Tag
#ai-agents
5 posts
Empathy at Scale: How an LLM Judge Improves Our Atlan MCP Server
How an LLM judge improves the Atlan MCP server with empathy at scale: it scores every outcome, and a loop turns failures into shipped fixes.
Evolving the infrastructure behind 600+ customer instances with an agent
The structural problem we found in how our catalog stored its data, how we redesigned for it, and how an agent scaled that fix across 600+ live customer instances.
Building a User Value Loop for MCP: What Traces Can't Tell You
Every tool call can succeed and the user can still get nothing. How and why we built a user value loop for the Atlan MCP server, and what it told us.
Loop Engineering in Production: Putting AI Agents on Call
We had an agent loop running in early 2026, and it still failed. Here is the scaffolding that made Sherlock, our investigation agent, useful in real incidents: 85% of the roughly 11,000 alerts a month suppressed as noise before a model ever runs, and investigations that once took 10+ minutes now finish in about 2 minutes on average, for less than a third of the cost.
Olof: How an AI Queue Manager Rebuilt Support Engineering at Atlan
On a typical weekday, our support engineers at Atlan used to start their shift in Zendesk with a familiar feeling: too many tickets, not enough clarity. Someone from the team was always wearing an…