Introducing Selector
Foundry
Agentic NetOps, delivered by a team of specialized agents. They investigate the incident, act inside your guardrails, and prove the fix, resolving incidents in minutes before your users notice.
Noise reduction
Faster RCA
Fewer incidents
See it. Understand it. Act on it.
Your tools each see one part of the path. Selector sees all of it, and now acts on it.
Selector Foundry runs a smart alert to a root cause: it investigates, coordinates specialists and recommends a fix, each at 02:40, then verifies recovery while flagging that the same push is staged on 2 more routers and waits for your approval.
One data foundation for the whole stack
Diagram: Selector’s agentic runtime. Rosetta calls five agents — Loom, TicketMaster, Artist, Herald and Sculptor — and the runtime connects to all four services: Collaboration, Knowledge, Data hypervisor and Collection. Raw telemetry, network, cloud and infrastructure, and existing tools and integrations all feed the Collection Service. In this example 1,412 signals across three alert clusters resolve into one episode on edge-rtr-3, with a device reboot as the root cause.
Agentic Runtime
Connected to every service
Rosetta → Loom · Retrieve the related signals behind this incident.
Collaboration service
Insight where you work.
Link failure → BGP session flap.
Teams · ServiceNow · PagerDuty · Jira
Knowledge service
Device reboot→Link failure→BGP session flap
Data hypervisor
One shared identity.
Collection service
Any source. Any cadence.
Every alert arrives with root cause
Correlation collapses the noise into a single incident, names the probable root cause and its blast radius, and recommends the fix, ready before anyone is notified and delivered where you already work.
Meet Selector Foundry
One shared context, a team of specialized agents.
Ask anything
Ask Rosetta in plain language and get the live state of your hybrid network in one place.
- Plain language in, no query syntax to learn
- One live view across network, cloud, and infrastructure
- Rosetta routes each ask to the right agent
Product demo: in the Rosetta chat window, “Give me a report of my branch routers” is answered by the Physical Infrastructure agent. It makes three inventory calls — get_network_device_inventory twice and get_facility_opstate — and returns a Branch Routers Inventory Report: 35 branch routers monitored across 7 regional hubs (Seattle, Dallas, Chicago, New York City, Los Angeles, Miami and Denver), followed by a summary table of region, site, device name and IP address.
Catch what matters early
Selector watches continuously and surfaces the signals that matter, with the context to know why.
- Continuous detection, tuned to your own baseline
- Information arrives with root-cause context attached
- Set background agents to watch for what you choose
Product demo: in the Rosetta chat window, the question “are any of these unhealthy?” is answered with a synthetics health and reachability check across the branch routers. Most are healthy and reachable; all 5 branch routers in the Denver region are currently unreachable — Albuquerque, Billings, Colorado Springs, Wichita and Salt Lake City. Branch routers in every other region are operating normally.
Root cause in minutes
- Correlates anomalies, changes, and events into one incident
- Names the root cause and its blast radius
- Every finding opens to the evidence behind it
Product demo: in the Rosetta chat window, “show me the active incidents right now” returns the active incident list, then “deep dive the incident in ashburn” runs the Incident Analyzer on S2INC-EQ-ASH1-EDGE01. The investigation names the likely cause — a configuration change under change ticket CHG0048271, titled “Optimize BGP convergence and add monitoring”, which destabilized the control plane on EQ-ASH1-EDGE01 — then lists the 10 regional branch sites whose reachability it disrupted, the blast radius, the timeline, the evidence and six recommended remediations.
Prove it, then push
- Pinpoints the offending lines in the config
- Validates the fix against live state
- Nothing executes until you approve it
Product demo: in the Rosetta chat window, “Show me the offending lines in the config” returns the configuration changes made to EQ-ASH1-EDGE01 under change ticket CHG0048271 — five violations against the golden baseline: an hourly BGP-ROUTE-REFRESH EEM applet, BFD removed from all 10 branch interfaces, BGP timers shortened from 10 30 to 3 9, maximum-prefix limits cut from 1000 to 50, and graceful restart disabled — each shown as a configuration diff. A corrected file, EQ-ASH1-EDGE01_good_config.txt, is then attached to the second prompt, “I've fixed the config. Would this address all the issues above?”, and the analysis confirms all four checks pass and the control plane instability is resolved.
Resolve it, then prevent it
- Runs under your existing RBAC and approval gates
- Confirms recovery and updates the ticket automatically
- Build custom agents in plain language to prevent recurrence
Product demo: in the Rosetta chat window, three turns. First, “I just uploaded the config...can you re-run the analysis and tell me if we're back in a compliant state.” confirms EQ-ASH1-EDGE01 is operationally remediated after CHG0048271 — the EEM applet removed, BFD restored, BGP timers, prefix limits and graceful restart back to baseline — with the only remaining discrepancy a configuration header timestamp. Second, a request to set up an event-based config agent that watches for config diffs and notifies the team on Slack returns the registered agents and a proposed configuration for confirmation. Third, “Yes, this looks good to me. Create it.” creates the agent config-compliance-watcher, now active and monitoring future configuration changes.
Agents you own. Answers you trust.
Selector agents run on your data, in your environment, on the LLM you choose. Yours to build, version, and govern.
Grounded in evidence
Every answer starts from correlated evidence. Click any claim to see the telemetry or config diff behind it.
Your data, your model
Agents run where your data already lives, so nothing goes to an outside service. You choose the LLM.
Built and versioned by your team
Author agents, commit them to your Git, and test against past incidents before promotion. Runs under your RBAC.
Product demo: in the Rosetta chat window, “deep dive the incident in ashburn” runs the Incident Analyzer on S2INC-EQ-ASH1-EDGE01, a P2 incident on the Equinix Ashburn hub router EQ-ASH1-EDGE01. The analysis walks its evidence: the incident overview, the root cause — a configuration change under change ticket CHG0048271 titled “Optimize BGP convergence and add monitoring” — five specific configuration regressions, the blast radius across 10 branch border routers, and a revert plan. Rosetta then answers with the likely cause and the ten regional branch sites whose reachability it disrupted.
A specialist for every job
Selector Foundry contains a set of specialized agents, each one an expert in one job with its own tools and guardrails. Ask in plain language, and the right agent takes it from there.
Conversational orchestration
Rosetta
Incident investigation
Loom
Operational views
Artist
Itsm workflow
TicketMaster
Reporting
Herald
The builder
Sculptor
Your whole environment
in one live view
Selector correlates network, cloud, infrastructure, and application data into a single operational picture. Build the views your team works from, watch them update, and ask your dashboards what they show in plain English.
Every domain in one view
Network, cloud, infrastructure, and application data arrive already correlated, so one screen shows the whole operational picture.
Views built to your business
Design consoles around how your team runs, from WAN resilience to firewalls, DNS, and synthetics, with no query language required.
Ask it in plain English
Query any dashboard in natural language, and Selector returns a written summary of what it shows and what needs attention.
Selector Recognized in the 2026 Gartner® Market Guide for Agentic NetOps Software
Read Gartners latest resport on Agentic NetOps Software to understand how the market is evolving, which capabilities matter most, and why Selector is recognized as a representative vendor in this emerging market.
Real impact, real results
Selector helps global enterprises reduce MTTR, unify visibility, and build resilient systems across every network domain.
News & insights
Every network engineer carries an instinct that outsiders mistake for caution: a change in one place can travel. Reroute a path, push a policy, drop an interface, and the effect
