https://blog.redgold.ai/Field notes from running coding agents, an LLM gateway and a data engine in production.https://blog.redgold.ai/prompt-cache-warm-while-rewriting-requestshttps://blog.redgold.ai/prompt-cache-warm-while-rewriting-requestsThu, 22 Oct 2026 12:00:00 GMTOur gateway adds context to every agent request so the agent knows who it is working for, which repositories and apps exist, and what the project’s rules are. Here is why that context matters, and how we add it without paying full price for the prompt each time.https://blog.redgold.ai/what-twenty-coding-agents-taught-us-about-supervisionhttps://blog.redgold.ai/what-twenty-coding-agents-taught-us-about-supervisionThu, 22 Oct 2026 12:00:00 GMTOne person, around twenty coding agents, one issue board. What the human actually does all day, what went wrong before each rule existed, and the numbers from running it.