Tag: APIs
-
people work better with HTML, not markdown
I like the idea of having your AI thingies creating one off HTML pages as output. For example, monitoring and management agents. Most services now have an MCP server that will give API access to observability, logs, etc. What if instead of emitting JSON, they (also) emitted an HTML page? 🔗 Using Claude Code: The…
-
Use AI to write more shorter pieces
While people are all excited shout using LLMs to write – which is awesome, I am all about AI empowering people to do things they didn’t have the agency to do, writing being one of them – I am imploring y’all to get the LLMs to write more concisely. I am looking at all y’all…
-
Platform engineering is what makes AI enterprise-ready
As we’ve found, writing AI-powered software is the easy part. Testing it, securing it, operating it at enterprise scale – that’s where things get interesting. “Guardrails,” all that. Purnima lays this out: a shift from deterministic systems (input goes in, predictable output comes out) to probabilistic ones where agents wander around exploring multiple paths to…
-
Say you love business logic without saying “business logic.”
Model Eats the Software: Why the Marginal Cost of Enterprise Software Approaches Zero More on agentic AI changing the software business from Jason Hoffman: Andreessen specifically predicted that Salesforce would disrupt Oracle. Fourteen years later, Oracle is roughly 2.5x the size of Salesforce. Salesforce sells application logic – workflows, configurations, business rules. Oracle sells infrastructure…
-
Debating AI dicks is pointless
He’s never been a fan of AI: I’ve stopped trying to debate software developers on LLMs…this is still a crowd that is explicitly fine with using tools that are themselves deeply unethical.” Going all “but it works great for me” even as the industry burns around you and the “it” is a right-wing political project…
-
Relative to your interests, Monday
Is Your AI Assistant Creating a Recursive Security Loop? AI security concerns and opportunities for 2026 – Tanzu security maestro David Zendzian rattles it off. Amazon gives managers a new way to spot employees who aren’t spending enough time in the office – Enterprise Nanny-state. What does the platform engineer do when the amount of…
-
What would an annual intellectual purge look like? Accounting for and getting rid of unfinished thoughts and beliefs to start fresh, rather, declutter the mind. The goal is something like inbox bankruptcy.
-
A race against software calcification
Eventually, software is very hard to change. There are numerous reasons for this, and they often don’t even involve the software. The systems that run the software are old, regulators don’t let you change things, security controls, people have just forgotten how to program COBOL. There is so much code that it’s hard to know…
-
Use yours secrets to get generative AI ROI
From an article by my colleagues and me: For generative AI (GenAI) apps to deliver real business value, they need access to your company’s proprietary data. Without it, models default to the public data they were trained on–meaning you get the same generic ideas as your competitors. If everyone is starting with the same new…
-
Shutdown and consolidate old IT so you can focus on new IT, like AI hoopla
People often say they spend 80% of their IT efforts on maintenance, “keeping the lights on”: Like all banks, our technology expenditure has been weighted towards maintenance and regulatory programs. These activities represented around 85% of our tech investment spend in 2024. So, simplifying that, shutting down old things is a positive thing to do;…
-
“technically fine, offends no one, and also does fuck-all to advance the conversation”
Me: Give me a definition of and commentary on “anodyne.” It seems like smarty-pants people use it as a dog whistle (a shibboleth!) for saying “I’m a smarty pants.” ChatGPT 5.1: **Definition** _Anodyne_ (adj. or noun): 1. Something that relieves pain or soothes; 2. By extension, a remark, policy, or idea that is inoffensive, bland,…
-
Make it so the robots can use your shit, or you might be irrelevant. At least, less so. Platforms, tools or frameworks that are hard for large language models (LLMs) and agents to use will start feeling less powerful and require more manual intervention. In contrast, tools that are simple for agents to integrate with…
-
“If the people building the tech are terrified of it, maybe we should listen to their fears rather than their sales pitch.” Ten Blue Links, “Pop goes the bubble” edition
-
Meatsack context engineering to defuse tense conversations
In a tense situation, take a moment to say out loud your opponents position, feeling, and perspective. This is like setting up context and prompting for an AI. You put that in the context window and it flavors the ongoing conversation. It’d probably do interesting stuff in AI chats. Those chats are so explicit and…
-

🤖 Old infrastructure considered not optimal, Forrester study
Legacy systems are creating measurable revenue drag, with 63% of surveyed companies citing efficiency losses. Early adopters of cloud-native infrastructure report 40% faster deployment cycles. Commissioned by Broadcom, based on June 2025 survey. 🔗 🤖 Forrester: Modernize or Fall Behind – Rethinking IT Infrastructure (October 2025) Citation: “Modernize Or Fall Behind: Rethinking IT Infrastructure For…
-
Make it easy for other people to pitch for you
With some generalization, this is good advice for any pitch, from corporate presentations to call for papers. The point that you need to make it easy for other people to advocate for you is a good one, rarely mentioned. 🔗 Setting up other people to pitch your idea for you
-
Vibe coding toolchain and method
A lot of effort went into making this effortless. 🔗 Just Talk To It – the no-bs Way of Agentic Engineering, Peter Steinberger
-
“The context window is a public good.” Skill authoring best practices,Claude Docs

You must be logged in to post a comment.