Igor Ostrovsky

Augment Code (@augmentcode) Co-Founder. Building Cosmos, a platform for software factories.

[Igor Ostrovsky @igoro]

Software factories accelerate software development, but the hard part is trust.

That’s why Harness + Cosmos makes so much sense: factories that move fast, with delivery and governance teams can trust.

Matt’s update: https://t.co/ukdpaNaqTc

[Igor Ostrovsky @igoro]

Maybe it's just me, but I'm finding GPT 5.6 Luna Max to be good enough for most of my coding tasks

[Igor Ostrovsky @igoro]

@petergyang Software factory still has humans in the loop!
https://t.co/xS0Wd1JyDm

[Igor Ostrovsky @igoro]

You can set up a real software factory in ~10 clicks and a single conversation with Cosmos Advisor.

[Augment Code by Harness @augmentcode]

Quick start: a software factory in Cosmos is two screens and one prompt.

1. Connect your repo
2. Create an environment
3. Describe the factory you want

Advisor picks the experts, writes the configs, applies them, and asks you when it needs a decision.

[Igor Ostrovsky @igoro]

Why bug fixing is the least important part of a bug-fixing software factory

Software factories are very effective at burning down issue backlogs, but it's primarily NOT about the fix implementation.

See the next article in my series on software factories:

https://t.co/r61xAwHAET

[Igor Ostrovsky @igoro]

Cloudflare, Vercel, Uber, LaunchDarkly, and others are building software factories.

I looked at how they work, the results so far, and what's next: will agents be prompting us?

https://t.co/AOlCfi2osU

[Igor Ostrovsky @igoro]

Augment Cosmos.

You just talk to the Cosmos Advisor agent and it will set up a software factory for you just the way you want it.

[Whole Mars Catalog @wholemars]

Has anyone tried to build self-developing apps and websites?

My concept for this is that you put some feedback form on the website where the user can report bugs or request features. Then once they hit submit, an agent reads the bug report and sees if it can diagnose and fix the bug itself and open a pull request. Or respond to the user if its user error or something.

You just have to merge pull requests in or give the model some more direction, but you could have an app or service that sort of evolved on its own organically based on user feedback even when the developer or maintainer was busy with other things.

You could imagine the user filing bug reports and having it fixed in minutes. Filing a feature request and using it a few hours later. Who knows, maybe if the model has strong judgement someday development can just proceed fully autonomously.

[Igor Ostrovsky @igoro]

@wholemars https://t.co/O9qHRNOwF3

[Igor Ostrovsky @igoro]

@GergelyOrosz @karpathy This is internal feedback on our version (Cosmos). Cloud agents + integrations + Slack.

[Igor Ostrovsky @igoro]

Mercury 2 goes brrrr! Well done, @_inception_ai.

Excited to be working with the @baseten team.

[Baseten @baseten]

We are excited to announce that we have partnered with @_inception_ai to make Mercury 2 available on Baseten. This makes us the first inference platform to bring Inception’s diffusion LLM to production.

Inception’s dLLM architecture fixes the bottlenecks of sequential token generation and can deliver 1,000+ tokens/sec on standard NVIDIA GPUs. Early users like @augmentcode have seen impressive results, such as an 82% reduction in latency and 90% cost savings, while maintaining high quality.

[Igor Ostrovsky @igoro]

Team-level agents will be the biggest change to how software is built in the second half of 2026.

https://t.co/RmkWfc86iO

[Igor Ostrovsky @igoro]

Now available to Augment Max Plan subscribers. Get it here: https://t.co/Eb9Vbo080I

[Igor Ostrovsky @igoro]

Cosmos Research Preview is here!

It is a new way to work with AI agents: as teammates with context and memory that take on larger roles, respond to events, and collaborate with you and others on the team.

[Igor Ostrovsky @igoro]

I can orchestrate complex workflows in plain English: "When that PR closes, mark this PR as ready for review and hand it off to a PR Author."

[Igor Ostrovsky @igoro]

2026 is the year software engineering flips.

Inversion of control: agents own the work and ask humans for input only when needed.

[Igor Ostrovsky @igoro]

For cyborging yourself, @reve > Nano Banana > GPT.