Morse Blog https://blog.morsehq.dev/ Engineering notes, product updates and field notes on AI-agent observability and evals, from the team building Morse. en-us Performance brief first. Traces on demand. https://blog.morsehq.dev/performance-brief-first-traces-on-demand/ https://blog.morsehq.dev/performance-brief-first-traces-on-demand/ Why Morse opens on a ranked performance brief instead of a wall of traces, and how every claim in the brief links back to the spans, logs and infra evidence you can open when you need it. product Mon, 26 Oct 2026 00:00:00 GMT LLM judges in production: sample them, don't trust them blindly https://blog.morsehq.dev/llm-judges-sample-dont-gate/ https://blog.morsehq.dev/llm-judges-sample-dont-gate/ Using a model to grade your agent's output is useful and cheap to start. Here is how to keep it honest: sample, calibrate against people, keep it apart from hard outcomes, and watch what it costs. industry Fri, 23 Oct 2026 00:00:00 GMT Staging OTLP exports on a stream before we parse them https://blog.morsehq.dev/staging-otlp-exports-on-a-stream/ https://blog.morsehq.dev/staging-otlp-exports-on-a-stream/ How Morse accepts an OpenTelemetry export fast, stages the encrypted raw bytes on a Redis Stream, and persists them in a worker. Covers the failure modes and what we chose not to build yet. engineering Thu, 22 Oct 2026 00:00:00 GMT Read agent cost and quality side by side, not as one score https://blog.morsehq.dev/cost-and-quality-side-by-side/ https://blog.morsehq.dev/cost-and-quality-side-by-side/ A single blended number for agent cost and quality feels tidy, but it hides the tradeoffs you need to see. Here is how to read them next to each other instead. industry Wed, 21 Oct 2026 00:00:00 GMT Typed spans from day one https://blog.morsehq.dev/typed-spans-from-day-one/ https://blog.morsehq.dev/typed-spans-from-day-one/ Why every span Morse stores carries a type, how OTLP and our REST path normalize into one model, and what the typing buys you once the data lands. engineering Tue, 20 Oct 2026 00:00:00 GMT What a Morse performance brief is (and what it is not) https://blog.morsehq.dev/what-is-a-performance-brief/ https://blog.morsehq.dev/what-is-a-performance-brief/ A performance brief is a ranked answer to one question: which of your production agents deserves attention first? Here is what goes into it, what stays out, and how teams use it week to week. product Tue, 20 Oct 2026 00:00:00 GMT Field notes on agent observability and evals: what this lane covers https://blog.morsehq.dev/agent-observability-and-evals-field-notes/ https://blog.morsehq.dev/agent-observability-and-evals-field-notes/ Agents moved from demos to production faster than the tools for watching them. What the industry posts will cover, and the few positions we start from. industry Mon, 19 Oct 2026 00:00:00 GMT Engineering at Morse: what this lane covers https://blog.morsehq.dev/engineering-at-morse/ https://blog.morsehq.dev/engineering-at-morse/ How we build an observability product for agents, the few rules we hold ourselves to, and what you'll read in the engineering posts. engineering Mon, 19 Oct 2026 00:00:00 GMT Hello from Morse: what the product posts will cover https://blog.morsehq.dev/hello-from-morse/ https://blog.morsehq.dev/hello-from-morse/ We're opening Morse in a soft launch this October. Here is the question the product is built around, what a performance brief is for, and what you'll read in this lane. product Mon, 19 Oct 2026 00:00:00 GMT