Assembling @droid, the frontier software development agent. Available to anyone, with any model, in any IDE/terminal.factory.com curl -L app.factory.ai/cli |shJoined April 2023
@tadasayy We think what people tend to overlook is the potential speed improvement and keeping the same quality & performance.
It's not just about cost-saving, but about overall better way to use AI.
Introducing model routing to Factory.
Factory Router picks the right model for every task, automatically.
Maintain frontier performance while cutting costs by 25%.
Introducing model routing to Factory.
Factory Router picks the right model for every task, automatically.
Maintain frontier performance while cutting costs by 25%.
@mattlam_@GergelyOrosz Can't speak for others, but Factory Router is customizable, so you can set up preferences for your teams or individuals.
We can also automatically route for example if one provider has a downtime.
I'm speaking at Snowflake Dev Day about the infrastructure shift required to support autonomous engineering at scale.
I will be talking about
- How enterprises keep using frontier models without burning so much cash
- What adopting AI really does to the organization
- What will happen to software engineers
Every engineering org is trying to figure out what their software factory will look like. Come hear more about how we’re thinking about it!
Each enterprise I've spoken to is spending their AI token budget quicker than they anticipate... @FactoryAI and @matanSF just came out with model routing which will help lower costs and save tokens without sacrificing performance. Will be huge as AI spend continues to explode!
Loving all the research coming out of @harvey, @FactoryAI etc right now
The earliest set of application companies are undergoing the evolution from pure app layer to serious research organizations.
A sign of things to come.
@SirUnco@MiclauMarius Neither. The model switch happens in the cases where one model shows as not sufficient to complete the task.
Factory Router is customizable and can have different model preferences for different teams and team members.
10K Followers 704 FollowingCEO at https://t.co/YKizWZdxjK ($7M ARR). Helping GTM teams scale with AI & Tech: https://t.co/Vooe1yaqqx.
Connect:
https://t.co/VCBGhgKTW7
https://t.co/PhINKB8p78
157 Followers 2K FollowingOpen to new roles in AI Infrastructure | Site Reliability Engineer | DevOps Engineer | Opinions are my own | prev. @zendesk , @oracle , @netsdanmark
363 Followers 2K FollowingBrand Engineer // Full-stack Design & Development // Founded @hi_commonwealth // One Membership. Every Service. No Limitations.
4K Followers 4K FollowingDispatches from the future we were promised. 📕Rethinking Cyber Warfare @OxUniPress. 🏛️ @MIT, @BrookingsInst. ⏪ Once upon a time @WhiteHouse & @StateDept.
542 Followers 1K FollowingIndian 🇮🇳 🔥| e/acc | Spaceflight Fan | Pursuing a Diploma in Mechanical Engineering | Founder/CEO of fictional space company @AgniteSpaceJNO
470 Followers 174 FollowingBuilding Aigon — multi-agent orchestration for AI coding agents. Sen Labs. Previously Head of Eng Atlassian, Snr Director of Engineering Zendesk
522 Followers 1K FollowingDefining the AI-native infrastructure layer—how intelligent systems should be built, operated, and evolved safely at planetary scale. Ex Salesforce, Microsoft
347 Followers 2K FollowingMTS @FactoryAI. I code often and sleep occasionally. I like systems. Agents are graphs. Harness is everything. Views are my own. #2 fan of Corvus Corax