kentik Kentik Product Updates logo
Back to Homepage Subscribe to Updates

Kentik Product Updates

Latest features, improvements, and product updates on the Kentik Network Intelligence Platform.

Labels

  • All Posts
  • Improvement
  • Hybrid Cloud
  • Core
  • Service Provider
  • UI/UX
  • Synthetics
  • Insights & Alerting
  • DDoS
  • New feature
  • BGP Monitoring
  • MyKentik Portal
  • Agents & Binaries
  • Kentik Map
  • API
  • BETA
  • Flow
  • SNMP
  • NMS
  • AI

Jump to Month

  • October 2026
  • September 2026
  • July 2026
  • May 2026
  • April 2026
  • March 2026
  • February 2026
  • January 2026
  • December 2025
  • November 2025
  • October 2025
  • September 2025
  • August 2025
  • July 2025
  • June 2025
  • May 2025
  • April 2025
  • March 2025
  • February 2025
  • January 2025
  • December 2024
  • November 2024
  • October 2024
  • August 2024
  • July 2024
  • June 2024
  • May 2024
  • April 2024
  • March 2024
  • February 2024
  • January 2024
  • December 2023
  • November 2023
  • October 2023
  • September 2023
  • August 2023
  • July 2023
  • June 2023
  • May 2023
  • April 2023
  • March 2023
  • February 2023
  • January 2023
  • December 2022
  • November 2022
  • October 2022
  • September 2022
  • August 2022
  • July 2022
  • June 2022
  • May 2022
  • April 2022
  • March 2022
  • February 2022
  • December 2021
  • November 2021
  • October 2021
  • September 2021
  • July 2021
  • June 2021
  • May 2021
  • March 2021
  • February 2021
  • January 2021
  • December 2020
  • October 2020
  • September 2020
  • June 2020
  • February 2020
  • August 2019
  • June 2019
  • April 2019
  • March 2019
  • February 2019
  • January 2019
  • December 2018
  • November 2018
  • September 2018
  • August 2018
  • June 2018
  • May 2018
  • April 2018
  • March 2018
  • February 2018
  • January 2018
  • December 2017
  • November 2017
  • October 2017
  • July 2017
  • June 2017
  • May 2017
  • April 2017
  • March 2017
  • February 2017
  • January 2017
  • December 2016
  • November 2016
  • October 2016
  • April 2016
ImprovementService ProviderAI
3 weeks ago

AI Advisor now speaks PeeringDB

If you work in network peering and interconnection, you probably remember when we first introduced the PeeringDB integration to Kentik Portal a few years ago. That integration gave network teams easy access to up-to-date information about an Autonomous System's (AS) network footprint, peering relationships, and interconnection opportunities, directly within Kentik.

Now, we're taking that integration a step further with Kentik AI Advisor.

AI Advisor can now incorporate PeeringDB's extensive interconnection data into its AI-powered investigations and analysis, bringing valuable peering intelligence directly into the investigative process.

Let's take a closer look at what's new and what it means for you. 


PeeringDB 101

For peering and interconnection teams, PeeringDB is an essential resource for understanding where networks operate, how they interconnect, and under what conditions they're willing to exchange traffic.

This community-maintained directory provides detailed information about registered Autonomous Systems (ASNs), including:

  • Data center presence: The facilities where networks have a physical presence, helping teams identify opportunities for private network interconnects (PNIs).
  • Internet Exchange (IX) participation: The exchanges where networks are present, including their peering IP addresses, enabling teams to identify public peering opportunities and establish BGP sessions.
  • Peering policies: The requirements and conditions under which networks are willing to establish interconnection relationships.

These insights inform a wide range of strategic and operational decisions, from evaluating inbound peering requests and identifying potential PNI partners to selecting the best Internet Exchanges for localized traffic exchange. They also help teams identify shared facilities for interconnection, minimize unnecessary backhaul costs, and determine where transit providers can efficiently deliver connectivity to prospective customers.

But PeeringDB is only one piece of the interconnection puzzle.

Developing an effective peering strategy also requires understanding what's actually happening across your network. That means analyzing traffic volumes, source and destination ASNs, traffic paths, and the types of connectivity carrying that traffic, whether public peering, private interconnection, or IP transit.

Equally important is understanding your network's current state. Do you already have BGP peering sessions established with a potential partner? Which routers and interfaces are involved? These answers often require consulting monitoring systems, routing data, and device configurations alongside PeeringDB.

Traditionally, bringing these data sets together has required network teams to move between multiple tools, manually correlate information, and piece together the insights needed to make informed interconnection decisions.

That's where Kentik AI Advisor changes the equation.

Kentik brings together the critical data needed to inform peering and interconnection strategies, and AI Advisor can now put that information to work:

  1. Unified access to critical network intelligence: Kentik combines PeeringDB interconnection data, traffic telemetry enriched with connectivity classifications, and router configuration context.
  2. AI-powered, cross-domain investigations: AI Advisor can reason across these data sources, connecting interconnection opportunities with actual traffic behavior and network configuration.
  3. Investigations tailored to your network: With Custom Network Context (aka AI Advisor's claude.md) and AI Runbooks (aka AI Advisor's Claude Skills) teams can guide AI Advisor using their network-specific knowledge, operational practices, and established investigation workflows.

Here's the great news moving forward: 

  1. Kentik collects all of this information: PeeringDB, Connectivity Type-enriched Traffic telemetry, Router Configuration
  2. Kentik's AI Advisor has access to it and can reason with it
  3. You can mix and match reasoning across these datasets using the guided context you have provided in both Custom Network Context (aka AI Advisor's claude.md) and AI Runbooks (aka AI Advisor's Claude Skills)

The net result is now AI Advisor can tackle complex, multi-layer peering and interconnection questions that previously required significant manual investigation, helping network teams evaluate opportunities, optimize connectivity decisions, and turn network intelligence into action.

Let's explore how you can put AI Advisor to work as an AI-powered teammate for peering and interconnection management.

The Basics: PeeringDB Intelligence in AI Advisor

AI Advisor can now automatically tap into PeeringDB's extensive interconnection data as part of its investigations. Using context-aware triggers, AI Advisor invokes a dedicated PeeringDB sub-agent when relevant, accessing detailed information about Autonomous Systems (ASNs), Internet Exchanges (IXes), and data center facilities. It can retrieve and analyze this information independently or combine it with other data sources and tools through multi-step investigations.

Here's a look at some of what AI Advisor can do with PeeringDB data:

  • Identify shared interconnection opportunities: Find Internet Exchanges and data center facilities where any two or more ASNs have a common presence, or explore the complete IX and facility footprint of any individual ASN.
  • Discover and compare Internet Exchanges: Identify IXes in a specific city, region, or country and compare them based on attributes such as member count, open peering policies, and aggregate member port capacity. AI Advisor can also locate IXes and facilities within a specified geographic radius.
  • Explore network presence and peering policies: Identify which ASNs are present at a particular IX or facility, filtering by criteria such as peering policy, contractual requirements, and available peering IP addresses.
  • Retrieve peering connection details: Look up an ASN's ports and IP addresses at specific Internet Exchanges to support interconnection planning.
  • Access peering policies and contacts: Retrieve relevant NOC and peering contact information, traffic ratio requirements, peering policy URLs, and other published interconnection requirements.

And that's just a starting point. Whenever AI Advisor invokes the PeeringDB sub-agent, users can inspect the underlying tool calls and retrieved data through the View Details side panel, providing transparency into the information used to inform its analysis.

These capabilities are valuable even for standalone queries. Rather than switching between Kentik Portal and PeeringDB to look up network footprints, peering policies, or interconnection details, users can access that information directly through AI Advisor, keeping their investigations in one place. 

In the next sections, we'll look at combining this data with other datasets in AI Advisor to demonstrate power user use cases!


Putting AI Advisor to Work: Advanced Peering and Interconnection Use Cases

Accessing PeeringDB data through AI Advisor is valuable on its own, but the real power comes from combining that intelligence with Kentik's broader network telemetry, device configurations, and operational context.

Let's explore how AI Advisor can bring these data sources together to streamline complex peering investigations, identify interconnection opportunities, and support more informed peering decisions.

Understand Existing BGP Peering Sessions

Before evaluating new interconnection opportunities, it's important to understand the peering relationships already established across your network. For devices monitored by Kentik NMS, AI Advisor can retrieve information about existing BGP sessions to help determine whether you're already peering with a particular ASN and understand the current state of those relationships. Similar information can also be obtained through router configurations when devices are enrolled in Kentik's Config Backup capability, or by executing show commands directly on supported devices with Command Access enabled.

Combine Traffic Intelligence with PeeringDB Data

Kentik regularly synchronizes PeeringDB data, including the IP address ranges associated with Internet Exchanges. This information helps enrich customer flow telemetry with additional interconnection context, making it easier to analyze traffic based on source and destination ASNs and connectivity attributes.


Consider a common peering optimization scenario: How much IP transit traffic could you potentially shift to direct interconnection if your network established a presence at Equinix Ashburn?


With Kentik Data Explorer, experienced users can investigate this opportunity by applying filters to identify traffic currently traversing transit links that may be eligible for alternative interconnection.

But what if you don't know which filters to apply or aren't familiar with Data Explorer? Simply ask AI Advisor.

AI Advisor can bring together traffic analysis and PeeringDB intelligence to help identify potential interconnection opportunities without requiring users to manually construct the underlying queries.

Fast forward: towards an AI-powered Peering Manager

Identifying potential transit offload is only the first step. A peering manager also needs to determine which networks to approach, where interconnection makes sense, and what information is needed to initiate a peering relationship.

Continuing our Equinix Ashburn example, AI Advisor can help translate the analysis into an actionable plan, identifying prospective peering partners and providing the relevant interconnection details needed to pursue those opportunities.

This helps bridge the gap between identifying an optimization opportunity and taking the next steps toward implementing it.

Streamline Peering Request Evaluations with AI Runbooks

Now consider another routine responsibility for peering managers: evaluating inbound peering requests. When another network requests a peering relationship, the evaluation typically involves several steps:

  1. Analyze traffic: Examine traffic volumes and patterns exchanged with the requesting ASN, including inbound and outbound traffic ratios.
  2. Evaluate interconnection options: Review the requesting network's PeeringDB footprint to identify shared Internet Exchanges or data center facilities.
  3. Apply peering policies: Assess whether the request meets established requirements, such as minimum traffic thresholds, traffic ratios, and geographic criteria.
  4. Determine eligibility: Evaluate the findings against your organization's peering policies to determine whether the request should be approved.
  5. Prepare next steps: Document the decision and outline the actions required to establish a BGP peering session at an agreed-upon location.

Traditionally, this process requires peering managers to move between multiple tools, manually correlate data, and apply internal policies before reaching a decision.

With AI Advisor and AI Runbooks, much of that multi-step evaluation process can be automated.

AI Runbooks allow network teams to define repeatable investigation workflows using natural-language instructions, giving AI Advisor a structured process to follow when evaluating peering requests.

For a deeper introduction to this capability, check out our recent webinar, Transforming Network Operations with AI Advisor. To get started, simply define the steps of your peering evaluation process in an AI Runbook.

Here's an example of a basic Peering Evaluation Runbook. While it can be expanded and customized to reflect more sophisticated policies, it demonstrates how AI Advisor can orchestrate an investigation across multiple data sources.

In this example, the Runbook instructs AI Advisor to first query Kentik Data Explorer to analyze the requesting ASN's traffic profile over the past seven days. It then evaluates common Internet Exchange and facility presence using PeeringDB data and checks the findings against predefined peering requirements, including minimum traffic thresholds.

Rather than requiring a peering manager to execute each step independently, AI Advisor follows the defined workflow to build a cohesive, evidence-based evaluation.

AI Advisor can also dynamically invoke the appropriate Runbook based on the context of a user's prompt, making it possible to initiate the process with a simple natural-language request. When a Runbook is invoked, AI Advisor indicates that it's following the defined workflow, providing visibility into the steps guiding its investigation.

Build Your Own AI-Powered Peering Workflows

The peering request evaluation example is just one of many ways to put AI Advisor and AI Runbooks to work. By defining repeatable procedures tailored to your network, peering policies, and operational priorities, you can equip AI Advisor to tackle a wide range of interconnection planning and optimization tasks.

Here are two more examples of what's possible:

Optimize Interconnection to Reduce Transit Costs and Improve Performance

Create an AI Runbook that evaluates interconnection opportunities in a specific country or region to identify ways to reduce IP transit costs, localize traffic exchange, and improve network performance. For example, the Runbook could instruct AI Advisor to:

  • Analyze traffic to and from ASNs in the target geography.
  • Identify Internet Exchanges with the greatest overlap among those networks.
  • Evaluate potential data center locations based on network presence and interconnection opportunities.
  • Recommend strategic locations for expanding your network's interconnection footprint.

Audit Existing Peering Relationships to Identify Optimization Opportunities

Not all optimization opportunities require establishing new peering relationships. Sometimes, you may already have a peering session with a network but still exchange a portion of your traffic with that ASN over paid transit. An AI Runbook could help uncover these inefficiencies by:

  • Identifying top inbound and outbound ASNs reached through existing IX or PNI peering connections.
  • Analyzing the distribution of traffic exchanged with those ASNs across transit, public peering, and private interconnection.
  • Flagging networks where traffic continues to traverse transit despite an existing peering relationship.
  • Investigating the relevant prefixes and routing behavior to identify potential opportunities to shift traffic onto established peering connections.
  • Generating a documented report of findings that can be shared with peering partners to support further investigation and optimization.

These are just a few examples of how AI Advisor can help turn complex, multi-step peering investigations into repeatable, AI-powered workflows.

Now it's your turn.

Whether you're evaluating new peering partners, optimizing interconnection costs, or auditing existing relationships, AI Advisor gives you the tools to build workflows around your network's unique requirements.

What will you build with your AI-powered peering teammate?

Avatar of authorGreg Villain
ImprovementUI/UXAI
3 weeks ago

AI Advisor "Full Screen Mode" facelift

As you already know, there are two ways to interact with AI Advisor: Co-Pilot Mode where AI Advisor is docked to the current screen you are on (and has page context in memory), and the Full Screen Mode which, well... kind of speaks for itself.

Today we're giving the Full Screen Mode a bit of a facelift, so read on!


The new AI Advisor sidebar

One of the piece of feedback we've gotten is that the AI Settings that host important operational aspects to how AI Advisor operates are burried. Unlike say, collection configurations, AI Advisor settings (notably Runbooks and Custom Network Context) are meant to be living reflections of the operational reality of your network. 

They by definition are better when you create/update them as you go. Forcing users to dig into settings and break the flow from AI Advisor was bad user experience. We're changing that to make AI Advisor settings easier to access, something that compounds with the recently announced RBAC for AI Advisor. 

Here's how in a screenshot since a picture is always better than a thousand words:

The main new change is the sidebar that

  • is horizontally resizable
  • is collapsible (so you can take the full screen for your chat session)
  • that now gives direct access to AI Settings: you don't need to go through Company Settings > Kentik AI to access these settings anymore

Note: The "Recent" section of the sidebar panel is a carryover from the previous version, it lets you navigate existing sessions and load them in one click in the central panel. Pinned Chat sessions will always appear at the top of the "Recent" section of the side panel - this section 

New AI Chat Sessions History screen

When clicking on the history button, a full screen history will load into the main panel. If you do this in the middle of a AI Chat Session, you can always go back by selecting the session from the "Recent" section.

This AI Chat History screen presents a few benefits

  • presents itself in a full screen experience instead of being locked in a side bar
  • allows users to easily filter between their own AI Chat Sessions, that of their company, or those automatically-generated by other parts of Kentik Portal  (as with the AI Auto-Investigation feature to come)

What do you think ?

We like to share these minor, quality-of-life improvements with our users, and we'd love to know what your thoughts are on this new version.

- Are you Team Co-Pilot Mode or Team Full-Screen Mode ?
- Do you think this new UI is better based on how you use AI Advisor ?
- What other improvements would you like to see us bring to our AI Advisor User Experience ?

Avatar of authorGreg Villain
ImprovementAI
4 weeks ago

RBAC for AI Runbooks: another AI Safety feature

In previous posts, we've discussed how AI Advisor Runbooks help teams capture the operational expertise, knowledge, and procedures specific to their networks, enabling AI Advisor to more accurately investigate issues and guide teams toward answers.

Until now, Runbook management was tied to Kentik's legacy user levels, meaning only Admins and SuperAdmins could create and maintain Runbooks. This created an unnecessary barrier to adoption for a very useful feature as the people who know your network best or operate it most hands-on aren't necessarily the administrators of the tool. 

That changes today. With role-based access control (RBAC) for AI Runbooks, organizations can give more team members the ability to contribute their expertise without granting them broader administrative privileges.

But expanding access also requires maintaining control over how Runbooks are managed. Because Runbooks influence how AI Advisor investigates issues and responds to questions, changes to their content can affect the answers users receive. It's important that those changes are authorized, transparent, and auditable so users can trust the knowledge guiding AI Advisor's behavior.

This reflects a broader principle behind our approach to AI: trust is essential to adoption. Organizations need the flexibility to put AI capabilities in the hands of more people while maintaining appropriate governance over the knowledge and instructions those capabilities rely on.

RBAC builds on the safeguards and we're rolling it out to AI Runbooks now, and to Custom Network Context in the near future.
In a nutshell, we are conducting Trus/Safety work around the entire AI stack:

  • Visibility into changes, even for users without permission to modify these configurations.
  • Version history and rollback, allowing teams to track changes and restore previous versions.
  • Audit logging for Create, Edit, and Delete actions, providing accountability for changes.

Together, these capabilities make it possible to expand participation in building AI Advisor's operational knowledge while retaining oversight and control.


RBAC for Runbooks

If you go to Company Settings > RBAC Management you will notice that Roles now include a new category of permissions titled Kentik AI

You can now create roles with granular permissions around Runbooks: Create, View, Edit, Delete - aka these are not governed by the legacy UserLevel anymore (Member, Admin, SuperAdmin)

Depending on your Runbook permissions, the Settings > Kentik AI left-side panel may have the Runbooks entry disabled: the screenshot below illustrates what it looks like when a user has all Runbook permissions disabled.  

The Settings > Kentik AI > Runbooks screen will offer different functionality depending on a user's RBAC permissions, as displayed in the screenshots below.

Example of the Runbook screen for a user with CREATE, EDIT and DELETE RBAC permissions

Example of the Runbook screen for a user with VIEW only RBAC permissions

Coming up next ?

As you have noticed, we're continuously adding AI Safeties around AI Advisor. Next on our list we'll be adding the following:

  • RBAC permissioning for Custom Network Context
  • RBAC permissioning for AI Advisor Chat Sessions: this will eventually regulate what AI Chat sessions users have access to (all users currently have access to all sessions)

Let us know what you think!


Avatar of authorGreg Villain
ImprovementAI
a month ago

AI Advisor MCP adds OAuth to its authentication methods!


Up until today, our users could only Authenticate our AI Advisor MCP into their own agentic solutions using an API Key and Token. A large number of users asked if we could add OAuth to the MCP Authentication methods, so today's post is about just that!

There are multiple benefits to using OAuth to Authenticate against AI Advisor's MCP:

  • OAuth allows our customers to control access to the MCP directly from their IdP (provided said users have a Kentik Portal account): centralized auth management
  • OAuth is useful for integrations: instead of relying on the API Token of a single user to build an integration and therefore making it brittle, OAuth elegantly solves for this use case, allowing more easy management for the business
  • OAuth prevents security issues such as a User's Kentik API Token leaking or being intercepted
  • More generally, OAuth has become the choice standard for MCP Authentication industry wide

Let's dive in!


Adding AI Advisor MCP to Claude Code

Before lauching Claude Code, punch this command in your project directory: 

claude mcp add ai-advisor --transport http https://api.kentik.com/mcp 
(use api.kentik.eu if you are on an EU account)

Then launch Claude Code and fire an /mcp command, you'll see the ai-advisor MCP configured, but unauthenticated, and follow the steps - a browser tab will be invoked to login to Kentik Portal.
The series of screenshot below illustrates these steps.

When done, the /mcp command should give you a similar output with a green check indicating that AI Advisor MCP is connected!

Adding AI Advisor MCP to Claude Desktop

Use the [+] button in your prompt box in Claude Desktop and select Add Connector > Add custom connector

Use this MCP URL to configure the custom connector: https://api.kentik.com/mcp (or api.kentik.eu if you're on an EU account) and follow the step by step, which will invoke a Kentik Portal login page.

 

Follow the steps until a browser tab opens prompting you to Authenticate

You're done once the browser tab gets to this state

Adding AI Advisor MCP to Cursor

 While in Cursor, use the [+] button in your prompt box, and select MCP > Manage, and on the next screen select New MCP Server, it will open your ~/.cursor/mcp.json config file, updated it as detailed in the screenshot below using this config block. (user api.kentik.eu if you are an EU customer) and Save the mcp.json file.

{  "mcpServers": {    "Kentik AI Advisor MCP": {
      "url": "https://api.kentik.com/mcp"
    }
  }
}

Then click on the Authenticate option for the MCP server entry you just created

and follow the instructions in the resulting browser page until the MCP server is displayed as below

The AI team over at Kentik is very excited to see what your teams are going to build using our MCP, give us a shout if you want to demo your integrations and we'll hop on a call!

Avatar of authorGreg Villain
ImprovementCoreAI
a month ago

AI Advisor can now be your Landing Page !

This feature request is a small-ish one, but you'd be surprised how many users have been asking for it in recent times :)
Title says it all, our users love AI Advisor so much that they want to make it their landing page, so here it is !


How can I switch my landing page to AI Advisor ?

First head out to your user profile, on the upper right corner of Kentik Portal

Once there, find the Landing Page setting as shown below

And you're done ! 

Hint: you can always go back to your landing page by clicking the upper left Kentik Logo 

What more can I do ?

Bulk-setting the landing page for multiple users in one go

If you go to the Settings > Users you'll notice you can select multiple users, it will make a bulk edit floater open at the bottom of the screen.
If you are an Admin user, you'll then be able to modify a variety of user attributes in bulk.

Role-Sets & the Landing Page

If you are an avid RBAC (Role Based Access Control) admin user, you may already have assigned users to Role-Sets: these objects are groups of RBAC Roles that can be assigned to users.
One of the things Role-Sets also allow you to do is let you configure a single Landing Page. Every user under this Role-Set will have their landing page follow this configuration.
We have made sure to add AI Advisor to the configuration options of these Role-Sets.


Avatar of authorGreg Villain
ImprovementAI
2 months ago

Custom Network Context: AI Safety

A steady portion of our Kentik AI Advisor work happens behind the scenes which main goal is to make it both safer and more transparent for users to feel confident when they use it.
When it comes to AI, we strongly believe that security, safety and transparency are key features, even though they're never listed as such and hardens the trust that our users place in Kentik, as well as provide the sound guardrails required for adoption to keep growing.

Today's release is about another one of these focused runs, it is about our engineering team adding guardrails around AI Advisor's Custom Network Context - read on!


AI is Magic. Sometimes too much.

As detailed in this previous post about Kentik's AI Runbooks, both the Custom Network Context (aka CNC) and Runbooks deeply affect AI Advisor's reasoning.
Imagine Kentik users whose workflow could rely on a very specific prompt, which they'd for example routinely enter every morning with their first coffee - say What's the status of my edge routers this morning ?

In this example, imagine that the list of Edge Routers is documented in their company's Custom Network Context. (which is one of the most common usages of CNC, by the way...)
Also a reasonable hypothesis: users who rely on this mapping ignore that it has been configured via CNC by a benevolent coworker.

What the above implies is the following sum of safety features:

  • provide ways to track any AI related configuration change (in this case Custom Network Context)
  • allow users to determine who made the change and when
  • allow the security team to be able to research modifications on such configuration objects, even if they are not users of AI capabilities
  • allow users to rollback such changes if it turns out that their effect on AI Advisor answers negatively impacts its answers

This is what today's feature is all about !

Side note: versioning and audit logging was already available for Runbooks, we extended them and perfected them for CNC.

Updated Custom Network Context Interface

Let's head to Company Settings > Kentik AI > Custom Network Context.
First off, we gave the default empty state a bit of a facelift, you know - while at it...

For those out there with an already populated Custom Network Context, here's what it looks like now: a right-side drawer contains every previous version with:

  • Date, Author and Summary metadata attached to it
  • The ability to load it in the main center section, from where the user will be able to
    • Inspect the Diff with the previous version
    • Trigger a Roll back to said version

Selecting a previous version, and then switching to Diff display mode:

Custom Network Context & Audit Log

While working on AI Safety measures for Custom Network Context, we also added support for Audit Log: with any modification on the CNC (Create, Edit, Delete), an Audit Log line is now generated, and visible in the usual Company Settings > Audit Log as displayed in the screenshot below.


Avatar of authorGreg Villain
ImprovementAI
2 months ago

AI Advisor Can Now Create Runbooks

Every network operations team has a "tribal knowledge" problem. When a critical alert fires at 2am, the outcome can depend too much on who responds — who has seen this problem before, who remembers that one strange configuration issue from six months ago, or who knows that when one signal looks normal, the next thing you should really be checking is somewhere else entirely.

Runbooks have always been the answer in theory, allowing organizations to codify that knowledge and those best practices into a repeatable checklist that can be applied consistently across the team irregardless of how good of network and infrastructure engineers they are - they used to be called NOC procedures. 

If only it were quite that simple.

In practice, runbooks tend to be partially maintained notes scattered across Confluence, Slack threads, old tickets, and sleeping brains. And even when a good runbook does exist, it is usually disconnected from the tools where the investigation is actually taking place — so you're context-switching between your observability platform and a document, manually translating "check the BGP neighbor state" into the right query, on the right device, for the right point in time.

Let's look at how AI Advisor natively includes the concept of Runbooks and how we cranked it up a notch in this release!


AI Advisor Runbooks in a nutshell

Runbooks: TL;DR

If you've been using AI Advisor for a while, you may already know that AI Advisor has a native Runbook capability designed to solve for this.
You can write, in natural (wiki-style markdown) language, specific step-by-step instructions for how you want AI Advisor to investigate a particular situation, including what to look at, what certain results mean, and what it should investigate next. 

You can either manage them in Org Settings > Kentik AI > Runbooks


...or ask AI Advisor directly


Composing with Runbooks

Here are a few cool things you can do with Runbooks - go ahead and try them

  • Let AI Advisor select the right Runbook for you. Runbooks can be dynamically invoked by AI Advisor based on the context of a user's prompt, so you don't always need to explicitly call one by name. AI Advisor will also expose if it is selecting and using a rubook for an investigation.
  • Run a Runbook with variable arguments. If the first lines of a Runbook define required variables, AI Advisor will ask the user to provide those inputs before execution.
    Example: Run the Peering Vetting Procedure for AS12322, where Peering Vetting Procedure is the runbook andAS12322 is passed in as the argument.
  • Run Runbooks on a schedule. A Runbook can be executed at a defined frequency using Org Settings > Report Subscriptions with the AI Advisor report type, with the resulting output attached to an email as a PDF.
  • Trigger Runbooks from alerts. In the near future, Runbooks will be able to map directly to Alert Policies and automatically execute as an Auto-Investigation whenever the associated alert fires. This capability is currently in Early Access with select customers and will be available more broadly soon.

Runbooks vs Custom Network Context

Now some of you may wonder what's the difference between Runbooks and the Custom Network Context that is also part of AI Advisor. To understand that, ket's look at the concept of AI Context and how it works in general. 

AI Advisor leverages incremental context within a session: this attached context is a consumable budget - it is handed over to the LLM with each prompt to help it answer the most recent question and each turn/response appends to the context, consuming budget: it is therefore a finite quantity and precious resource 

A fresh AI Advisor session launches with the default System Prompt that's common to every customer, to which we append the Custom Network Context (CNC) on the fly. This is specific information you or your organization has provided to AI Advisor that matters for understanding your network.

This is why CNC is best used for general directives and metadata that apply broadly to the entire infrastructure, because it's your default context spend.

If are familiar with Claude, Custom Network Context is basically your claude.md.

Realistically, you cannot attach every single task-specific procedure your NOC has in the CNC because of the risk of eating your entire context budget the second AI Advisor instantiates. For that, we we created Runbooks.

Runbooks leverage dynamic linking: AI Advisor fires a Runbook tool with every turn, which looks up similarities between the ongoing prompt and all of the Runbook's Title and Description (do make sure these are self-explanatory). When a match is found, the Runbook is appended to the session's AI Context, only consuming from the budget when a match is found.

Again, if you are fluent with Claude, a good way to reason about AI Runbooks in Kentik is the parallel with Claude Skills.
 
As explained, both technically and conceptually behave the same:

  • Runbooks are task-specific, describe complex and multi-steps workflows (troubleshooting, analyzing, auditing, planning...)
  • Runbooks are discovered via metadata (title, descriptions) and loaded only when Claude recognizes a relevant task.

Runbooks & AI Safety

Modifying Runbooks (also valid for CNC), may make AI Advisor start giving different answers overnight to users that were use to getting consistent answers from the same prompts day after day.

As a first principle, Kentik strives to provide the necessary guardrails for the entire company to use AI Safely and Transparently, which implies the following features that come for free with Runbooks:

  • Any change (or creation, deletion...) on a Runbook is logged in our Audit Log facility
  • Any time AI Advisor dynamically summons a Runbook, it will
    AI Advisor always shows int he reasoning when a Runbook is linked
    • explicitly mention it in its reasoning
    • let the user view the runbook as part of the process
  • Any change in an AI Runbook populates a history, with a view to track changes across time and the ability to revert them

An example of Runbook history

Building on Runbooks

Cranking it up a notch

Now that you know everything there is to know about Runbooks, a problem still stands: you can't foresee every situation in advance, and not every troubleshooting process is already documented well enough to turn into a runbook.

In fact, something we've heard from customers is that one of the useful parts of working with AI Advisor is the ability to prod and poke at an investigation — telling it to look somewhere else, providing additional context, correcting an assumption, or guiding it toward the signals you know matter in your network. 

Here's the beauty of it all: over the course of a fruitful investigation, you've effectively taught AI Advisor how you would troubleshoot that particular problem.
...and now you're telling me I need to open an extra tab, and tediously copy/past every single prompt I've entered during that session into a newly created Runbook ?  Color me disappointed!

Try a prompt like this and AI Advisor will have your back!
"- Turn this session into a Runbook
 - use this title: 'Peering Request Assessment Procedure'
 - use the following Description: "Standard procedure our Peering Managers use to evaluate peering requests from an ASN"

... and AI Advisor will create said runbook for you to keep hacking on.

You didn't give it a name or a description? AI Advisor will figure it out for you based on the content of your session.

Lastlt -- useful advice for the social Runbook writer

  • Your NOC team most likely has existing wiki-based or google docs-based procedures.
    Why don't you just pick a couple of them, copy paste them into Runbooks and try them on for size? You'd be amazed how little tweaking these actually need!
  • AI is a muscle: build habit around always turning a fruitful AI Advisor session into a runbook.


Avatar of authorGreg Villain
ImprovementAI
2 months ago

AI Advisor can now create Sites in Kentik Portal

Today we're releasing one of AI Advisor's first Write features: a feature that allows it to create objects in your Kentik Portal configuration.

When AI Advisor launched, its initial scope was to help network operators understand and gain insights on their network data faster, whether during a routine investigation or planning exercise or troubleshooting a critical network outage. It was intentionally limited in scope to reading network data, with no ability to make changes. Today marks the first release of a new family of AI Advisor capabilities to help you configure Kentik itself and accelerate onboarding.

Let's take a look at it!



How does it work ?

Let's just ask AI Advisor, shall we?

So all we have to do is prompt AI Advisor to create a site by submitting its main attributes – to double-check which attributes we can set at creation time, let's just ask it again.

Starting with a simple example, note how it will always ask for permission to create, edit, or delete any object in Kentik Portal via a Human in the Loop (HITL) prompt.

Once created, we can update it, since AI Advisor has the info in its recent context. In this example, let's add a "User Access Network" IP Range to that site by asking it to edit the one we just created.

What about batch creating sites?

While creating Sites with AI Advisor  in Kentik Portal is neat, what we really want it to do is speed up onboarding (i.e. to create multiple sites in one go).

Good news: AI Advisor can do that!

All we have to do is submit the content of a CSV file that has a row for each site. Here's an example with three sites and a header row that names the fields:

"site name","address_street","address_zipcode","address_country_2_letter","address_region","site_type","site_market","peeringdb_fac"

"[test] CDG Telehouse 2","137 boulevard Voltaire","75011","FR","Île de France","Connectivity","test_site_market","53"

"[test] CDG Equinix PA3","114 rue Ambroise Croizat","93200","FR","Île de France","Connectivity","test_site_market","717"

"[test] LYS Free Pro Lyon Rock","60 Avenue Rockfeller","69008","FR","Rhone Alpes","Connectivity","test_site_market","6976"

This results in the successful creation of three sites, with a single HITL confirmation prompt to confirm.

Taking site creation to the next level: Combining AI Advisor tools

Let's imagine we have all our sites registered in PeeringDB as Facilities. The good news is that AI Advisor can access a tool (to be announced in a separate article) with access to the entire up-to-date PeeringDB data.

So we can ask questions such as:

...and follow up with a request to create them in Kentik.

And voila!


Avatar of authorGreg Villain
ImprovementAI
4 months ago

Export your AI Advisor chat sessions!

Since we released our AI Advisor agent, we've been noticing a steady and consistent increase of its usage throughout our user base. When discussing with our customers to understand how they use it, we usually notice a couple things:

  • More often than not, a few champions within the company use AI Advisor in a rather advanced fashion, chaining prompts that leverage different data-sets;
  • The rest of the users mostly use AI Advisor in a one-shot pattern of question, answer, then move on.

Some of our key conclusions are

  1. AI (Advisor) is a muscle: unless you keep exercising it and attempt new prompts, it is hard for users to wrap their heads around what AI Advisor can do that they haven't yet discovered
  2. Emulation is key to adoption: constant exposure to successful/fruitful AI Advisor sessions is a big factor for internal adoption, and helps users develop a sense of the "field of the possibles" in terms of its usage
  3. Sometimes (often) you need to share things with non Kentik users: Whether attaching investigation context for post-incident reporting, or sharing a network planning exercise with others in the organization, we see many needs to be able to create a sharable, portable artifact that is better than "copy & paste."

For that reason, we're adding a couple features for users to share sessions recorded as PDF.


Export AI Advisor chat sessions as PDF

Title says it all: with this function, users can now download any chat session, current or past as a PDF file and share it with other users.

When using AI Advisor in the chat popover mode, you'll notice these series of icons in the title bar, one of them will download the current chat session as a PDF


When using AI Advisor in Full screen mode, 

In both cases, a green toast will let you know when your export is ready with a link to save it as a PDF

Cranking it up a notch: Scheduled Export Subscriptions

This is when things get interesting: building on this foundation, we added a capability for AI Advisor to run offline, on a schedule.
First off head to Company Settings > Reports Subscriptions

and then click Add Subscription (top-right action button), you will now be presented with a new Share type: AI Advisor

which will give you access to configuration options for your scheduled AI Advisor Report

  • Naming the PDF file exported
  • Email recipients to configure it for (TO, CC, BCC)
  • Scheduling options (daily, weekly, monthly, last day of the month)
  • A field for the prompt you want AI Advisor to run and export as a PDF

Here's an idea of how we've seen this feature being used: 

  1. Schedule a report to be run every Monday morning and set to your inbox
  2. Configure the report to rely on the following prompt: 

"Give me a summary of anything critical that has happened over the past weekend, only display a table of summary action items, each one with their level of priority"

Here's an extract of a sample report you could receive in your inbox after a busy weekend

...another example, derived from this one:

  • Network Config Changes made over the weekend can be seen as riskier because of only On-Call staff being available to review them
  • Sometimes these changes are made in emergency to temporarily solve a customer issue and need to be reviewed on Monday when all the engineering staff is present
  • Kentik's NMS offering now by default includes Config Back and Diff'ing for devices enrolled in it, meaning AI Advisor knows about any change made at anytime, by anyone.

What about getting a weekend config change summary on Monday delivered to the Engineering team's inbox to review ?

A scheduled prompt like this one would do the trick

"Show me a summary of all device config changes that have happened over the weekend on all devices, including who made the change

Which would yield a PDF report similar to the one below

How do I make the best use of AI Advisor Scheduled Reports?

This feature really shines when used in conjunction with our AI Runbooks (see the AI Advisor release announcement): with Runbooks, our users can instruct AI Advisor to follow a specific procedure, featuring

  • Natural language instructions that mirror your own operating procedures
  • A step by step detailed reasoning containing what data-sets to pull into an investigation: traffic analysis queries, NMS metrics, Syslog and Trap event entries, on-demand synthetic tests, configuration backups diffs and even run show commands
  • Title and Description metadata, leveraged by AI Advisor to know when to dynamically summon them

Concretely, if you're a Claude Code user, you can think of these as Claude Skills.

These capabilities now can get leveraged offline with AI Advisor Subscription Reports with prompts such as:

Execute the "NTP and Syslog audit" Runbook

In that example, AI Advisor would fetch the Runbook and execute the instructions in it, turning it into a powerful audit tool that will be summoned regularly, sending your Engineering/Operations team a report with actions for them to review and apply.

Avatar of authorGreg Villain
UI/UXSyntheticsNew featureNMSAI
6 months ago

Accelerate Network Diagnostics with Command Access, Config Diffs and On-Demand Tests

Network problems happen all the time, but the hardest part isn't detection. It's getting to the why. Detection is easy, but diagnosis is not. Observability has gotten incredibly good at detecting issues and narrowing down the problem space. But actually diagnosing the network and finding the root cause? That is still painfully manual.

Engineers often need to look at multiple tools, dashboards and CLIs to get to root cause. Introducing, Kentik's new AI diagnostics for faster root-cause analsys! By bringing diagnostic tools-of-the-trade directly into your telemetry and alerting workflows, you can stop the swivel-chair investigation and confirm root causes faster.

Here are three new capabilities launching today to help you streamline troubleshooting:

On-Demand Connectivity Tests

Need to confirm an issue from a specific vantage point? You can now use AI Advisor to validate reachability and path behavior from Universal Agents. This allows you to test and confirm network issues exactly where they matter most to your end-users.

📝 Config Context (Backups + Diffs)

Configuration changes are a leading cause of network incidents. Kentik NMS now periodically captures running configs over SSH, securely stores them as secret-redacted backups, and surfaces diffs between revisions. Even better: AI Advisor can instantly analyze these backups and diffs to answer questions about configuration states and identify if a recent change is the culprit behind your current issue.


💻 SSH Command Access

When an investigation requires live device data, the usual answer is to pull up a CLI and start digging. Now, you can do it right from AI Advisor. AI Advisor can propose, run, and analyze read-only show commands directly inside your investigation thread.

  • No memorizing vendor syntax: AI Advisor handles the complex commands.
  • No context switching: Keep your CLI output and your telemetry in the same window.
  • Empower your team: Junior or less specialized staff can safely troubleshoot complex issues and correlate live device truth with ease.

Ready to see it in action?

Monitor your devices with NMS, configure SSH access and start solving problems faster today. There's no "upcharge" for this new feature. It's included with an NMS device license. Need more details? Check out our knowledge base article and release blog.



Avatar of authorJason Carrier