For most people, ideas used to die before they were ever built.

… “How are you actually going to build this?”

And we didn’t have a real answer.

Fast forward to today, that exact situation looks very different.

If you have an idea now, you don’t immediately worry about whether you can build it or not. You open an AI tool, start describing what you want, explore possibilities, and within minutes, you have something that resembles a working prototype. The barrier between imagination and execution has almost disappeared.

This shift is what we call vibe engineering. — Read More

In complex, long-running agentic systems, maintaining alignment and coherent reasoning between agents requires careful design. In this second article of our series, we explore these challenges and the mechanisms we built to keep teams of agents working productively over long time spans. We present a range of complementary techniques that balance the conflicting requirements of continuity and creativity.

… Language model APIs are stateless: to provide continuity between requests, the caller must provide the complete message history with each request. Agent frameworks solve the state management problem for users by accumulating message history between API calls. This fills the agent’s context window, which provides a hard limit on how much information the agent can handle. Even approaching an agent’s context window limit can degrade the quality of responses. For short-run applications, no extra context window management is typically required.

Complex security investigations can span hundreds of inference requests and generate megabytes of output, requiring special handling. Multi-agent applications, like ours, add further complexities. For each agent to optimally execute its role, it requires a tailored view of the investigation state. Each view must be carefully balanced. If agents are not anchored to the wider team, the investigation will be disconnected and incoherent. Conversely, sharing too much information stifles creativity and encourages confirmation bias.

Our solution uses three complementary context channels: Director’s Journal, Critic’s review and Critic’s Timeline. — Read More

Earlier Article

Back in October, my AI assistant stored a memory with an importance score of 8/10. Content: “Investigating Bun.js as a potential runtime swap.”

I never actually switched to Bun. To be fair, it was a two-day curiosity that went nowhere. But this memory persisted for six months, popping up each time I asked about my build process and quietly pushing the AI toward a Bun solution with confidence.

There was nothing wrong with the system; it was doing exactly what it was supposed to do. That was the issue. — Read More

Skills have become one of the most used extension points in agents. They’re flexible, easy to make, and simple to distribute.XXXXBut this flexibility also makes it hard to know what good and what works. What type of skills are worth making? What’s the secret to writing a good skill? When do you share them with others?

I have been using skills extensively with many of them in active use. Here are some tips I’ve learned along the way. — Read More

Most AI agents fail in production not because the model is bad, but because keeping them running reliably costs months of engineering work that has nothing to do with the actual agent. Sandboxed containers, credential handling, state management, error recovery, all of it falls on your team before a single user ever sees the thing.

On April 8, 2026, Anthropic launched Claude Managed Agents in public beta, and the core pitch is simple: they handle that infrastructure layer, you handle the agent logic. — Read More

A beginner-friendly guide for developers who want to actually understand what they are building.

… There are numerous terms:

LLM, agents, vector databases, tokens, embeddings, RAG, and fine-tuning
Additionally, the majority of tutorials skip over the basics and start building chatbots right away.

The truth is simple:

AI becomes much easier once you understand the core concepts. — Read More

Most agentic AI systems are built pattern by pattern, decision by decision, without any governing framework for how the agent should reason, act, recover from errors, or hand off work to other agents. Without structure, agent behavior is hard to predict, harder to debug, and nearly impossible to improve systematically. The problem compounds in multi-step workflows, where a bad decision early in a run affects every step that follows.

Agentic design patterns are reusable approaches for recurring problems in agentic system design. They help establish how an agent reasons before acting, how it evaluates its own outputs, how it selects and calls tools, how multiple agents divide responsibility, and when a human needs to be in the loop. Choosing the right pattern for a given task is what makes agent behavior predictable, debuggable, and composable as requirements grow.

This article offers a practical roadmap to understanding agentic AI design patterns. It explains why pattern selection is an architectural decision and then works through the core agentic design patterns used in production today. For each, it covers when the pattern fits, what trade-offs it carries, and how patterns layer together in real systems. — Read More

Companies building for agents often treat them as a bolt-on feature.

This is a mistake.

Agents today are more like a new form factor – an interaction layer that sits between your product and your users.

That means you need to build for agents as a primary surface, not an afterthought.

… We learned this the hard way and overhauled our AI architecture two times in the last year. Now, our agent and MCP have 6K+ daily active users.

Here are the golden rules of agent-first product engineering we learned along the way.

1. Let agents do everything users can
2. Meet agents at their level of abstraction
3. Front-load universal context
4. Writing skills is a human skill
5. Treat agents like real users

Read More

Coding agents working from code alone generate shallow hypotheses. Adding a research phase — arxiv papers, competing forks, other backends — produced 5 kernel fusions that made llama.cpp CPU inference 15% faster.

Coding agents generate better optimizations when they read papers and study competing projects before touching code. We added a literature search phase to the autoresearch / pi-autoresearch loop, pointed it at llama.cpp with 4 cloud VMs, and in ~3 hours it produced 5 optimizations that made flash attention text generation +15% faster on x86 and +5% faster on ARM (TinyLlama 1.1B). The full setup works with any project that has a benchmark and test suite. — Read More

The practices that make human pair programming effective—onboarding, structured design discussion, shared standards—apply equally to working with AI coding assistants. I propose five patterns that bring this collaborative scaffolding to AI-assisted development, shifting the experience from correcting a tool to collaborating with a capable teammate.

PATTERNS
Knowledge Priming
Design-First Collaboration
Context Anchoring
Encoding Team Standards
Feedback Flywheel

— Read More