THE KERNO BLOG
All
AI Builder Series
Guides
Others
Sean Madigan
∙
August 12, 2026
Kerno tests MCP servers at runtime
Kerno now tests MCP servers at runtime: it introspects your server, plans scenarios per tool, runs them in a sandbox, and verifies findings against your sou
Dr. Michael Coughlan
∙
April 24, 2026
Dataset curation for agent testing pipelines
Principles for getting dataset creation right from the start, and the impact it can play in your agent development.
Maxi Delo
∙
March 12, 2026
How To Use Skills To Write Better PRDs and Tickets
Using Skill.md and MCP to automate ticket creation with the full context of your product.
Dr. Michael Coughlan
∙
March 10, 2026
The Halting Problem in AI Coding
No algorithm can predict all program behaviour not even AI. The only way to know is to run the code.
Dr. Michael Coughlan
∙
27 Feb 26
LLM-as-a-Judge: Evaluating Output Without a Ground Truth
Jordan Bergin
∙
19 Feb 26
Multi-Agent Validation Gates: Why Claude Can't Break Our Architecture
Dr. Michael Coughlan
∙
10 Feb 26
Runtime evaluation of coding agents
Sean Madigan
∙
10 Feb 26
Understanding the LLM Marginal Costs
Sean Madigan
∙
05 Feb 26
AI-DLC Startup Edition
Dr. Michael Coughlan
∙
29 Jan 26
Building Trustworthy Agents: The Business Case for Rigorous Evaluation Frameworks
Dr. Michael Coughlan
∙
16 Dec 25
Lessons from Biology for Scalable Compute Experiments
Antoine Frau
∙
24 Dec 25
Bulk Testing Docker Agent Performance Across 18 Codebases
Antoine Frau
∙
24 Dec 25
CLI Tooling for Agent Testing Pipelines
Dr. Michael Coughlan
∙
27 Feb 26
LLM-as-a-Judge: Evaluating Output Without a Ground Truth
Jordan Bergin
∙
19 Feb 26
Multi-Agent Validation Gates: Why Claude Can't Break Our Architecture
Dr. Michael Coughlan
∙
10 Feb 26
Runtime evaluation of coding agents
Sean Madigan
∙
10 Feb 26
Understanding the LLM Marginal Costs
Sean Madigan
∙
05 Feb 26
AI-DLC Startup Edition
Dr. Michael Coughlan
∙
29 Jan 26
Building Trustworthy Agents: The Business Case for Rigorous Evaluation Frameworks
Dr. Michael Coughlan
∙
16 Dec 25
Lessons from Biology for Scalable Compute Experiments
Antoine Frau
∙
24 Dec 25
Bulk Testing Docker Agent Performance Across 18 Codebases
Antoine Frau
∙
24 Dec 25
CLI Tooling for Agent Testing Pipelines
Dr. Michael Coughlan
∙
April 24, 2026
Dataset curation for agent testing pipelines
Principles for getting dataset creation right from the start, and the impact it can play in your agent development.
Maxi Delo
∙
March 12, 2026
How To Use Skills To Write Better PRDs and Tickets
Using Skill.md and MCP to automate ticket creation with the full context of your product.
Dr. Michael Coughlan
∙
10 Mar 26
The Halting Problem in AI Coding
Dr. Michael Coughlan
∙
27 Feb 26
LLM-as-a-Judge: Evaluating Output Without a Ground Truth
Jordan Bergin
∙
19 Feb 26
Multi-Agent Validation Gates: Why Claude Can't Break Our Architecture
Dr. Michael Coughlan
∙
10 Feb 26
Runtime evaluation of coding agents
Sean Madigan
∙
10 Feb 26
Understanding the LLM Marginal Costs
Sean Madigan
∙
05 Feb 26
AI-DLC Startup Edition
Dr. Michael Coughlan
∙
29 Jan 26
Building Trustworthy Agents: The Business Case for Rigorous Evaluation Frameworks
Dr. Michael Coughlan
∙
16 Dec 25
Lessons from Biology for Scalable Compute Experiments
Antoine Frau
∙
24 Dec 25
Bulk Testing Docker Agent Performance Across 18 Codebases
Sean Madigan
∙
November 10, 2025
eBPF – The Best Kept Secret in Technology
eBPF enables low-overhead, real-time observability and security, powering AI-native apps without sidecars, agents, or manual instrumentation
Vladimir Romanov
∙
November 16, 2025
Network Observability
Observability is used to describe the ability to understand the current or past state of a software system.
Karim Traiaia
∙
November 10, 2025
Programming the Kernel with eBPF
Learn about eBPF, an exciting new technology that makes programming the kernel flexible, safe, and accessible to developers.
Vladimir Romanov
∙
November 10, 2025
Understanding What is ECU in AWS
An ECU is an EC2 Compute Unit used to measure the power of resources in the cloud. Based on that single ECU, the user can...
Vladimir Romanov
∙
10 Nov 25
DevOps Pipeline - Understanding the Steps, Benefits, and Tools for Developers
Vladimir Romanov
∙
10 Nov 25
DevSecOps with GitLab CI
Vladimir Romanov
∙
16 Nov 25
Advanced Workflows in GitHub Actions
Vladimir Romanov
∙
16 Nov 25
CI CD Pipelines with GitHub Actions
Vladimir Romanov
∙
10 Nov 25
IAM Roles for Service Accounts
Vladimir Romanov
∙
16 Nov 25
GitOps with Kubernetes
Vladimir Romanov
∙
10 Nov 25
Kubernetes Monitoring | Tools & Techniques You Should Know
Vladimir Romanov
∙
16 Nov 25
Exploring Amazon EKS Cluster Management with EKSCTL: A Comprehensive Overview
Vladimir Romanov
∙
10 Nov 25
Kubernetes Ingress: Efficient Strategies for Service Routing
Vladimir Romanov
∙
10 Nov 25
DevOps Pipeline - Understanding the Steps, Benefits, and Tools for Developers
Vladimir Romanov
∙
10 Nov 25
DevSecOps with GitLab CI
Vladimir Romanov
∙
16 Nov 25
Advanced Workflows in GitHub Actions
Vladimir Romanov
∙
16 Nov 25
CI CD Pipelines with GitHub Actions
Vladimir Romanov
∙
10 Nov 25
IAM Roles for Service Accounts
Vladimir Romanov
∙
16 Nov 25
GitOps with Kubernetes
Vladimir Romanov
∙
10 Nov 25
Kubernetes Monitoring | Tools & Techniques You Should Know
Vladimir Romanov
∙
16 Nov 25
Exploring Amazon EKS Cluster Management with EKSCTL: A Comprehensive Overview
Vladimir Romanov
∙
10 Nov 25
Kubernetes Ingress: Efficient Strategies for Service Routing
Sean Madigan
∙
November 10, 2025
Truck Factor: The Silent Debt
Explore the Truck Factor, its impact on engineering teams, and strategies to prevent knowledge silos from stalling development.
Sean Madigan
∙
November 10, 2025
When Collaboration Becomes Counterproductive for Engineers
While collaboration is essential, its misuse in problem-solving can prolong issues and magnify costs.
No items found.
Docs
Blog
Pricing
Quickstart
Log in
Log in
|
Quickstart
Set up Kerno for this repo: install the CLI, bind it to this workspace, register MCP with my coding tool, then trigger workspace analysis and list the available apps for me to choose from. Follow the Kerno MCP's instructions throughout. Don't run any tests, and don't set up the environment yet. Read rather than improvise. kerno init prints what you need, and once MCP is live every Kerno tool carries a What/When description saying what to call next. Follow those, and call kerno_guide for detail. The commands below are the happy path; if kerno init prints something different, its output wins. Prerequisites that must already exist. If any of these is missing, stop and tell me: Node.js 18+, npm, Docker running, and a git repo. npm install -g @kerno/cli kerno login kerno init -w "<absolute path to this repo>" Don't run kerno login yourself. It renders an interactive terminal UI and dies immediately in an agent shell with "Raw mode is not supported on the current process.stdin", so the browser never opens. Instead, tell me to run ! kerno login in the prompt myself, then pause and wait for me to confirm I've logged in before continuing. Run kerno init -w even if something seems to be listening already, never two at once, then use the workspace, port and registration snippet it prints verbatim. The port is per-session, so never reuse one from docs, an old config, or memory. Be aware that init's port and registration snippet render through the same terminal UI, so in an agent or piped shell the plain output may stop at "Starting agent..." with no port and no registration line. If that happens, don't guess: either re-run under a pseudo-TTY to force the full snippet to render (script -q /dev/null kerno init -w "<path>"), or read the port from ~/.kerno/agent.stdout.log (the line "Kerno MCP server started on port N") and build the endpoint as http://localhost:N/mcp. kerno doctor --clean fixes an orphan or inconsistent agent. Default to registering with the host you are running in, but confirm r, and ask if I want a different one. Don't infer my preference fromthe tool alone. Register at one scope only, project or user, and merge rather than overwrite other servers. Then allowlist Kerno before calling any tool. A single task runs manypeated status and job polling, so without this I am clicking approveevery few seconds. Explain that to me, show me the change, and apply it once I accept. If it's already present, tell me and move on. Claude Code: "mcp__kerno__*" in permissions.allow in .claude/settings.json or ~/.claude/settings.json. Codex: default_tools_approval_mode = "approve" under [plugins."kerno@kerno".mcp_servers.kerno] in ~/.codex/config.toml. Cursor: no file, tell me to set Run Mode to r id you registered if it isn't "kerno". Registering the server does not load its tools into a session that was already running. Before you try to call anything, expect the kerno_* tools to be absent, and tell me to reconnect: in Claude Code run /mcp, select the server, and reconnect, or restart the tool. A "Connected" line from claude mcp list is not proof your current session can call the tools, because that check opens its own Verify only with kerno_get_applications. Verify with kerno_get_applications; that succeeding means connected. Don't use a healthcheck, which blocks 120 seconds and can report a schema error while MCP is fine, and don't use kerno status, which needs a TTY and exits 1 in agent shells even with CI=true. Also note: any stop, restart or workspace switch kills the MCP session even on the same port. Re-parse the MCP endpoint URL from the registration snippet and reconnect the same way. Once connected, let Kerno finish analyzing the workspace, then list the apps it found and present them to me so I can choose which one to test. Stop there and follow the Kerno MCP's tool guidance for what comes next.
COPY SETUP PROMPT
COPY CLI COMMAND
Get started for free | Works with your AI stack
.jpg)
.png)
