- AI Marketing Stacks That Don't Suck
An opinionated listicle: the components of an AI marketing stack we would actually trust an in-house team to run.
Editorial Team
·
- On-call runbooks for AI products — the new incident class
Ginger Wolfe-Suarez
·
- Inside the Tooling Choices of Twelve Frontier AI Teams
A survey piece on what tooling the better-known agentic teams are actually running with — drawn from public writeups, conversations, and our own audits.
Editorial Team
·
- Rust for high-throughput agent runners — when it's worth it
Editorial Team
·
- Claude Code vs Cursor vs Copilot Workspace — Q2 2026
Three coding agents, three different bets on where the IDE is going. What each ships, where each fails, and a team-size matrix that we actually use when somebody asks.
Reza Mokhtari
·
- What 'AI Agency' Actually Means in 2026
An essay on what has changed in the term 'AI agency' since 2023 — and what to look for if you are hiring one.
Editorial Team
·
- OpenTelemetry for LLM applications — instrumentation patterns
Reza Mokhtari
·
- The Open-Source Agent Stack — OpenHands, Aider, Continue, Cline
Four open-source coding agents, four different shapes of the same bet — that bring-your-own-model is the more durable architecture. A practitioner comparison.
Reza Mokhtari
·
- Fine-tuning vs prompt engineering — a cost/quality decision tree
Ginger Wolfe-Suarez
·
- The 2026 Agentic Stack Survey: What Teams Are Actually Running
A practitioner-side landscape map of the agentic stack as actually shipped — not the slide-deck version.
Editorial Team
·
- GraphRAG vs. plain RAG vs. hybrid — measured on real corpora
Editorial Team
·
- Eight Open-Source Tools Every Agentic Engineer Should Know
Categories of open-source tooling we keep reaching for. Not a ranking — a working kit.
Editorial Team
·
- Prometheus + LLM observability — the cardinality problem
Reza Mokhtari
·
- Building a Marketing Agent: A Walkthrough
An end-to-end tutorial: a single specialist agent that takes a brief, drafts a blog post, runs it past an editor, and returns a result you can ship.
Reza Mokhtari
·
- dbt-Cloud agents — when warehouse-side LLM calls beat application-side
Ginger Wolfe-Suarez
·
- Vibe Coding for Teams — From Karpathy's Tweet to Production
Karpathy named it in a tweet. Eighteen months later there are job postings, magazines, and a quiet generation of slop. What it takes to do this on a team without producing the bad version.
Ginger Wolfe-Suarez
·
- k8s for AI workloads — node autoscaling for variable inference
Reza Mokhtari
·
- The Quiet Power of Vertical Agentic Agencies
An essay on a category that gets less press than it should: the small, vertical-focused agency running on its own agentic platform.
Ginger Wolfe-Suarez
·
- Vector DB benchmarks: Qdrant, Weaviate, Pinecone, pgvector under real load
Editorial Team
·
- MCP in Anger: One Year of Building With the Protocol
A practitioner essay on what the Model Context Protocol gets right, where it gets ugly, and what it has cost us to ship on it.
Reza Mokhtari
·
- Embedding drift in production — what actually moves and how to detect it
Reza Mokhtari
·