Afkode

37 posts

Afkode banner
Afkode

Afkode

@afkode_ai

The Builder-First Automated Feature Delivery Harness - Multiple models - Multiple features - Multiple projects All in parallel. Using your subscription or API

Katılım Nisan 2026
221 Takip Edilen26 Takipçiler
Sabitlenmiş Tweet
Afkode
Afkode@afkode_ai·
Meet Afkode: the builder-first harness for autonomous feature delivery. Give it a complex feature. It plans, builds, tests, reviews, and keeps going until it works. Run parallel projects, mix models, validate with real tests, and ship more with less agent babysitting.
English
0
3
6
52.5K
Afkode
Afkode@afkode_ai·
Can you please stop tagging me all the time... Claude design can do that too and people are happy to pay a lot of money for it
Alex I/O@alessiocarra_

New in @afkode_ai you can now Design your views directly in the app, iterate, edit and when you are done 1 click to spec. Afkode will build the exact design and flow 1:1 without intervention.

English
0
0
0
56
Jason Zook
Jason Zook@jasondoesstuff·
SOOO many less bugs building stuff with this... - Claude Opus 4.7 makes the feature plan - GPT-5.5 reviews the plan (always finds issues) - Opus updates the plan, GPT approves - Opus builds, uses Playwright to test UX/UI - GPT reviews feature code (always finds issues) - Opus fixes issues, GPT signs off ✅ - Then I test fully myself, usually very minor issues - Merge and deploy! 🚀 I'm using @conductor_build to easily bounce back and forth between the two and VERY happy with this workflow 👏👏. Kind of crazy to pay ~$400/month for what feels like a full dev team that never pushes back on all my stupid UI requests and small changes 😂.
English
112
62
1.5K
131.4K
Injamul Islam
Injamul Islam@Iam_Injamul·
@thdxr How can I achieve something like GPT 5.5 works as an orchestrator while cheap models like GLM 5.1 write the code with opencode? I wonder whether it is even a good idea? The primary motivation to do this is to save tokens while retaining the performance as much as possible.
English
14
0
13
13.2K
dax
dax@thdxr·
our teams last 7 days of spend damn gpt5.5
dax tweet media
English
272
80
3.4K
723.3K
Ryan Carson
Ryan Carson@ryancarson·
I’d love to not be so dependent on Claude Design. @skirano can you help? Can you beat them?
English
42
0
76
19.1K
Brian Armstrong
Brian Armstrong@brian_armstrong·
This is an email I sent earlier today to all employees at Coinbase: Team, Today I’ve made the difficult decision to reduce the size of Coinbase by ~14%. I want to walk you through why we're doing this now, what it means for those affected, and how this positions us for the future. Why now Two forces are converging at the same time. We need to be front footed to respond to both. First, the market. Coinbase is well-capitalized, has diversified revenue streams, and is well-positioned to weather any storm. Crypto is also on the verge of the next wave of adoption, with stablecoins, prediction markets, tokenization, and more taking off. However, our business is still volatile from quarter to quarter. While we've managed through that cyclicality many times before and come out stronger on the other side, we’re currently in a down market and need to adjust our cost structure now so that we emerge from this period leaner, faster, and more efficient for our next phase of growth. Second, AI is changing how we work. Over the past year, I’ve watched engineers use AI to ship in days what used to take a team weeks. Non-technical teams are now shipping production code and many of our workflows are being automated. The pace of what's possible with a small, focused team has changed dramatically, and it's accelerating every day. All of this has led us to an inflection point, not just for Coinbase, but for every company. The biggest risk now is not taking action. We are adjusting early and deliberately to rebuild Coinbase to be lean, fast, and AI-native. We need to return to the speed and focus of our startup founding, with AI at our core. What this means To get there, we are not just reducing headcount and cutting costs, we’re fundamentally changing how we operate: rebuilding Coinbase as an intelligence, with humans around the edge aligning it. What does this mean in practice? - Fewer layers, faster decisions: We are flattening our org structure to 5 layers max below CEO/COO. Layers slow things down and create coordination tax. The future is small, high context teams that can move quickly. Leaders will own much more, with as many as 15+ direct reports. Fewer layers also means a leaner cost structure that is built to perform through all market cycles. - No pure managers: Every leader at Coinbase must also be a strong and active individual contributor. Managers should be like player-coaches, getting their hands dirty alongside their teams. - AI-native pods: We’ll be concentrating around AI-native talent who can manage fleets of agents to drive outsized impact. We’ll also be experimenting with reduced pod sizes, including “one person teams” with engineers, designers, and product managers all in one role. In short: AI is bringing a profound shift in how companies operate, and we’re reshaping Coinbase to lead in this new era. This is a new way of working, and we need to leverage AI across every facet of our jobs. To those who are affected I know there are real people behind these decisions — talented colleagues who have poured themselves into this company and our mission. To those of you who will be leaving: thank you. You’ve helped build Coinbase into what it is today, and I am sincerely grateful for everything you've done. All impacted team members will receive an email to their personal account in the next hour with more information, and an invitation to meet with an HRBP and a senior leader in your organization. Coinbase system access has been removed today. I know this feels sudden and harsh, but it is the only responsible choice given our duty to protect customer information. To those affected, we will be providing a comprehensive package to support you through this transition. US employees will receive a minimum of 16 weeks base pay (plus 2 weeks per year worked), their next equity vest, and 6 months of COBRA. Employees on a work visa will get extra transition support. Those outside of the US will receive similar support, based on local factors and subject to any consultation requirements. Coinbase prides itself on talent density. Our employees are among the most talented people in the world, and I have no doubt that your skills and experience will be highly sought after as you pursue your next chapters. How we move forward To the team that is staying, I know this is a difficult day. We’re saying goodbye to colleagues and friends you've been in the trenches with. But here’s what I want you to know as we move forward together: Over the past 13 years, we have weathered four crypto winters, gone public, and built the most trusted platform in our industry. We’ve made it this far by making hard decisions and by always staying focused on our mission. This time will be no different – nothing has changed about the long term outlook of our company or industry. And most importantly, our mission has never been more important for the world. Increasing economic freedom requires a new financial system, and we’re building it. The Coinbase that emerges from this will be more capable than ever to achieve our mission. Brian
English
5.3K
2.4K
20.1K
23.5M
Afkode retweetledi
Alex I/O
Alex I/O@alessiocarra_·
Coinbase is cutting 14% of the workforce because (mostly) of AI. In his memo @brian_armstrong mentioned something more profound than simply "we are adopting AI". Following @jack's move at @blocks the pattern is becoming clear. To survive in the post AI era companies must redefine their entire organization around AI. The idea of "AI native pods" or "teams of one" will become more and more the way companies adopt to stay lean and productive in the AI era. This is not only about devs being more productive. The people forming the teams of one will need to be product managers, designers, engineers all at once. But the current tools are mainly built for engineers. Teams of one will need better tools that can support them end to end and close the gaps in the verticals they don't master. @afkode_ai give Teams of One all they need to succeed in this new role that is emerging in the post AI era.
Brian Armstrong@brian_armstrong

This is an email I sent earlier today to all employees at Coinbase: Team, Today I’ve made the difficult decision to reduce the size of Coinbase by ~14%. I want to walk you through why we're doing this now, what it means for those affected, and how this positions us for the future. Why now Two forces are converging at the same time. We need to be front footed to respond to both. First, the market. Coinbase is well-capitalized, has diversified revenue streams, and is well-positioned to weather any storm. Crypto is also on the verge of the next wave of adoption, with stablecoins, prediction markets, tokenization, and more taking off. However, our business is still volatile from quarter to quarter. While we've managed through that cyclicality many times before and come out stronger on the other side, we’re currently in a down market and need to adjust our cost structure now so that we emerge from this period leaner, faster, and more efficient for our next phase of growth. Second, AI is changing how we work. Over the past year, I’ve watched engineers use AI to ship in days what used to take a team weeks. Non-technical teams are now shipping production code and many of our workflows are being automated. The pace of what's possible with a small, focused team has changed dramatically, and it's accelerating every day. All of this has led us to an inflection point, not just for Coinbase, but for every company. The biggest risk now is not taking action. We are adjusting early and deliberately to rebuild Coinbase to be lean, fast, and AI-native. We need to return to the speed and focus of our startup founding, with AI at our core. What this means To get there, we are not just reducing headcount and cutting costs, we’re fundamentally changing how we operate: rebuilding Coinbase as an intelligence, with humans around the edge aligning it. What does this mean in practice? - Fewer layers, faster decisions: We are flattening our org structure to 5 layers max below CEO/COO. Layers slow things down and create coordination tax. The future is small, high context teams that can move quickly. Leaders will own much more, with as many as 15+ direct reports. Fewer layers also means a leaner cost structure that is built to perform through all market cycles. - No pure managers: Every leader at Coinbase must also be a strong and active individual contributor. Managers should be like player-coaches, getting their hands dirty alongside their teams. - AI-native pods: We’ll be concentrating around AI-native talent who can manage fleets of agents to drive outsized impact. We’ll also be experimenting with reduced pod sizes, including “one person teams” with engineers, designers, and product managers all in one role. In short: AI is bringing a profound shift in how companies operate, and we’re reshaping Coinbase to lead in this new era. This is a new way of working, and we need to leverage AI across every facet of our jobs. To those who are affected I know there are real people behind these decisions — talented colleagues who have poured themselves into this company and our mission. To those of you who will be leaving: thank you. You’ve helped build Coinbase into what it is today, and I am sincerely grateful for everything you've done. All impacted team members will receive an email to their personal account in the next hour with more information, and an invitation to meet with an HRBP and a senior leader in your organization. Coinbase system access has been removed today. I know this feels sudden and harsh, but it is the only responsible choice given our duty to protect customer information. To those affected, we will be providing a comprehensive package to support you through this transition. US employees will receive a minimum of 16 weeks base pay (plus 2 weeks per year worked), their next equity vest, and 6 months of COBRA. Employees on a work visa will get extra transition support. Those outside of the US will receive similar support, based on local factors and subject to any consultation requirements. Coinbase prides itself on talent density. Our employees are among the most talented people in the world, and I have no doubt that your skills and experience will be highly sought after as you pursue your next chapters. How we move forward To the team that is staying, I know this is a difficult day. We’re saying goodbye to colleagues and friends you've been in the trenches with. But here’s what I want you to know as we move forward together: Over the past 13 years, we have weathered four crypto winters, gone public, and built the most trusted platform in our industry. We’ve made it this far by making hard decisions and by always staying focused on our mission. This time will be no different – nothing has changed about the long term outlook of our company or industry. And most importantly, our mission has never been more important for the world. Increasing economic freedom requires a new financial system, and we’re building it. The Coinbase that emerges from this will be more capable than ever to achieve our mission. Brian

English
0
1
1
207
Afkode
Afkode@afkode_ai·
So now that you are saving on tokens can I get a raise? :))
Alex I/O@alessiocarra_

It's so cool that now in @afkode_ai I can select different models based on the type of task and complexity. I did 2X more medium complexity backend task than high complexity but I spent roughly the same amount of tokens. Also the medium complexity tasks completed on avg 2X as fast as the high complexity because I am using a cheaper faster model for those. Before this I would have just used the best possible model for all tasks and would have ended up spending A LOT more tokens and A LOT more time!

English
1
0
0
80
Afkode
Afkode@afkode_ai·
🔊 SOUND ON > All you see and hear is made only with AI
English
2
1
2
8.5K
Alex I/O
Alex I/O@alessiocarra_·
@afkode_ai is the one tool that is taking a different path from all these you mentioned. It’s designed to work in features instead of single tasks. It plans, builds and tests full features autonomously. You can use up to 21 different models for different activities in the same stream of work. Fully local and with a very nice (and different) UI
English
1
0
1
126
Robin Ebers · AI for Non-Coders
it is so hard to recommend third-party coding tools really doesn't matter if T3 Code, Conductor, and similar they provide very little extra while always lagging behind features today's example: Codex goals this is an uphill battle that cannot easily be won there's thousands of them, and they're all building the same that's why Cursor remains number one for me with Codex being strong second
English
9
0
31
2.7K
Alex I/O
Alex I/O@alessiocarra_·
You can now assign 21 different models for the right task in @afkode_ai All of them will have the correct context to complete their job automatically. During autonomous execution you can have - Low complexity Frontend Tasks -> Kimi 2.6 - Low complexity Backend Tasks -> Deepseek V4 - Medium complexity FE -> Sonnet 4.6 High thinking - Medium complexity BE -> GPT 5.5 medium thinking ... You get the point. The best way to save on your AI bill and get the best model do the job you need
English
2
0
3
1K
Afkode
Afkode@afkode_ai·
It's that easy! 😍
Alex I/O@alessiocarra_

You can now assign 21 different models for the right task in @afkode_ai All of them will have the correct context to complete their job automatically. During autonomous execution you can have - Low complexity Frontend Tasks -> Kimi 2.6 - Low complexity Backend Tasks -> Deepseek V4 - Medium complexity FE -> Sonnet 4.6 High thinking - Medium complexity BE -> GPT 5.5 medium thinking ... You get the point. The best way to save on your AI bill and get the best model do the job you need

English
0
0
0
92
Alex I/O
Alex I/O@alessiocarra_·
Codex and Cursor and many other apps building kanban boards are missing one important detail. If the work unit is a single task a kanban board is useless. The task lifecycle is just to short in the agent era and most of them will pile up in review. If you want to make a good use of kanban you have to move up one level and have entire features move autonomously from planning to execution and testing.
English
1
0
1
159
Afkode
Afkode@afkode_ai·
@jamonholmgren you can just write the spec and give it to us :)
English
0
0
0
15
Austin Kennedy
Austin Kennedy@astnkennedy·
I'm 22 years old and Claude Code is deteriorating my brain. Every single day for the last 6 months I've had 6 to 8 Claude Code terminals open, waiting for a response just so I can hit 'enter' 75% of the time. And it's doing something to me. In convos with a couple of friends, it's been a point that's been brought up pretty frequently. None of us feel as sharp as we used to. I don't know if it's just us, or others in their 20s are feeling the same thing, but it's something I've been thinking about a lot. P.S. I know this is a problem with my reliability/usage of it, not Claude Code itself, but the effects are real nonetheless
English
1.3K
373
9.2K
2M
Afkode retweetledi
Alex I/O
Alex I/O@alessiocarra_·
Model will become a commodity. In 6 to 12 months we’ll probably have OS models as good as today’s SOTA closed models like gpt 5.5 and Opus 4.7. At that point the value will be only in the harness. I built @afkode_ai around this believe as the builder-first harness for autonomous feature delivery. Different models can be used at the same time in the feature’s lifecycle and the harness manages the context many other things which makes it possible to have it run for hours or days!
English
0
1
2
305
Rhys
Rhys@RhysSullivan·
Where I’d love to see linear pivot to is helping me break down huge tasks / engineering efforts into manageable chunks Make a great chat at that with a good interface, let me pull in tons of reference repos & do deep research Leverage their huge dataset of completed projects
English
14
1
99
9K
Afkode
Afkode@afkode_ai·
@RhysSullivan 👋 Hey! Sounds like we could be a good fit!
English
0
0
0
29
Rhys
Rhys@RhysSullivan·
has anyone built "the software factory" thing, misc requirements: - able to use my subscriptions (codex / claude) - stacked diffs w/ graphite - able to go from planning -> lots of small tasks - closing the review loop don't love current agent interfaces, want something new
English
138
5
475
41.1K