Is this you? As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work.
Claim your profile
Articles by Joe Karlsson
Best MCP Servers for ChatGPT, Dots, and Meta Muse
ChatGPT and Meta Muse can both draft an email or summarize a meeting. Ask either one which renewals are at risk this quarter, though, and the answer depends on whether it can access the customer relationship management (CRM) system, the support desk, and the finance system that hold that information. Both assistants connect to those systems through model context protocol (MCP) servers, new ones show up every week, and they don’t all solve the same problem.
How to Use ChatGPT Dots with Salesforce, Jira, and More
TL;DR: Connect ChatGPT dots to the business apps you already use, like Salesforce, Jira, Google Analytics, and NetSuite, in a few minutes and without code. Once it’s connected, your dot can answer questions that span those apps, flag deals at risk, combine invoices from two accounting systems, and run a weekly check without being asked. OpenAI launched ChatGPT dots on September 29, 2026, and the setup flow suggests connecting email, calendar, and files first.
Enterprise Data Access for AI Agents: What Model Routing Doesn't Cover
You’ve got model routing sorted. A routing layer, a config file, one endpoint: the model underneath your application is a runtime variable. That part’s relatively easy. The part that isn’t: getting your AI agent to reliably query your CRM, your data warehouse, your ERP, and a dozen other systems, scoped to what the requesting user is allowed to see, returning data that means something, and leaving an audit trail of what got accessed.
LiteLLM or CData Connect AI? Choosing the Right Enterprise AI Gateway in 2026
Building enterprise AI infrastructure usually starts the same way: LiteLLM goes on the shortlist. It’s open source, MIT-licensed, routes to 100+ model providers behind one OpenAI-compatible endpoint and deploys to Docker or Kubernetes in an afternoon. It has real enterprise deployments at Netflix, NASA, Ramp, and Okta and one of the most active contributor bases in open-source LLM tooling. CData Connect AI takes a different approach.
AI Gateway for Developers: What Teams Are Building on Live Enterprise Data
Developer teams are connecting AI agents to production data, and what gets built on top of that access is already taking shape. With the launch of Connect AI’s AI gateway, that architecture has a managed home. An enterprise AI gateway is a managed layer between AI agents and data systems that handles authentication, scopes what each agent can interact with, and logs every request. CData Connect AI is a managed model context protocol (MCP) platform built for this role.
How to Connect Your Business Apps to Meta Muse
If you’ve been using Meta Muse as your personal AI agent and you want it to actually reach your work systems (Salesforce, NetSuite, HubSpot, ServiceNow), this post is for you. By the end, you’ll have Muse connected to your enterprise data so you can ask it questions about your pipeline, your customers, or your open support tickets and get answers without switching apps. It takes about 10 minutes and doesn’t require any technical background.
The Official MCP Roadmap: What Enterprise Teams Need to Plan for
The model context protocol (MCP) core maintainers published their updated roadmap on Aug. 22, 2026 (The New MCP Roadmap). If you’re an engineering or AI lead managing MCP servers for a large team or enterprise deployment, this covers what you need to know: what each of the five priorities means in practice, which ones require migration work and which you can safely watch from a distance, and where the gaps stay even after all five ship.
What I Learned When I Could Finally Prove My Work Mattered
For most of my last job I couldn’t answer the one question that mattered most: did any of this turn into a customer? I could tell you how much traffic I’d brought in, which pages were climbing, and what people searched before they found us. I had a good report. And every time somebody asked the follow-up, I said some version of I don’t know, that lives in a system I don’t have. You can only say that a few times before it starts to feel like a description of you rather than of your tooling.
The 2026-07-28 MCP Release Explained: What It Means for Enterprise Teams (2026)
The MCP 2026-07-28 release is the largest revision of the Model Context Protocol (MCP) since its launch, and it reaches into transport, extensions, authorization, and tool schemas at once (release announcement). If you run MCP anywhere near production, this MCP release is less a feature drop than a re-foundation. This overview walks through what changed and, for each change, what it means for the teams running MCP against real enterprise data.
Why Terraform is green when your cloud is broken
It was a Tuesday afternoon. Terraform plan came back clean. No changes. I double-checked, because the last few deploys had been messy and I wanted to be sure. Still clean. So I merged the PR, grabbed coffee, and went to a 3 p.m. meeting about Q3 roadmap priorities that I genuinely did not need to attend. Forty-five minutes later, I had five Slack messages waiting for me. Our API was returning 403s on a specific endpoint.
The one Slack message that proved our elite engineering team was flying blind
The one Slack message that proved our elite engineering team was flying blind sponsor-env-zero,sponsored-post-contributed, Adriandra Karuniawan for Unsplash+ Someone posted a question in Slack that seemed straightforward: What are we actually running across both cloud environments? Not what our Infrastructure as Code documentation says. Not what the billing reports show. What’s actually running, right now, across every account, every provider, both orgs.
How to Build Applications over Streaming Data the Right Way
In the bustling metropolis of modern data ecosystems, streaming data is the lifeblood coursing through its veins, much like the traffic on a busy city highway. Each packet of data, akin to a vehicle, has a specific destination. Some are on a leisurely ride to a data lake for historical analysis, while others are zipping toward real-time analytics engines, where they will be used to power automation, user-facing features and real-time operational intelligence.
The Engineer’s Guide to Enriching Streams and Dimensions
Data — it’s the new oil, the new gold, the new … you get the idea. There’s a whole lot of it, and it’s valuable. But unless you’re into data hoarding, the point isn’t just to collect it; you want to use it. You want to massage it, query it, build with it and glean insights from it in real time, right? Well, brace yourself, because you’re in for a treat.
Data Warehouses Are Terrible Application Backends
The ever-increasing tide of data has become a paradox of plenty for today’s developers. According to a report from Seagate, by 2025 worldwide data will grow to a staggering 163 zettabytes, over 10 times the volume in 2016. More data should mean deeper insights and better user experiences, but it also leads to problems. For data-oriented developers, this explosion is a double-edged sword.
Why Clickhouse Should Be Your Next Database
Today, we’re venturing into the riveting realm of databases. Now, I can hear you sigh: “Another database to learn? Seriously?” But before you sprint for the hills, allow me to introduce you to ClickHouse, the Sonic the Hedgehog of the database multiverse. Lightning Quick: Decoding ClickHouse Architecture ClickHouse is an open source, column-oriented database management system (DBMS) designed for running real-time analytical queries and updates on mammoth datasets.
Databases and DevOps: How to Use SingleStore With GitHub Actions
Databases are frequently not included when transforming an application and engineering culture toward a DevOps, or continuous deployment engineering organization. And, you could be forgiven for this because setting up repeatable, fast and up-to-date database environments for an application is really hard! By not including the database in the pipeline, most of the work related to database changes ends up being manual, with the associated costs and risks.
How to work with Johns Hopkins University COVID-19 Data in MongoDB Atlas
#The MongoDB Dataset All the data we use to create the MongoDB COVID-19 dataset comes from the JHU dataset. In their turn, here are the sources they are using: the World Health Organization, the National Health Commission of the People's Republic of China, the United States Centre for Disease Control, the Australia Government Department of Health, the European Centre for Disease Prevention and Control, and many others. You can read the full list on their GitHub repository.
Show More
loading
Actions
Is this you?
As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work.Get in touch with Joe
Contact Joe, search articles and posts on X, monitor coverage, and track replies from one place.
Learn more about Muck Rack