Submissions from mendral.com

		Automating the engineering work that isn't your product (mendral.com)
		2 points by shad42 3 days ago \| past \| discuss
		How we know if our agent is right (mendral.com)
		3 points by shad42 9 days ago \| past \| discuss
		You Should Not Update Your Dependencies (mendral.com)
		29 points by OlivierCG 17 days ago \| past \| 20 comments
		Not update your dependencies in 2026 (mendral.com)
		1 point by shad42 18 days ago \| past
		Supply chain attacks don't wait for CVEs (mendral.com)
		3 points by shad42 22 days ago \| past
		We built an agent for CI despite using Claude Code for everything else (mendral.com)
		2 points by shad42 23 days ago \| past
		We built an agent specialized for CI (using the 3 Claude models) (mendral.com)
		2 points by shad42 29 days ago \| past
		How we know if our agent is right (mendral.com)
		2 points by shad42 34 days ago \| past
		How we know if our agent is right (mendral.com)
		5 points by shad42 40 days ago \| past
		The agent harness belongs outside the sandbox (mendral.com)
		182 points by shad42 42 days ago \| past \| 121 comments
		We decreased our LLM costs with Opus (mendral.com)
		106 points by shad42 46 days ago \| past \| 31 comments
		Multi-player agents don't fit in the sandbox (mendral.com)
		2 points by shad42 49 days ago \| past
		Agent Harness: Inside vs. Outside the Sandbox (mendral.com)
		3 points by MangledDeutz 57 days ago \| past
		We built our AI agent, for analyzing CI logs (mendral.com)
		1 point by shad42 59 days ago \| past
		Same LLM, different agent: a CI debugger built on Claude (mendral.com)
		2 points by shad42 60 days ago \| past
		Agent Harness: Inside vs. Outside the Sandbox (mendral.com)
		3 points by shad42 63 days ago \| past
		Same LLM but different output: we built a CI specialist (mendral.com)
		1 point by shad42 67 days ago \| past
		We upgraded our agent to Opus and our costs went down (mendral.com)
		2 points by shad42 68 days ago \| past
		Same LLM, Different Agent: What Changes When You Specialize for CI (mendral.com)
		3 points by shad42 75 days ago \| past
		We decreased our LLM costs by switching to Opus (mendral.com)
		2 points by shad42 85 days ago \| past
		What CI looks like at a 100-person team (PostHog) (mendral.com)
		56 points by shad42 3 months ago \| past \| 30 comments
		We Built Our AI Agent (mendral.com)
		2 points by aluzzardi 3 months ago \| past
		We upgraded to a frontier model and our costs went down (mendral.com)
		1 point by shad42 3 months ago \| past
		Our Agent's Most Important Job Is Deciding Not to Think (mendral.com)
		4 points by aluzzardi 3 months ago \| past
		We gave terabytes of CI logs to an LLM (mendral.com)
		233 points by shad42 3 months ago \| past \| 111 comments
		Anatomy of a Production AI Agent (mendral.com)
		2 points by shad42 3 months ago \| past
		What CI Looks Like at a 100-Person Team (mendral.com)
		3 points by shad42 3 months ago \| past
		What CI looks like at a 100-person team (mendral.com)
		4 points by shad42 4 months ago \| past
		LLMs Are Good at SQL. We Gave Ours Terabytes of CI Logs (mendral.com)
		19 points by aluzzardi 4 months ago \| past