The third MCP server was reasonable. The rest were not
MCP was the right answer for giving an agent a project's documentation. As the count grew, the servers themselves became the thing needing maintenance.
Tag
The PostgreSQL database: index strategies, the query planner, vacuum and performance.
There are 4 posts with this tag.
MCP was the right answer for giving an agent a project's documentation. As the count grew, the servers themselves became the thing needing maintenance.
RAG or fine-tuning gets answered everywhere. The three questions left after it — the key, the model choice, the budget — get answered nowhere.
Two phases of the same run measured the same service three times apart. What caught the wrong one was not a better statistic but a second method.
Four index strategies on a 10M-row Postgres queue table: the winner didn't win for the reason I gave, and one setting turned it into a 1,635x loss.