Blog

Agentic memory: what agents should and shouldn't remember

Agentic memory: what agents should and shouldn't remember

2026-04-10 · 11 min

Conversation state and retrieved context lead naturally into memory, but only if we're clear about what memory is for. Rules, skills, and instruction files package what you already know. Memory should capture what the work itself teaches the system, and that means reflection, verification, and forgetting matter just as much as recall.

AGENTS.md and SKILL.md: building a reusable agent toolbox

AGENTS.md and SKILL.md: building a reusable agent toolbox

2026-04-08 · 19 min

Context engineering gets more useful when the knowledge it depends on is packaged for reuse. In this post I map the portable core (AGENTS.md and SKILL.md), Copilot-specific concepts like custom instructions, agents and prompt files, and how to decide what knowledge belongs where.

Context engineering: more context isn't better context

Context engineering: more context isn't better context

2026-04-05 · 15 min

Better prompts help, but they're only part of the story. Context engineering is the craft of designing what an AI agent sees, when it sees it, and how that changes across the session. The goal isn't a bigger context window. It's a more effective one.

The DevRel randomisation trap (and how to stop it)

2026-03-31 · 20 min

There's a pattern I've seen play out across dozens of DevRel conversations, confirmed in my MBA dissertation research: teams without a clear golden thread from company strategy to daily activity get 'randomised' by whoever asks most urgently. Here's what the research says about why it happens and how to build your way out of it.

The feedback loop: how DevRel bridges community and product

2026-03-22 · 11 min

DevRel is often framed as the voice of the developer. My research suggests a broader job: gathering representative feedback, reducing friction, and showing developers what changed.

From tactics to strategy: the DevRel measurement gap

2026-03-22 · 15 min

Of the 13 DevRel leaders I interviewed for my MBA dissertation, only two could clearly demonstrate a coherent link between tactical activity and organisational strategy. In this post, I talk through how focusing on the developer journey can help bridge that gap.

Why developer communities are not brand communities

2026-03-21 · 12 min

Academic research on brand communities can help DevRel, but only up to a point. The bigger lesson is where the model breaks: developer communities run on trust in the technology, not loyalty to the brand.

Company context: the conditions that shape DevRel strategy

2026-03-19 · 11 min

Two companies can have similarly capable DevRel teams doing similar work and still get different results. In my research, company type, lifecycle stage, and technology cycles kept shaping what DevRel could realistically do.

The four pillars of DevRel (and the foundation they rest on)

2026-03-16 · 16 min

Education. Success. Marketing. Programs. These four pillars describe what Developer Relations teams do. But the more important question is what makes that work credible, useful, and trusted by developers.