Really appreciate that, thanks a lot Mike!

Best practices for building agentic systems Which technologies, designs, standards, development approaches, and security practices are gaining momentum in multi-agent enterprise systems? We asked the experts.

What actually goes into building enterprise-grade AI agents?

My latest for @infoworld.bsky.social explores the emerging best practices behind agentic systems:

www.infoworld.com/article/4154...

How ING Bank Manages 2,000 Microservices With Service Mesh | Nordic APIs | How ING scaled 2,000 microservices with a service mesh, covering governance, discovery, and security lessons.

Today I look into ING Bank's journey developing a custom-made service mesh to manage its 2k microservices portfolio.

We covered their API-first transition on @nordicapis.com in 2017, so it's pretty cool to see the journey coming full-circle after 9 years.

nordicapis.com/how-ing-bank...

AI & API Security Dinner | Nordic APIs Join Nordic APIs, Akamai and Curity for a night of dinner, AI & APIs onboard a classic archipelago ship.

Calling out folks in the Stockholm and Nordic area: @nordicapis.com, Akamai, and @curity.io are hosting a pretty dreamy event next month: a dinner cruise through the Stockholm archipelago 🚢

Check out the details and register interest here: nordicapis.com/events/api-s...

How to build an enterprise-grade MCP registry MCP registries are emerging as the new integration catalog for AI agents. Building one for the enterprise requires semantic discovery, strong governance, and developer-friendly controls.

What goes into an enterprise-grade MCP registry?
My latest for @infoworld.bsky.social goes deep into this topic:
www.infoworld.com/article/4145...

APIs are the new perimeter: Here’s how CISOs are securing them Today’s attack surface is shifting from the endpoint to the API, and AI and third-party SaaS are worsening the issue. CISOs offer advice for API defense.

My first-ever contribution to @csoonline.bsky.social looks at the shifting landscape, from perimeter-based security to #API security, and how CISOs are responding.
www.csoonline.com/article/4148...

96% of codebases rely on open source, and AI slop is putting them at risk AI-generated slop is overwhelming open source maintainers with low-quality pull requests. Here's how projects are fighting back with policies and new tools.

Okay, how do we fix open source Slopmageddon?

My latest feature is live on the @thenewstack.io:
thenewstack.io/ai-slop-open...

Squarespace redraws the boundaries of platform engineering AI is transforming platform engineering from a support function into a more agile hands-on discipline, reshaping teams and accelerating migrations.

Platform engineering is being redefined in the agentic era: less shared code, slimmer platforms, more focus on developer experience.

In my latest for @leaddev.com, I interview Squarespace director of engineering Jon Thornton on the shift:

leaddev.com/ai/squarespa...

Tackling API Security in the AI Era | Nordic APIs | How AI accelerates API security risks and why access control and IAM remain critical safeguards.

"We know that API breaches in general are much more severe than a common data breach," says @curity.io's CTO, Jacob Ideskog. Now with AI agents using APIs, "take that and multiply it."
via @nordicapis.com
nordicapis.com/tackling-api...

LiveCast: Asynchronous APIs for AI and Data Science YouTube video by Nordic APIs

Yesterday, I had a great chat with Phil Leggetter and Ryan Day on the role of asynchronous APIs in AI and machine learning. The full recording is here on the @nordicapis.com YouTube!
youtu.be/PPQ5yfgeMXs?...

What are some solid API monetization success stories of the 2020s? Here's why Plaid, OpenAI, AssemblyAI, Algolia, and others make the list.
via @zuplo.com
zuplo.com/blog/5-api-m...

Open source maintainers: how are you managing the influx of AI contributions to your projects? Would love to hear from you you for a piece I’m working on!

LiveCast: Asynchronous APIs for AI and Data Science | Nordic APIs Join us for a LiveCast to explore the benefits of using asynchronous patterns in AI and data science, when to use them, and the end results.

What happens when AI agents need to rely on event triggers?

Excited for this week's @nordicapis.com LiveCast on asynchronous communication patterns in AI, featuring insights from a data science and webhook expert.

Details: nordicapis.com/events/async...

What is context engineering? As developer teams integrate more AI tooling into their workflows, a new practice is emerging: context engineering.

What exactly do we mean by context engineering? I unpack the term for @leaddev.com and look at some emerging context engineering patterns.
leaddev.com/ai/what-is-c...

The real breakthrough in robotics is foundation models — not hardware Discover how physical AI foundation models are moving beyond chatbots to power autonomous robotics in the real world. Explore LBM, VLA, and edge computing.

AI is getting physical — and the real differentiator won't be hardware. It'll be the models.

My latest for @thenewstack.io looks at LBM, VLA, open world models, edge constraints, and what it takes to make physical AI work at scale.

thenewstack.io/physical-ai-...

How to justify AI investments Workato CTO Adam Seligman explains why internal AI initiatives must tie directly to real business outcomes, and how deeper integration via MCP was their big game-changer.

For this month's DirectorPlus edition, Workato's CTO shares their internal success story using MCP within Claude. Some impressive usage numbers and outcomes!
Read on @leaddev.com:
leaddev.com/ai/how-to-ju...

Five MCP servers to rule the cloud The hyperscalers were quick to support AI agents and the Model Context Protocol. Use these official MCP servers from the major cloud providers to automate your cloud operations.

The hyperscalers jumped on the #MCP train quickly. So what can you actually do with MCP servers for major clouds?

My latest for @infoworld.bsky.social looks at what's possible using official MCP servers from AWS, Azure, GCP, Oracle, and IBM Cloud.

www.infoworld.com/article/4129...

6 agentic knowledge base patterns emerging in the wild Organizations are actively building agentic knowledge bases for AI agents. Here are six real-world approaches taking shape across the software industry.

How are organizations using agentic knowledge bases in practice? Today, my feature on @thenewstack.io looks at six emerging patterns.
thenewstack.io/agentic-know...

My report for the eBPF Foundation, "eBPF in Production," was published today. The 20-page report explores emerging deployment patterns for #eBPF, four original case studies, and a comprehensive look at tangible business outcomes.

📘 PDF: www.linuxfoundation.org/hubfs/eBPF/e...

10 strategies to reduce MCP token bloat Unrestrained use of MCP can quickly flood context windows. Experts share ten practical techniques to rein it in.

MCP servers can quickly drain context windows without the right guardrails. Thankfully, there are ways around this...

My latest feature with @thenewstack.io breaks down a number of practical techniques for reducing MCP token bloat.

thenewstack.io/how-to-reduc...

What CIOs in finance do to navigate AI agents As AI sweeps through every sector, some are held to a greater degree of scrutiny. Finance is one of them and CIOs across its institutions and systems work within narrow margins of error due to increas...

My latest for @cio.com looks at how CIOs are deploying agentic AI in finance. 🏦

Although AI agents feel like they’re everywhere, in finance and banking, the reality is more cautious and more deliberate than the hype suggests.

www.cio.com/article/4123...

How should AI agents consume external data? The jury’s out on screen scraping versus official APIs. And the truth is, any AI agent worth its salt will likely need a mixture of both.

To scrape or integrate? It's an age-old question resurfacing for AI agent builders.

My latest for @infoworld.bsky.social breaks down the upsides and caveats of both approaches — and when it actually makes sense to use each.

www.infoworld.com/article/4120...

Shipping nano updates in the AI era Are nano updates the missing link in your strategy?

What does it mean to go "nano" with your software updates — to "carve with a scalpel" instead of swinging a hammer?

My latest DirectorPlus edition with @leaddev.com interviews @chainguard.bsky.social VP Dustin Kirkland to find out.

leaddev.com/ai/shipping-...

Port of Context: The open source code mode The “better way to use MCP” just got open sourced.

Heavy MCP use can lead to flooded context windows, fast. My latest piece for @thenewstack.io looks at an interesting project aiming to address this problem: Port of Context.

One of the big downsides of AI is decreasing quality and slop in open source contributions. I have a lot of respect for Daniel Steinberg, and I'm sure the decision wasn't taken lightly!

LiveCast: API Standards for AI Agents | Nordic APIs Our LiveCast on API standards and AI agents explores how core API and open web standards enable accurate, reliable, and safe agent behavior.

Excited for this @nordicapis.com chat tomorrow with Kin Lane, Lorna Mitchell, and Kevin Swiber on the role of API standards in agentic AI.

Come join us in real-time, or wait til the recording is posted. Registration and information are here. ⬇️

nordicapis.com/events/api-s...

AI doesn't create great developers, it amplifies them Research from GitClear suggests the best devs benefit the most when using AI coding tools.

As it turns out, the engineers seeing the biggest gains from AI were top performers all along.
@billharding.bsky.social @leaddev.com
leaddev.com/ai/ai-doesnt...

Edge AI: The future of AI inference is smarter local compute Smaller models, lightweight frameworks, specialized hardware, and other innovations are bringing AI out of the cloud and into clients, servers, and devices on the edge of the network.

Edge AI is gaining new importance as the industry shifts from training to inference. My feature on @infoworld.bsky.social today digs into edge AI, and why tech leaders are betting on it for reduced cost, better privacy, and lower latency.
www.infoworld.com/article/4117...

The State of MCP — Survey Report How teams are really adopting MCP. Practical findings on security tradeoffs and production readiness, plus the patterns shaping what comes next.

The State of #MCP report from @zuplo.com has some good nuggets...

• 72% of adopters expect MCP usage to increase

• 40% expect it to account for a quarter to half of their AI tool usage

• 70% of devs have 2-7 MCP servers configured, often for context engineering use cases

zuplo.com/mcp-report

6 incredibly hyped software trends that failed to deliver In hindsight, what were we thinking?

Blockchain for everything, metaverse, big data, NFTs... In hindsight, what were we thinking? Today, I call out some of tech's biggest overhyped trends on @infoworld.bsky.social.
www.infoworld.com/article/4109...