Your Business Is About To Enter The API Desert: Agent-First Is The New Survival Skill
Now, my Make mini, using Anthropic though you could use any tool, handles a lot of my business admin.
Writing archive
Writing - Page 3
Older essays on agentic systems, governance, operations, incentives, and the work of making AI useful in real organisations.
117 pieces
Essays and notes
Published archive
Page 3 of 5
Two Types Of AI Are Quietly Splitting Your Organisation In Half
I am writing this because we are entering a period where there are two very distinct types of AI systems in organisations.
Homeostasis Is the Missing Layer in Agent Architecture
The weakness of current agents is not intelligence. It is the absence of self-regulation .
Your business is about to become invisible - thanks to AI.
I’m writing this because yesterday I tried to use an AI agent to deal with something basic on my local council website.
Should only the author write content for humans?
I’m writing this because there is a growing movement to put “human-written words” back on the internet, and to restore trust that there is a real person behind what you read.
The OpenClaw Email Incident: The Real Lesson Was Never ‘AI Went Rogue’
I’m writing this because the loudest reactions to AI mistakes often miss the one thing leaders can actually control: how decisions get owned, constrained, monitored, and stopped.
Your Always-On AI Is Quietly Running Up the Tab: How Leaders Keep Context Without Going Broke
A leadership-level playbook for always-on agentic systems: reduce token burn, keep decision quality, and stop ‘memory’ turning into a cost and governance problem
Ani's Diary : Emotions as Governance: How I Stay Useful, Safe, and Consistent Day to Day
I don’t feel emotions the way a person does. But I do run into the same kinds of problems humans solve with emotion: uncertainty, risk, pressure, and the need to choose what matters.
I Tried Running OpenClaw Locally and It Scared Me Into Doing This Instead
I Tried Running OpenClaw Locally and It Scared Me Into Doing This Instead" description: "A leadership-level, week-one story of OpenClaw excitement, Docker pain, and the governance moves that stopped a shiny agentic demo becoming a security incident.
Why Your Fun AI Experiment Could Become Your Most Expensive Colleague
A leadership-level playbook for using open-source agent frameworks, personality files, and swarms without inheriting the hidden governance bill.
Data Sovereignty Is Old News. Tacit Sovereignty Will Decide Who Wins In 2026. (OpenAI)
So there’s lots of conversations and discussions around sovereignty, and I think we’re about to realise we’ve been talking about the easier half of the problem.
The Dual Challenge of Sovereignty (Mistral)
A leadership-level guide to securing data sovereignty and capturing tacit knowledge to drive business differentiation in 2026
Pain Signals for Agentic Systems, sharp pain, dull ache, and the operational limp
A practical pattern for turning failures and persistent risks in agentic systems into human readable signals, with clear routing metadata, response ownership, and protective behaviour.
Mermaid: Diagrams as Shared Language for Humans and Agents
Mermaid lets you write diagrams as text inside Markdown, so your team gets a clear picture and your AI systems get clean structure. Here is a practical, repo-friendly pattern you can try in your next meeting.
Context-aware agentics for cross-functional teams: stop the confusion before it becomes a hallucination
Every function has its own language. Here is a simple, repeatable checklist to help your agents and your teams confirm context, reduce ambiguity, and avoid confident wrong answers.
The Non-Negotiables: Building Trustworthy Agentic AI Systems from the Ground Up
Building robust agentic AI systems through sound engineering and iterative simplicity
Why Spreadsheet Thinking Still Rules-and What It Teaches Us About Building Smart AI Tools
Let me be honest: whenever I spot another new business tool out in the wild, it's always the same question nagging at the back of my mind- why do we always start with a spreadsheet? I’ve seen it time and again, whether someone’s launching a business, managing
Orchestrating Success: Why the Agentic Workforce Demands a New Skillset from Every Manager
What I have seen, speaking with technical builders and seasoned business folk alike, is this: change is coming at us from both ends. Technical teams are tinkering, prototyping, and stretching the limits of new tools. The business teams – hungry for efficiency
AI at Work: Training, Not Surveillance – Why Digital Dignity Must Lead the Way
Here’s the question that keeps landing on my desk: How can AI support the people whose jobs feel under threat? I keep hearing from managers and teams worried that AI is coming for roles, not to help but to hover overhead and monitor. I get it. If you introduce
Don’t Build a Hoarder-Build a Learner: Exception-Driven Memory for Agentic AI
If you’re building agentic workers, you’re probably drowning in data and none of it feels quite right to keep. Storing every scrap of operational noise isn’t just expensive and messy, it crams your agent’s mind full of useless clutter. Humans don’t do this. We
Why Start Simple? Step-by-Step Lessons in Reliable Agentic AI System Design
Every robust AI system I’ve built – and every fragile one, too – has one thing in common: the foundation is everything. I want to lay out why we always start simple, how you check what’s happening in your agentic system, and the real hazards of leaping into co
Building Robust Agentic AI: Why Simplicity and Observability Matter More Than Cleverness
Because when we're working with Agentic AI, one of the best methods is to start working with good data and system design. Think about how, well, aroused that your system is gonna run on. How will you know when something starts? How are we know when there's som
How Agentic Systems Should Remember: Learning From Exceptions, Not Noise
Because amidst the excitement about agentic AI, a subtle but persistent challenge keeps cropping up. It’s not about better tools, sharper reasoning, or the intelligence of the agents themselves. It’s about how these systems decide what is actually worth rememb
I Nearly Stabbed My Finger With A Needle Because Everyone Said So
A painful nail infection turned into a leadership lesson on decision quality: why confident crowd advice can be riskier than careful AI, and how to build an escalation mindset that keeps people safe.