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.
Blog
Posts from Inkie Marketing Platform.
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.
How Claude Code injects context: hooks, native memory, and the prompt cache
How memory actually gets into Claude Code: the CLAUDE.md trap, the SessionStart hook fix, and the real 10K-token hook limit.
Built to Work How You Work: Designing Tech Around Your Life
Tired of fighting rigid software? Learn how to design your tech stack around your unique lifestyle and workflow to reclaim your creative freedom today.
Why We're Live-Demoting Marketing AI Agents at EVOLVE Brighton Today
Join Simon Dixon at EVOLVE Brighton today as he live-demos how Inkie’s structured multi-agent AI pipeline automates small business marketing. 50% ticket discount inside!
The Digital Loom: How AI is Democratising Custom Software
Discover how AI is democratising custom software for small businesses. Learn how to build bespoke tools tailored to your unique workflows without costly fees.