7SIGNAL Presents at Networking Field Day 41

7SIGNAL The Air and the Endpoint are Part of the System

Watch on YouTube
Watch on Vimeo

7SIGNAL argued that the air and the endpoint belong in the network engineer’s definition of the system rather than in separate silos. The session introduced its architecture of device agents and Wi-Fi 7 sensors, the troubleshooting patterns they reveal, data collection and retention practices, and Iris, the company’s AI engine for root-cause analysis and remediation recommendations. Eric Cammuli opened the session at Networking Field Day 41 with Joe Tennant and Marko Pirinen, who founded 7SIGNAL in Helsinki in 2007.

Pirinen contrasted easy problems, such as falling beacon availability or a failed primary DNS server, with hard ones like business-hours slowdowns that require ruling out the radio before tracing the path to the application. He recommended keeping transmit power within three to five dB and stretching RRM channel changes to 12 to 24 hours. The sensor acts as a high-performance client that continuously joins the network to baseline it and catch DHCP, DNS, and RADIUS failures. The lightweight agent, running on Windows, macOS, Linux, and Android devices including Zebra scanners, uses about 1% of memory, collects scan data every minute, and runs short throughput, latency, and jitter tests for roaming, coverage, congestion, and interference analysis. Tennant said raw data is retained for 90 days in the US or EU and encrypted at rest and in transit, though customer-managed keys aren’t supported.

Tennant described Iris as a mix of statistics, procedural code, workflows, and multiple LLMs that triages issues, draws on a library of root causes, and returns next steps that can flow into a ticket. Because customers load their own service levels, Iris judges compliance against each organization’s definition of good performance. Iris is read-only by policy for now, though the team said MCP-based workflows can carry out changes and controller integrations with more vendors are coming. Cammuli argued that nearly 1,000 metrics once seemed excessive but now give AI the depth it needs, combining what the infrastructure sees with what the air and device actually experience.

Personnel: Eric Camulli, Joe Tennant, Marko Pirinen

7SIGNAL Leveraging Outside-In Vantage Points for Proactive Remediation

Watch on YouTube
Watch on Vimeo

7SIGNAL demonstrated how its platform turns minute-by-minute measurements from endpoint agents and sensors into proactive Wi-Fi remediation. The session walked through device-level spectrum and roaming analysis, a global adapter and driver performance database, experience-based signal reports, the AI-generated Iris Pulse daily report, and the Sonar endpoint for testing performance across the wide area network. Eric Camulli led the demo at Networking Field Day 41 with Marko Pirinen and Joe Tennant, starting from a dashboard that rolls nearly a thousand measurements into four scores covering Wi-Fi and network connectivity and quality.

Per-minute spectrum snapshots from Camulli’s laptop exposed an unnoticed roam onto a congested 2.4 GHz network sharing the same SSID, and roaming analysis caught a client holding on at -85 dBm while an access point overhead offered -43 dBm. Device details such as spatial streams, supported bands, and VPN state feed Iris so its recommendations match each device’s capabilities. Tennant noted that 7SIGNAL can’t see inside security agents but can rule out the network when they cause slowness. The performance lab database holds 4.7 billion samples across 776 adapter and driver combinations, grading roaming against a 99% standard and revealing fleets where one laptop model shipped with different adapters. Pirinen showed a signal distribution report based on what devices actually experienced where people work, rather than a site survey’s view of potential coverage.

The Iris Pulse report summarizes the previous day’s network health, ranks issues by priority, examines the five worst service areas, and flags offline access points, while trending beacon availability and radio attach success help catch degrading hardware. The Sonar endpoint, a Docker container deployed in customer data centers or used from 7SIGNAL’s cloud, measures throughput, packet loss, latency, and jitter across the WAN to isolate backhaul problems. The agent already tracks Wi-Fi 7 multi-link operation, driver CVE reporting is on the roadmap, and a public version of the driver database has been discussed but not committed.

Personnel: Eric Camulli, Joe Tennant, Marko Pirinen

7SIGNAL Automation to Remediation. Deep Data In. Smart Answers Out

Watch on YouTube
Watch on Vimeo

7SIGNAL showed how its EYERIS AI engine and deep endpoint telemetry connect to AI orchestration platforms through MCP and APIs to move from detection to automated remediation. Demos covered driver checks in Microsoft Copilot, Intune roaming remediations, Teams call analysis, an access point reboot through a Cisco controller using Claude, and Jira and ServiceNow ticketing. Presenting at Networking Field Day 41, Eric Camulli, joined by Marko Pirinen and Joe Tennant, argued that customers are underusing platforms such as Slack, ServiceNow, Copilot, Claude, and Cisco Cloud Control.

In Copilot, EYERIS checked one user’s wireless driver against 7SIGNAL’s database and concluded it wasn’t the newest but was performing well, so no upgrade was needed. Paired with Intune remediation scripts, Iris flagged a Windows device with 100 minutes of roaming impact over 30 days and recommended a fix suited to its operating system and band support. The MCP server is read-only, while the API adds write access, and SLA compliance is calculated on the 7SIGNAL side. A Teams call analysis through Microsoft Graph traced poor quality to 7% packet loss on a home network, ruled out Wi-Fi, and filed a detailed Jira ticket linked in Slack. In Claude, EYERIS identified a failing access point, confirmed the Cisco RRM settings were clean, rebooted the AP, documented the work, and verified recovery with 7SIGNAL metrics.

Camulli said a workflow already starts this analysis automatically when an alarm lands in Slack, with sensors acting as clients to catch outages before users call. A ServiceNow portal widget lets employees check their own connectivity before an important call and open an incident with one click, and a daily scheduled workflow files incidents on its own. The closing argument was that grounding AI tools in deep, auditable telemetry traceable to specific KPIs prevents hallucinations and shortens time to identify and resolve problems. Rather than building one interface for everyone, 7SIGNAL wants customers to combine its data with their other systems, and Camulli welcomed a delegate’s suggestion to add BLE location data for continuous, experience-based site surveys.

Personnel: Eric Camulli, Joe Tennant, Marko Pirinen