Agent Month — WritingDeep technical writing on LLM cost optimization, agent infrastructure, evals, and MCP.https://agentmonth.com/en-usStandardizing AI coding tools without killing autonomyhttps://agentmonth.com/blog/standardize-ai-coding-without-killing-autonomy/https://agentmonth.com/blog/standardize-ai-coding-without-killing-autonomy/How DevEx and platform leaders turn a Claude Code / Cursor / Copilot free-for-all into a golden path — shared slash commands, agent definitions, MCP access, and review hooks — without mandating a single way to work.Thu, 25 Jun 2026 00:00:00 GMTdevexplatformgolden-pathThe “add AI” mandate: a CTO’s first 90 dayshttps://agentmonth.com/blog/cto-add-ai-mandate/https://agentmonth.com/blog/cto-add-ai-mandate/The board wants AI in the product and you have to commit before the bets are proven. A sequencing playbook for CTOs — what to ship first, how to handle build-vs-buy, and how to keep costs forecastable.Wed, 24 Jun 2026 00:00:00 GMTctostrategysequencingSecuring AI-generated code: a checklist for security leadershttps://agentmonth.com/blog/securing-ai-generated-code/https://agentmonth.com/blog/securing-ai-generated-code/AI is writing code faster than anyone can review it. A practical checklist for CISOs and AppSec leaders to control AI-generated code, prompt data leakage, and new injection surfaces — without slowing the team down.Mon, 22 Jun 2026 00:00:00 GMTsecurityai-codechecklistYou shipped AI features with no evals. Here’s how to fix that.https://agentmonth.com/blog/you-shipped-ai-with-no-evals/https://agentmonth.com/blog/you-shipped-ai-with-no-evals/Most teams shipped production AI with zero evaluation. This is how to add evals incrementally — without stopping the roadmap — so prompt and model changes stop being blind deploys.Thu, 18 Jun 2026 00:00:00 GMTevalsqualityci-cdIs your codebase agent-ready? A scoring rubrichttps://agentmonth.com/blog/is-your-codebase-agent-ready/https://agentmonth.com/blog/is-your-codebase-agent-ready/Agents thrive in some codebases and thrash in others. Here is the rubric we use to score how ready a codebase is for agentic development — and what to fix first.Tue, 02 Jun 2026 00:00:00 GMTagentic-devcodebaserubricHow to cut LLM costs 30–60% without losing qualityhttps://agentmonth.com/blog/cut-llm-costs-without-losing-quality/https://agentmonth.com/blog/cut-llm-costs-without-losing-quality/A practical, vendor-agnostic playbook for finding and removing 30–60% of your production LLM spend — model routing, caching, batching, and the observability to keep it gone.Tue, 12 May 2026 00:00:00 GMTllm-costsobservabilityplaybook