Risk Management for Claude Code in Big Codebases
Failure modes, blast radius, and containment patterns for running Claude Code safely in a large codebase — least privilege, diff caps, and verification gates.
7 min read
Agentic AI & LLMs
Agentic AI & LLMs archive page 64 of 631
Agentic AI & LLMs
Agentic AI, LLM engineering, and the models behind modern automation — multi-agent systems, LLM evaluation and comparisons, RAG, fine-tuning, AI infrastructure, security, and production AI engineering.
From the blog
Latest articles
Hiring for an AI-native startup: skills founders need now
The skills and roles founders must hire for to run an AI-native startup on Claude — spec-writing, evals, and agent orchestration in 2026.
8 min read
Skills Engineers Need to Use Claude Code at Scale
The concrete skills, habits, and hiring shifts engineers need to make Claude Code pay off in a large codebase — decomposition, specs, review, and verification.
8 min read
Scaling Claude agents across a company without the chaos
How founders take agentic AI from one team to many: shared skills, governed MCP infrastructure, orchestration, and the org design that prevents sprawl.
8 min read
Scaling Claude Code From One Team to Many Without Chaos
How to scale Claude Code from one team to many on a large codebase — shared skills, federated guardrails, cost control, and rollout without chaos.
7 min read
When to use AI agents — and when you really shouldn't
Honest founder trade-offs: where Claude agents clearly win, where they quietly cost more than they save, and the simpler alternatives to try first.
8 min read
When to Use Claude Code in Big Repos — and When Not To
An honest guide to when Claude Code is the right tool for a large codebase and when it isn't — the trade-offs, failure modes, and better alternatives.
7 min read
Claude Code Governance: Guardrails Before You Scale
Governance, trust, and safety guardrails engineering leaders need before scaling Claude Code: permissions, risk-based review, auditability, and ownership.
7 min read
Governance for AI agents: guardrails before you scale
The governance, trust, and safety guardrails a founder needs before scaling Claude agents: least-privilege permissions, review gates, and audit trails.
7 min read