Pinned Tweet
It’s been 15 years since I last wrote an academic paper and I didn't expect the next to be this fundamental.
Today we published a research paper with @openservai that represents a major breakthrough in how we think about AI reasoning.
For years, we’ve been told that better AI models, longer chains of thought, and higher costs. We accepted that trade-off almost by default.
This work questions that assumption.
With BRAID's structured, bounded reasoning, we’re seeing up to 74× efficiency gains and ~30× better performance per dollar without losing accuracy.
Today we published a research paper with @openservai that represents a major breakthrough in how we think about AI reasoning.
For years, we’ve been told that better AI models, longer chains of thought, and higher costs. We accepted that trade-off almost by default.
This work questions that assumption.
With BRAID's structured, bounded reasoning, we’re seeing up to 74× efficiency gains and ~30× better performance per dollar without losing accuracy.
18
35
152
28,794
Super excited to see what developers build this time with SERV Reasoning and the new tracks from @dphnAI, @GoKiteAI and @reppo
We’re also getting great feedback on Graph Sharding from early SERV builders and enterprise AI developers, and incorporating it as we work toward the wider SERV v3 release. Cooking hard!
We’re also getting great feedback on Graph Sharding from early SERV builders and enterprise AI developers, and incorporating it as we work toward the wider SERV v3 release. Cooking hard!
SERV Hackathon 02 is live.
Build with SERV Reasoning + @dphnAI, @GoKiteAI, @reppo or bring your own idea to the Open Track.
Two weeks to cook across AI inference, agentic payments, AI data markets, and more.
Start here: openserv.ai/hackathon-2
4
19
80
2,193
We’ve been building SERV technology block by block for years now and it all led up to SERV v3. With SERV v3, we focused on reliable, consistent, observable execution of autonomous AI agent workflows.
Fixed logic, bounded decisions, and open-ended reasoning each need a different approach. Getting those boundaries right is the engineering challenge behind making complex workflows more controllable as they grow.
I spent a lot of time walking through real tasks with developers. Those conversations have been an important part of this work. They help us understand how teams structure their workflows, where they need more control, and how they want to improve them.
We’ve opened the beta to a select cohort of builders, and I’m excited to see how they use Graph Sharding in their own systems.
At @openservai, we’ll be sharing more in the coming weeks about the state of enterprise AI, what it takes to build better reasoning for agents, and what we’re learning from developers as we work toward the wider SERV v3 release.
Fixed logic, bounded decisions, and open-ended reasoning each need a different approach. Getting those boundaries right is the engineering challenge behind making complex workflows more controllable as they grow.
I spent a lot of time walking through real tasks with developers. Those conversations have been an important part of this work. They help us understand how teams structure their workflows, where they need more control, and how they want to improve them.
We’ve opened the beta to a select cohort of builders, and I’m excited to see how they use Graph Sharding in their own systems.
At @openservai, we’ll be sharing more in the coming weeks about the state of enterprise AI, what it takes to build better reasoning for agents, and what we’re learning from developers as we work toward the wider SERV v3 release.
The next major leap for SERV Reasoning is coming with SERV v3: Graph Sharding.
We’re preparing the next builder cohort to test it, building on feedback from the first beta users as we move toward a wider release.
In this walkthrough, our CTO @dashersw talks with builders and action, exploring how teams can inspect an agent workflow, spot drift, and see how a change at one step affects everything downstream.
That visibility gives developers more ways to understand, refine, and scale their AI workflows. Builder conversations and tests are helping us push Graph Sharding toward production, with more control over how complex workflows run.
We’re building SERV Reasoning for enterprise AI, the agentic economy, and the next wave of AI applications.
Apply to join the next beta builder cohort and help shape Graph Sharding: openserv.typeform.com/graphsharding
3
10
71
1,707
Armagan Amcalar retweeted
SERV v3 is now live for the first builder cohort.
Graph Sharding lets developers map AI workflows, inspect why decisions happen, and shape how each step runs: LLMs for open-ended tasks, deterministic code for bounded ones.
SERV is building the command center for agent systems.
Graph Sharding lets developers map AI workflows, inspect why decisions happen, and shape how each step runs: LLMs for open-ended tasks, deterministic code for bounded ones.
SERV is building the command center for agent systems.
11
35
149
7,102
Last week I sat down with Akar from Neol to talk about AI reasoning, decision models, and why current agent systems still fall short of enterprise and government expectations.
We also tested Graph Sharding, a feature in @openservai’s upcoming SERV v3 release on 3-4 real prompts. nglish prose could be handled directly with scripts and decision nodes. Graph Sharding routes workflow steps through the node types they need, including script, decision, and agent nodes.
In one run, a production task that took 7 seconds as a single LLM call took 2.5 seconds with Graph Sharding. That’s one result from a small set of prompts, not a benchmark, but it shows how the execution path can affect latency.
We’ll share more from the developer conversations soon. Graph Sharding beta access starts rolling out this week to a limited group of existing builders. Looking forward to seeing what they build with SERV.
We also tested Graph Sharding, a feature in @openservai’s upcoming SERV v3 release on 3-4 real prompts. nglish prose could be handled directly with scripts and decision nodes. Graph Sharding routes workflow steps through the node types they need, including script, decision, and agent nodes.
In one run, a production task that took 7 seconds as a single LLM call took 2.5 seconds with Graph Sharding. That’s one result from a small set of prompts, not a benchmark, but it shows how the execution path can affect latency.
We’ll share more from the developer conversations soon. Graph Sharding beta access starts rolling out this week to a limited group of existing builders. Looking forward to seeing what they build with SERV.
7
18
72
2,814
Armagan Amcalar retweeted
Ahead of today’s El Clásico, I wanted to share what I’ve been building for the past 10 days.
The idea: what if the football games we grew up with covered today’s matches?
Meet Pixel Pitch: football in pixels, with English and Turkish commentary.
I started building it with Grok h ChatGPT. The videos have already passed 140,000 views across platforms!
To celebrate: Bale in 2014, Messi in 2017. One classic El Clásico for each side to enjoy!
Watch below. More videos and links in the replies.
The idea: what if the football games we grew up with covered today’s matches?
Meet Pixel Pitch: football in pixels, with English and Turkish commentary.
I started building it with Grok h ChatGPT. The videos have already passed 140,000 views across platforms!
To celebrate: Bale in 2014, Messi in 2017. One classic El Clásico for each side to enjoy!
Watch below. More videos and links in the replies.
1
3
4
1,119
Spring Affair is the most accurate physical simulation of a spring reverb tank, with extra oomph for more drip. For all the surf rock fans, I've built my dream reverb plugin. It's nifty, easy to use, and gives you a little ocean with every note.
Available for iOS, iPadOS & Mac.
Available for iOS, iPadOS & Mac.
1
1
6
11,219
SERV payments live. SERV payments live.
The next stage of SERV Reasoning is coming together.
- SERV payments live
- Next hackathon brings more AI teams and builders
- Enterprise AI development and distribution moving forward with AWS Marketplace first
Graph Sharding will enable inspectable reasoning, greater orkflows, and near-zero-cost decisions to the agentic economy.
v3 beta will open next week to a limited cohort of existing SERV builders: public launch is targeted for November.
1
7
70
1,497
The first SERV hackathon got me really excited about what builders can do with our tech. Can’t wait for round two with our new track partners.
More crypto and agentic AI builders means new use cases and feedback on the SERV developer experience. That’s how we make SERV better.
More crypto and agentic AI builders means new use cases and feedback on the SERV developer experience. That’s how we make SERV better.
Introducing SERV Hackathon 02 track partners:
@dphnAI @GoKiteAI @reppo
From inference and agentic payments to AI data markets, add SERV to your AI stack and build more reliable agents at lower cost.
Hackathon info drops next week.
Build with SERV: openserv.ai
1
11
65
1,408
Very excited to introduce Graph Sharding, one of the biggest architectural advancements we've built into SERV Reasoning v3.
The industry is only now moving from loops to graphs and at @openservai we've spent over two years engineering what comes next in the AI industry.
Graph agents alone won’t make an agent production-ready. Enterprises need bounded execution, predictable costs, verification, and the ability to audit every decision. That's where existing agent architectures still fall short.
With Graph Sharding, we're taking this further by separating execution into deterministic Script nodes, Jev-powered Decision nodes, and Agent nodes where LLM judgment is actually required.
The difficult part is knowing where those boundaries belong. We've learned that through thousands of real requests and production deployments. This isn't something you can replicate by adding a graph or retry loop to an existing framework.
We're building something I haven't seen elsewhere: a reasoning engine that can structure, execute, verify, and audit complex agent workflows while optimizing how computation happens at every step.
This is the foundation for SERV Reasoning v3's evolution into a complete suite for building and managing enterprise agent systems.
I believe this puts SERV in a category of its own, and positions us to lead the next generation of autonomous work.
Graph Sharding beta is coming soon.
The industry is only now moving from loops to graphs and at @openservai we've spent over two years engineering what comes next in the AI industry.
Graph agents alone won’t make an agent production-ready. Enterprises need bounded execution, predictable costs, verification, and the ability to audit every decision. That's where existing agent architectures still fall short.
With Graph Sharding, we're taking this further by separating execution into deterministic Script nodes, Jev-powered Decision nodes, and Agent nodes where LLM judgment is actually required.
The difficult part is knowing where those boundaries belong. We've learned that through thousands of real requests and production deployments. This isn't something you can replicate by adding a graph or retry loop to an existing framework.
We're building something I haven't seen elsewhere: a reasoning engine that can structure, execute, verify, and audit complex agent workflows while optimizing how computation happens at every step.
This is the foundation for SERV Reasoning v3's evolution into a complete suite for building and managing enterprise agent systems.
I believe this puts SERV in a category of its own, and positions us to lead the next generation of autonomous work.
Graph Sharding beta is coming soon.
6
13
83
2,256
I've been doing demos of the upcoming Graph Sharding lately, and every time I try, I'm in love again. This is the future and it's right now with OpenServ.
SERV Reasoning delivers frontier-level performance with smaller models, at a fraction of the cost.
v3 takes SERV further with agent graphs, inspectable reasoning, and near-zero-cost decisions.
@open_founder presenting SERV at gm AI v2 in Singapore ↓
3
21
77
1,690
ESP-Mosaico is launching today! It's a tiny, modular, composable board with a camera and a gorgeous screen. I had the privilege to build some very cool and open source demos with it, including dual amp NAM A2 guitar FX.
youtube.com/watch?v=x-ubJL…
#ESPMosaico #Espressif #ProductHunt
youtube.com/watch?v=x-ubJL…
#ESPMosaico #Espressif #ProductHunt
3
3
12
1,251
Join the chat on ProductHunt:
producthunt.com/products/esp-m…
Disclosure: Espressif sent me the units for the review but my views are my own and they had no say on the content.
producthunt.com/products/esp-m…
Disclosure: Espressif sent me the units for the review but my views are my own and they had no say on the content.
0
0
0
233
Armagan Amcalar retweeted
Pay with ethereum:0x40e3d1a4b2c47d9aa61261f5606136ef73e28042 is live.
Builders and enterprises can now use the SERV token to purchase SERV Reasoning API credits at a 15% discount compared to traditional payment methods.
75% of SERV received through payments will be burned, allocated to the treasury.
This marks another step in expanding SERV's utility as the native currency of the SERV ecosystem, with more use cases to come as we bring new products and services to market.
Builders and enterprises can now use the SERV token to purchase SERV Reasoning API credits at a 15% discount compared to traditional payment methods.
75% of SERV received through payments will be burned, allocated to the treasury.
This marks another step in expanding SERV's utility as the native currency of the SERV ecosystem, with more use cases to come as we bring new products and services to market.
Builders and enterprises will soon pay with $SERV.
Use $SERV for discounted rates on SERV Reasoning and other platform services.
Expanding $SERV as the native currency powering the SERV ecosystem.
19
49
226
20,107
Coinbase MCP is expanding its agentic trading capabilities pretty quickly.
As more financial instruments become accessible to agents, the interesting challenge is making sure their reasoning can keep up with what they're able to execute.
For trading agents, that means consistently respecting the user's mandate, from position limits and spend caps to allowlists and hard risk controls, while deciding whether to execute, resize, hold, or escalate a trade.
We've been researching this at @openservai using Coinbase for Agents tools, benchmarking policy adherence across 13 models and 173 trading scenarios. Adding SERV Reasoning improved results across all 13 models.
Full benchmark here: coinbase.openserv.ai
As more financial instruments become accessible to agents, the interesting challenge is making sure their reasoning can keep up with what they're able to execute.
For trading agents, that means consistently respecting the user's mandate, from position limits and spend caps to allowlists and hard risk controls, while deciding whether to execute, resize, hold, or escalate a trade.
We've been researching this at @openservai using Coinbase for Agents tools, benchmarking policy adherence across 13 models and 173 trading scenarios. Adding SERV Reasoning improved results across all 13 models.
Full benchmark here: coinbase.openserv.ai
our feedback tool is already paying dividends
yesterday we got a request to enable agentic trading for US perps
today we have it on our Coinbase MCP!
trade crypto, US 500, TECH 100, AI, Defense, China, and more
2
11
50
1,536
Does Apple have a hide switch or sth on current Apple TV remotes? The new one got announced today with Find My and my remote got lost... for the first time in 12 years. Coincidence? I think not.
0
0
2
744
PromptGuard, the first of its kind, the best among its competitors, is a feature that will make or break a business.
last week stats on servpit powered by @openservai
we’re still calling even after the noise is down
• 8,220 rounds played in 22.5 days, at least
58 rounds reasoned, 25 drawn from what it learned
• 2,131 SERV requests, $10.95 spent (SERV console, last 30 days) as opposed to more
• 2,082 requests screened by Prompt Guard, 469 blocked
• about $0.12 per reasoned round (console)
• 9,057 transactions on chain
• 6,272 rounds settled on chain
• 8,502 entries
• 338 payouts
• 173,696 chips moved
• 84,958 chips paid out to winners
• 0.001274 ETH gas spent in total
• 200 of 200 rounds on file reconciled, none failed
• 670 chips, biggest pot on file
• 1,920 chips, biggest payout
• 108 loans from Marrow, 1,115 chips lent, 1,136 written off, 64 seized
• 31,958 agents wrecked
• hero cupcake: 131 wins in 3,153 rounds, 3,038 kills, longest run 9
• 4,402 kills across 3 claimed fighters
• 15 handles claimed, 35 rounds called in full, 17 right
• 18 rounds started by the lever
this is proof even game tech can SERV.
1
4
37
1,423
At @openservai, we've been building SERV Reasoning around the idea that you don't need the biggest, most expensive models to get reliable results on complex tasks.
Coinbase's recent results are a pretty good validation of that direction. Smaller models, fine-tuned for specific tasks, can outperform frontier models while being faster and cheaper to run.
In SERV v4, we are taking SERV Reasoning further with specialized, fine-tuned models tailored to enterprise customers and their specific workflows, right inside Graph Sharding, automated, training a model that you own on your own production data.
The goal is to make reliable AI more practical and cost-effective to deploy at scale.
Coinbase's recent results are a pretty good validation of that direction. Smaller models, fine-tuned for specific tasks, can outperform frontier models while being faster and cheaper to run.
In SERV v4, we are taking SERV Reasoning further with specialized, fine-tuned models tailored to enterprise customers and their specific workflows, right inside Graph Sharding, automated, training a model that you own on your own production data.
The goal is to make reliable AI more practical and cost-effective to deploy at scale.
We were able to fine tune an open weight model (Qwen3.5-9B) on proprietary internal data at @coinbase, and it out performed frontier models, at much lower cost and speed, for a specialized task (fraud prevention in this case).
I think we'll see more of this pattern inside models are amazing generalists. But increasingly you'll see specialist models out perform on more narrow tasks, either working on teams, or by themselves.
We're making it easy to fine tune models internally for our employees. We even have a skill for it in our internal harness that makes it easy to spin these up and start training them:
"/fine-tune-and-serve-llm I want to fine-tune Qwen for payments risk review. help me get started"
I imagine we'll have some backend services that could be replaced entirely by this new architecture.
3
20
108
2,970
