Rustam Lalkaka

Today, we’re announcing that Firetiger is joining Cursor. We started Firetiger to tame software operations chaos with AI-powered agents, and it sounded crazy at the time! The goal: attack all measurement and remediation of software problems in production, and allow our customers to deploy fleets of agents to

A case study on production objective hill climbing Firetiger runs a few hundred large language model (LLM) agents in production, and prompt caching is a critical tool to manage the cost of running such a workload. Properly setting cache time-to-live (TTL), how long a cached prefix survives before

Today, we're making Change Monitors generally available for all Firetiger customers. Firetiger Change Monitors pair with every pull request to form a per-change safety net: an agent reads your diff, studies the systems it touches and how they behave in prod, and drafts a targeted post-deploy

Today we're shipping Agent SLOs, a new feature that gives every Firetiger agent a structured way to track the health of the missions it's assigned. Agents now define their own service level objectives (SLOs), evaluate them every session, and use those evaluations to triage the issues