconANGLE: Support our mission to keep content open and free by engaging with theCUBE community. Join theCUBE’s Alumni Trust Network, where technology leaders connect,