The Firetiger Blog

Subscribe

Latest — 22 Apr 2026

Firetiger Change Monitors: does your PR do what it says on the tin?

Today, we're making Change Monitors generally available for all Firetiger customers. Change Monitors turn every pull request into a per-change safety net: an agent reads the diff, studies the systems it touches, and drafts a targeted monitoring plan while the code is still in review. When the PR

More posts

Object store as a primitive for Agent runtime

In this article, we are presenting how Firetiger uses S3 and Lambda as the core primitives for the development of long-horizon agents. Our agents run 24/7, tirelessly helping software engineer with production operations, from monitoring deployments to joining the incident response team when problems unexpectedly hit. I've

Agent SLOs: Grounding autonomous agents in metrics that matter

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

Claude Code, meet the Firetiger plugin! Giving Claude Code super powers in prod

Firetiger makes software in production should be self-operating and self-improving. Our agents understand your observability data, codebase, and the outcomes you care about, and make sure they come true. Think of our agents as little tooth fairies that keep the "bad news" monsters away and leave treats under

Agent Engineering Patterns: Dealing with very large tool results

Agents are models with tools in a loop. Your first job then, when building an agent, is to give them useful tools. But wasting tokens on unimportant information is catastrophic for agent brains, so you need to be careful and protect your agents from tools that can blast out 40,

We built an observability database for agents, not humans

Firetiger helps you engineer outcomes: we build AI agents that operate and improve your software. To operate and improve software, you need “observability”: visibility into what your software is actually doing. To make observability possible, you need a data layer that lets you ask questions of your telemetry: logs, metrics,

Everybody has a Datadog cost problem

Today we're announcing a new specialized agent available to use on Firetiger, designed to help platform engineering teams cut their Datadog bill in half. Datadog costs are out of control, and everyone knows it I've used Datadog since 2016 (what? 10 years now?), and from the

Give your IDE a new superpower

Firetiger is now available in the Cursor Marketplace! If you use Cursor to write code, you can now also use it to operate the software in production with Firetiger: Using our Cursor plugin, you can create agents, instrument services, and resolve issues without leaving your IDE. How do you give

Custom programming languages make agents really, really good

Agents are good at both creating and using new domain-specific languages You’re probably sleeping on how effective domain-specific languages have become in the last few months. If you’re building a product on top of LLMs and agents (and even if you aren’t, really), you should probably be

Networking with Agents: How to Put Them in the Right Conversations

We briefly considered prompting our agents with the classic networking playbook: polish the profile, craft a compelling personal narrative, ask for warm intros, comment “Insightful perspective” on questionable posts about politics in the workplace. Sadly, this did not help them reach your private Postgres database. In theory, Firetiger Database Agents