tamer.ai blog Field notes on agentic engineering, kernel sandboxes and human-in-the-loop AI for coding agents. https://tamer.ai/en/blog/ 2026-05-07T00:00:00Z tamer team https://tamer.ai BSL 1.1 — Apache 2.0 after 4 years Why your AI agent is silently degrading your codebase https://tamer.ai/en/blog/2026-05-07-why-your-ai-agent-is-silently-degrading-your-codebase/ 2026-05-07T00:00:00Z 2026-05-07T00:00:00Z tamer team 75% of AI agents see their regression rate grow over time. Here's how to avoid it. Spec is the bottleneck, not the model https://tamer.ai/en/blog/2026-05-05-spec-is-the-bottleneck/ 2026-05-05T00:00:00Z 2026-05-05T00:00:00Z tamer team Once model capability passes a threshold, code quality depends on the completeness of the specification — not the intelligence of the model. A field note from tamer's design log.