
Mobile AI Lab. We train specialized models & build tools for agentic mobile development: @apex__ai + @agent_device. Hosting @AgentConf. React Native experts.
Wroclaw, Poland
Joined August 2016
- Tweets4.8K
- Following398
- Followers17.2K
- Likes3.9K
Pinned Tweet
Announcing Apex: agentic coding model for mobile and web, specialized in React.
We built Apex from a single idea: can an open-weight model deliver frontier-level performance at lower cost?
Yes. Apex is SOTA in React Native and Next.js.
Try it now: apex.callstack.com
Your team adopted AI agents. But how much work have you actually delegated?
Our new guide explains how to move more of development into agent workflows, with context, tools, and verification. React Native examples, broadly applicable practices.
Read the guide 👇
Get access here:
clstk.com/4zsj7GI
2
168
My Developer Word of the Year 2026 is “sloppy precision”. What’s yours? #DevWordOfTheYear devword.callstack.com/
there we go
Callstack Engineers retweeted
My Developer Word of the Year 2026 is “meat proxy”. What’s yours? #DevWordOfTheYear devword.callstack.com/
Callstack Engineers retweeted
When optimizing apps we often use other popular apps as baselines - so we built a benchmarking leaderboard to see how we compare!
Is your app faster? Come find out! 👇
Callstack Engineers retweeted
Excited to share that the demo of mine & @LeSiOO's, "Apex: Quantization Impact on Gemma," was featured in the latest AI Tinkerers Community Spotlights newsletter!
Thanks to @AITinkerers for the spotlight, and @callstackio for making this project happen!
What did building software feel like in 2026? Give it a word!
Nominations for Developer Word of the Year are open until 25 November. Words, phrases, and acronyms are all welcome.
Nominate yours at clstk.com/4zQYDsf
Storybook Connect gives AI story generation a defined path. The command-line tool handles repeatable steps, the agent interprets component context, and the developer controls what gets generated
🧵 1/2
1
574
The agent reads TypeScript props and applies Storybook guidance for variants, structure, mocking, and interaction tests. Discovery and scaffolding stay consistent across runs. Full case study: clstk.com/3UALdBo
🧵 2/2
184
Mobile Development, Plugins & AI-Powered Workflows www.teapawt.org/i/broadcasts/2KoOJjJVz…
At @nextappdevcon in Berlin, @satya164 explored the decisions behind React Navigation 8, from its Static API to native vs custom primitives and type-safe navigation.
Watch “Building a Modern Navigation Library: The Hard Parts” 👉 clstk.com/4k8vW56
2
518
React’s future is a conversation we want to be part of 🙌 @ChmalSzymon, @thymikee & @artus9033 are in London for the React Foundation Contributors Summit. Yesterday, Szymon also spoke at the community meetup. Thanks to the React Foundation team & @Meta for making it happen!
An agent is a model plus a harness. Test suites, feedback loops, and CI/CD help shape how it works. @AmazonAppDev’s @anisha_malde joins @lukasz_app on React Universe On Air to discuss reliable AI workflows across platforms.
Watch the full episode below 👇
Chapters:
00:00 Welcome to React Universe On Air
00:49 Introduction from Agent Conf 2026
01:26 How AI is changing developer workflows
02:33 From prompt engineering to harness engineering
04:45 Amazon Devices Builder Tools and Vega
06:29 Choosing a starting point for cross-platform development
09:30 Sharing agent workflows and domain expertise across teams
11:49 What reliable AI engineering should deliver
13:14 Maintaining technical expertise while AI writes code
16:22 Do agents still need tickets and Agile?
18:36 Context, token budgets, and familiar engineering practices
20:37 Focusing on user experience as AI handles implementation
24:08 Closing takeaways
Read full show notes and resources on our website 👇 clstk.com/4z8fTrB
if you care about AI agents fixing/verifying mobile UI cheap and fast, give them agent-device. thank us later
it's a small benchmark that shows @agent_device is fastest and one of the cheapest per task, even on cold runs.
agents using agent-device make the fewer steps to get the task done.
the bench team did extra mile to consult the methodology with me, which I deeply appreciate!
A software factory cost model projects 65% lower costs across the build and three years after launch.
What drives the forecast? Agents implement and verify changes; engineers approve requirements and handle exceptions.
Read the breakdown 👇
Read the article:
clstk.com/4C0l9R4
171
How can cloud agents check mobile app behavior before changes reach production?
At @nextappdevcon in Berlin, @thymikee showed how QA agents test iOS and Android user flows and bring evidence into pull requests.
Watch the talk 👉 clstk.com/4BSPcdf













