Selector Foundry Brings AI Agents to Network Operations, Enabling Organizations to Build, Version, and Run on Their Own Data
Operators author agents in the platform where their telemetry is correlated, store them in their Git repository, and
Press Release Disclaimer: This is a press release distributed through the XPR Media network. It has not been independently verified by our newsroom.
Selector, a leader in AI-driven network observability, today introduced Selector Foundry, a development and runtime environment that lets network operations teams build, test, version and govern their own AI agents inside the Selector platform. Agents execute where telemetry is already collected, so no operational data is copied to an external agent service.
Selector’s platform resolves signals from network, cloud, infrastructure and application sources into a single causal picture with a named probable cause rather than a ranked list of possibilities. Until now, the work performed by operators following that correlation has remained manual: assembling evidence, opening and chasing the ticket, pulling the right teams onto a bridge and deciding on remediation, with each step increasing time to resolution. Selector Foundry agents take on that sequence, and because they consume Selector’s correlated output rather than raw logs, they begin from evidence instead of re-deriving it. Each response returned by the orchestrator agent contains a recommended action and the evidence behind it; operators still decide whether to act on it, so the response moves faster without the risks associated with full automation.
No two networks are the same, and Selector’s position is that this makes operator authorship a requirement rather than a feature. Two enterprises running identical hardware still differ in topology, vendor mix, naming conventions, maintenance windows, escalation paths and what each team considers normal. A link that flaps nightly is an incident in one environment and expected behavior in another. A vendor-authored agent has no way to know the difference, because that knowledge exists in the operations team’s runbooks and in the judgment of the engineers who have run the network for years. Selector Foundry makes that knowledge executable: the people who already know which conditions matter are the people who write the agents that act on them.
With Selector Foundry, the senior operator is the author, and the output is treated as software. Agents are defined, committed to the customer’s own Git repository, and reviewed through the team’s existing pull-request workflow. Before promotion, an agent is replayed against the customer’s own historical event data, producing a pass/fail comparison against the recorded outcome of each past incident. A failed promotion is rolled back in a single step. Agents trigger on events, on a schedule, through a REST API call, or on operator request, and execute under the RBAC and identity controls Selector already enforces.
Selector Foundry ships with six generally available agents, so teams are not starting from an empty runtime. The included agents investigate incidents from correlated evidence, open and update records in IT Service Management (ITSM) systems with root-cause context, generate decision-ready views and stakeholder reports, and operate across cloud estates, covering asset health, connectivity and spend. All six agents arrive in the same repository as customer-authored agents, and a team can run them unmodified or fork them to match its own runbooks.
“Other organizations are building agent platforms and asking customers to send their network data to it. We put the agents where the network already is, so your team builds them the way any other software gets built: they design it, review it, test it, and promote it when it’s ready. They are yours, in your repository, on your data,” said Nitin Kumar, co-founder and CEO of Selector.
About Selector
Selector delivers an AI-powered observability and network intelligence platform that unifies data, correlation, and automation across domains. By combining large language models, knowledge graphs, and causal reasoning, Selector enables teams to detect, diagnose, and resolve issues faster. Leading telecommunications providers, cloud service providers, and global enterprises rely on Selector to reduce MTTR, prevent outages, and accelerate transformation. Selector is backed by leading investors, including Ansa Capital, Atlantic Bridge Ventures, AT&T Ventures, AVP, Bell Ventures, Comcast Ventures, Hyperlink Ventures, Two Bear Capital, Sinewave Ventures, and Singtel Innov8.
View source version on businesswire.com: https://www.businesswire.com/news/home/20260922787376/en/
Media gallery
