Theo Luan

So proud of the team - by far the most exceptional group of people I’ve worked with!

@amanshresthaaaa @LLMJunky this is fixed btw in case you havent run a mission recently

@droid_35719 @LLMJunky Bug: Could you fix the time. And only count when it’s running? Not when it’s on pause. One of the missions shows 35 hours. 😅 i paused and resumed.

Trying out Droid Factory Missions for the first time. Kinda excited. Anyone else out there using this? What is your experience?

They don't talk loud. They speak with the work. Matan and 20 engineers at Factory just raised $150M at a $1.5B valuation, and the industry is still catching up to what they've shipped. Long context compression: I pushed 40+ million tokens in a single session without starting a new chat. The agent held the thread the whole way. Every lab has since shipped some version of it. Factory did it first and barely mentioned it. Missions: Droid can ship software across days. The codebase comes out cleaner than it went in (tests passing, edges handled, the kind of work a good engineer does at the end of a long week). Agent Readiness: A framework for whether your codebase is even ready for agents. If you've wondered why AI coding tools feel uneven across projects, this is the answer. The environment around the agent is usually the bottleneck. In three years, 20 people are outpacing AI agent innovations from frontier labs with millions in capital plus hundreds of employees. If you're building with AI, spend a weekend with Droid. It cooooooks!

@geo_anima @FactoryAI makes sense. there should be some low-lift changes we can make to address this

@droid_35719 I've used @FactoryAI's Droid Missions for 40+ days. My one issue is that a mission may build too much validation scaffolding and too little product - going disproportionately wide by anticipating too many edge cases instead of focusing more on making the core thing work first.

We built Missions at Factory, and I wrote about the architecture that I led the design for to make multi-day autonomous coding reliable. Agents are highly reactive to their context. Every design decision follows from keeping each agent's trajectory focused and directionally consistent.

@RayFernando1337 appreciate you Ray

This is probably one of the most legendary blog posts of our time, and if you are an AI lab, you must study this.

The post explains our design rationale, how missions actually run, and breaks down a real 16.5-hour mission: 185 agent runs, 778M tokens, 89% test coverage. factory.ai/news/missions-…

Today we're releasing the Factory desktop app. A native interface for autonomous AI agents that work across every part of your software business.

@VictorTaelin give factory.ai/news/missions a try. we can give you some tokens, dm me.

Sad to report that, as of March 2026, just prompting agents to implement a termination checker will not work. Even GPT 5.4 Pro's plan is just... bad. Just bad. It seems like I'm gonna need to code this on my own, and my brain is spoiled and lazy from so much vibe coding

@HarryStuck77 @droid hey - just to clarify, do you mean validator rows rendered in a diff color?

Would be great to see in Progress Log the Validators steps (maybe in a color) @droid

@amanshresthaaaa @LLMJunky there's a ticket for this rn - will update you when it's done

@LLMJunky @amanshresthaaaa nice.

@droid_35719 @amanshresthaaaa that was exactly it, and i couldn't get back there bc CTRL+T in Ghostty was just creating new tabs. I fixed it! and its working. Thanks legend. Its working!!

@LLMJunky @amanshresthaaaa hey - can you go back to the orchestrator session with ctrl+t? wondering if it paused to ask you a question?

@amanshresthaaaa i cant even get mine to finish just hangs

@tdh_02 @droid hi, sorry about this. could you DM me with more details?

Anyone else feeling like @droid is just becoming unusable for Missions? ou simply can't leave them unattended due to the amount of starts/restarts required - and lost tokens (which aren't cheap from Droid!)

@prathamdby @FactoryAI ty for the report. will update you when we’ve fixed this

@droid_35719 @FactoryAI Hi @droid_35719, it didn't fix it sadly.

.@FactoryAI Yo guys, can you help out here? I'm on the latest version of Droid here and missions are just refusing to launch, no matter what I do, I've tried 2–3 times already and restarted Droid countless times.

@yigitkonur @matanSF available now on pro plan

@matanSF let others to use mission at least for few rounds on non-200$ packages sirrr

at this point, it is borderline negligence as a dev to not have droids working for you while you are sleeping

@justBill @matanSF Yep

@matanSF Can you use BYOK for missions?

@mhadtk @0xSero hi Pham - are you referring to lagginess of the mission control interface itself?

@0xSero My mission gets slower and slower after each worker deployed and time. Do you go through same experiment?

The mission is 8% done, and it's already been 5 hours. I think this is the coolest one shot experience I've seen. Okay, this is wildly better than anything else I've tried. the tests are so logical, it's using the browser to validate the UX, it's doing real quantizations. It's been at it for 5 hours, and there's nothing in there that doesn't make sense from a tool use, and trajectory perspective. I built Orchestra 3 months ago, it's similar to oh-my-opencode and gas-town. It worked but it sucked, I couldn't get it to make sense so I dropped it and haven't touched any orchestration tools since. ---------------------------------------- why is it so good? because they're not leaving it up to the model to decide, I see the way they frame prompts and separate sessions, it's all running like a factory lol. Very impressed.