Quasar IT Services - Insights https://quasaritservices.com/insights/ Quasar IT Services is a senior-only engineering consultancy for data engineering, machine learning and AI agents. We build the data platforms that make analytics trustworthy, the model lifecycles that reach production, and the agents that run on top of both. en-us Building an agent on your own data, without regretting it in six months https://quasaritservices.com/insights/building-agents-on-your-own-data-with-langchain/ https://quasaritservices.com/insights/building-agents-on-your-own-data-with-langchain/ Fri, 23 Oct 2026 09:00:00 GMT LangChain will get you a working agent on your data in an afternoon. The question is whether you can still change it in half a year. Here is where we draw the line. What the Databricks agent features actually give you https://quasaritservices.com/insights/what-databricks-agent-features-actually-give-you/ https://quasaritservices.com/insights/what-databricks-agent-features-actually-give-you/ Fri, 23 Oct 2026 09:00:00 GMT The platform now covers tools, retrieval, serving, tracing and evaluation. It does not cover the three things that decide whether your agent survives contact with production. Your multi-agent system probably doesn't need five agents https://quasaritservices.com/insights/your-multi-agent-system-does-not-need-five-agents/ https://quasaritservices.com/insights/your-multi-agent-system-does-not-need-five-agents/ Thu, 24 Sep 2026 09:00:00 GMT Every agent you add multiplies latency, cost and the number of ways the system can be confidently wrong. Here is the test we apply before adding a second one. A model registry is not a folder https://quasaritservices.com/insights/a-model-registry-is-not-a-folder/ https://quasaritservices.com/insights/a-model-registry-is-not-a-folder/ Thu, 10 Sep 2026 09:00:00 GMT Most enterprise ML teams have tracking and think they have a lifecycle. The gap shows up the first time someone asks which model is in production and who approved it.