Today we're introducing @usefiretiger. You and your AI agents write code. Firetiger makes sure it works.

Our team and I have plenty of incident war stories building @Cloudflare, @segment, @Twitch. In the agentic coding era, the volume of code changes + quality issues in prod is ever increasing, but observability vendors aren't incentivized to close the gap. They make money when you write more data to them, not when your software actually works.

Firetiger is the agentic operations layer for the agentic coding era. We combine production observability data, codebase understanding, and knowledge of your business to find problems before your customers do and fix them before they notice.

We've raised $7.6 million led by @sequoia with participation from angels who believe in better software, including @eastdakota, @calvinfo, @NicoRosberg, @dok2001, @jeffawilke, and @alanaagoyal.

You can sign up for @usefiretiger today, self serve. We charge for agents that directly make your software better and more reliable, not for observability data ingested, with plans starting at $599/month.

Observability is dead. Long live outcome engineering.

Quest Diagnostics has been hacked. Patient data was exposed. They serve roughly half of U.S. hospitals and physicians. Investigation ongoing.

s tier list

the real bitter lesson

!

More and more of our production debugging at SpaceXAI now starts in Slack, with an agent.

An alert fires, and the agent is already watching the channel. It reads logs, metrics, errors, and code, then replies in the thread with what broke and why. Often we read its answer before we open a single dashboard.

We're now letting a few teams outside SpaceXAI add this debugging agent to their own Slack. If you want early access for your team, reply or DM me! 👇

@lalkaka @usefiretiger @cursor_ai Congrats on an incredible run & team you built!! The Cursor team is lucky to have you. The building will never stop 💪

We’re excited to welcome the Firetiger team to Cursor!

Together, we're building agents that can follow their work into production and fix what goes wrong.

cursor.com/blog/firetiger

Today, we’re announcing that @usefiretiger is joining @cursor_ai.

Together with Cursor, we can combine the loops driving development and production, and automate the process of software engineering end-to-end.

Thank you to everybody who used Firetiger in its current incarnation. It has been a privilege building and learning at the frontier with you.

We can’t wait to show you what we’re up to next :)

first of a few medium deep dives on how our @usefiretiger agent harness supports determinism when we need it, advanced context management, and more.

excited to cover things we got right, screwed up, etc in the next posts

blog.firetiger.com/nxl-a-declarat…

new integration dropped: @cognition @DevinCow is now the 7th coding agent @usefiretiger can dispatch an issue to (joining @cursor_ai, @tembo, @tryreplicas, and others).

issues get sent to agents with issue evidence attached so agents start from root cause.

found a live seal worm/anisakis 🪱 in some fish AMA.

@mattpocockuk the model is able to work some magic when it has jaeger

Let’s get this started 🚀 @aiDotEngineer

@typesfast i think it's a GDPR thing

outcomemaxxing the new tokenmaxxing. where’s the leaderboard

Introducing Horizon from @0rinlabs: the first long-horizon learning benchmark made from real agent logs

- SOTA is 21% on the hardest section
- 7-35M tokens of real agent history per task
- Models are hardly getting better on the hardest tasks
- Humans can score 100%

(1/7)

@lalkaka @deepseek_ai @usefiretiger Great writeup. There will be a number of teams following in your footsteps in the coming months!

When paired with the right context engineering, open-weight models have become good enough that they can match the quality of frontier models for certain tasks.

This is the story of how we migrated our core product from Claude to Deepseek ↓

claude->deepseek: we cut token costs by 60%+ and maintained quality, all without a ton of eng effort.

a little story about our migration from claude to @deepseek_ai to power parts of @usefiretiger 's agent stack: blog.firetiger.com/migrating-from…

@ritakozlov if you eat the best food first you’re always eating your best food! been meaning to write a linkedin post about my philosophy on this.