Running ten agents broke my brain
Discover what happens when you scale up parallel AI agents and experience agentic cognitive overload. Learn how to manage AI workflow burnout effectively.
simons linkie
Simple, automated marketing for founders and small businesses who want to get back to building cool stuff
Latest from the blog
A live timestamp in a cached prompt will quietly wreck your bill
Why one live timestamp in a cached system prompt busts your entire prompt cache, and the one-line fix that stops it happening.
io-auto-mode: the missing security layer for autonomous agents
A three-layer security classifier that lets autonomous agents act without constant approval, built runtime-agnostic from day one.
A second opinion only works if it's actually a second opinion
Why a second opinion only works if it comes from a genuinely different model, and how Antigravity reviews code Claude Code already approved.
MCP vs A2A: which one do you actually need?
Confused by MCP and A2A? Discover the key differences between agent-to-service and agent-to-agent protocols, and find out which one you actually need today.
We've open sourced the UAIL (Universal AI Level)
Sophie Boulderstone published UAIL, a 0 to 10 scale for real AI capability. Simon Dixon on why he open sourced it on GitHub under CC BY 4.0 the same day.
The Brain: a memory system for my AI agents, and why the "why" is the bit that actually matters
The Brain: Simon's long-term memory system for AI agents, markdown files, decision cards, vector search, and sidecars, explained end to end.
MCP vs raw API: one interface you learn once, or one you rebuild every time
MCP or a raw API for agent tooling: one interface you learn once and reuse everywhere, versus one you rebuild for every service.
MCP or CLI: the right answer depends on where your agent runs
MCP or CLI for your agent's tools: it comes down to where the agent runs, your own machine or a server you don't fully control.
AI agents have a goldfish memory. Here's how to fix that.
AI agents forget past a certain point. Four ways to fix it: memory files, RAG, the file system, and observational memory, with the real tradeoffs of each.
Spend your expensive model on judgement, not on typing
How to make a scarce model's usage last: Fable plans and verifies, Sonnet or Opus does the building, same quality, far fewer tokens burned.
The Maker's Mindset: Why Small Victories Lead to Big Outcomes
Discover why small, consistent steps beat grand marketing plans. Learn how to adopt the maker's mindset to build trust and grow your business today.
Recent posts
Links
Get in touch
Send Inkie Marketing Platform a message. It goes straight to them.
About Inkie Marketing Platform
I'm Simon, and along with Sophie, we built Inkie to help small businesses, solo founders, and makers handle their marketing without the stress. We know you need to get your product in front of people, but writing copy, sourcing images, and remembering to post takes up hours you just don't have. That is why we built an AI-powered platform that plans, writes, and schedules your social media, blogs, and newsletters for just £39 a month.
We do not do complicated dashboards or confusing tech. Onboarding is a simple, human-like conversation where Inkie learns about your business and your unique voice. Our focus is making helpful tech accessible to everyone, which is why we won an Innovate UK grant to build for neurodivergent users. We want to give you tools that feel like a natural extension of your own voice, without the heavy agency price tag.
When you sign up, you are not left to figure it out alone. Every membership includes a free 45-minute 1:1 onboarding call with us to set up your content plan, alongside real-person support whenever you need a hand. We are here to keep things simple, affordable, and completely within reach so you can focus on building what you love.