Architecture & Patterns

1+ hour, 39+ min ago   (263+ words) This article opens up that layer. Compaction, memory strategy, context budgeting, and todo-state are the machinery that turns a shallow loop into a deep agent. We look at how LangChain Deep Agents, Claude Code, Manus, OpenAI Codex, and Amazon Bedrock…...

8+ hour, 44+ min ago   (1126+ words) A short tour of everything Enverge Cloud does today: instances, the 2× DGX Spark cluster, the queue, reservations, startup scripts, SSH keys, billing, teams, usage history, and account basics. An instance is a containerized GPU sandbox running on dedicated hardware. Each…...

6+ hour, 47+ min ago   (633+ words) Each of the three Abacus.AI Smaug models targets a different slice of enterprise agentic AI work, and each is built on a different open-weight base rather than a proprietary Abacus.AI architecture. What Abacus.AI calls “Smaug” isn’t just…...

1+ hour, 35+ min ago   (504+ words) This guide compares the main modernisation strategies, when each makes sense, and how to choose. The drivers are consistent across UK enterprises: the COBOL and mainframe skills pool is retiring, mainframe operating costs are high, the systems are hard to…...

1+ hour, 36+ min ago   (1655+ words) Most teams still pick one LLM and send every request to it. That worked in 2023 when there were three viable models. In 2026, with dozens of frontier, mid-tier, and specialist models — each with different pricing, latency, and quality profiles — committing to…...

2+ hour ago   (480+ words) From a business perspective, system instability during peak usage events directly damages user retention, degrades brand trust, and triggers SLA violations. For e-commerce, financial platforms, and real-time gaming, a latency spike or dropped connection state can result in direct financial…...

2+ hour, 52+ min ago   (650+ words) The agent had been running for four hours and it was arguing with itself about a file it had already fixed. For years I'd thought about context window management as a packing problem. How do I fit more in. That…...

2+ hour, 57+ min ago   (332+ words) A polished AI-generated website can hide an unfinished delivery model. The hard question is not whether a builder can produce a convincing page. It is whether the next person can safely change the real system without reconstructing the original prompt,…...

2+ hour, 56+ min ago   (564+ words) Disclosure: I maintain Selvedge, an open-source decision-history tool. This article was prepared with AI assistance from Grok and Codex. The example below is hypothetical and uses plain Markdown; it does not require a particular product. A repository can show what…...

3+ hour, 31+ min ago   (623+ words) The agent we built in Post #4 has one big problem — the moment the script ends, it forgets everything. Next time you run it, it starts from zero. No memory of past conversations, no retained facts, nothing. For a quick experiment…...