I design and ship production-grade AI agents that take real workflows off your team and keep running when it matters. Available for select engagements.https://anasnisar.com/https://anasnisar.com/writing/keeping-agents-fast/https://anasnisar.com/writing/keeping-agents-fast/An agent that's correct but slow loses to one that's slightly worse and snappy. Most latency in agent systems is self-inflicted — here's where it hides.Tue, 09 Jun 2026 00:00:00 GMTPerformancehttps://anasnisar.com/writing/observability-for-agents/https://anasnisar.com/writing/observability-for-agents/When an orchestrator hands off to a sub-agent that calls a tool that calls a model, 'it gave a bad answer' isn't a bug report. Here's the instrumentation that turns it into one.Thu, 07 May 2026 00:00:00 GMTObservabilityhttps://anasnisar.com/writing/memory-is-not-context/https://anasnisar.com/writing/memory-is-not-context/Conflating long-term memory with live state is the fastest way to make an agent confidently wrong. The fix is a hard line between what the agent recalls and what it looks up.Thu, 16 Apr 2026 00:00:00 GMTMemoryhttps://anasnisar.com/writing/facts-affordances-pertinence/https://anasnisar.com/writing/facts-affordances-pertinence/Two failure modes haunt every agent: it makes up things that aren't true, and it nags about things at the wrong moment. Both come from putting the wrong decision in the wrong place.Thu, 26 Mar 2026 00:00:00 GMTDesignhttps://anasnisar.com/writing/the-context-ladder/https://anasnisar.com/writing/the-context-ladder/Most agent bugs aren't reasoning failures. They're context failures — the model was asked to answer without the one fact it needed, or drowned in ten it didn't.Thu, 05 Mar 2026 00:00:00 GMTContext