Engineering Director, Agent Stack at @Vercel | @aisdk, AI Gateway, and @WorkflowDevKit | Previously Founded @askviable, VPE @eaze, and early eng @Yammer.
Silverton, OR
Joined March 2008
- Tweets59.1K
- Following1.5K
- Followers4.1K
- Likes74.4K
Daniel and 10 others retweeted
Two new decision models from @baseten are free on AI Gateway through October 27.
β’ πππππππ/πππππππ-π· currently ranks #1 on the Jev Decision Index
β’ πππππππ/ππππππππ-π· is #1 on the Artificial Analysis Decision Index
vercel.com/changelog/basetenβ¦
Daniel and 10 others retweeted
DeepSeek v4.1 Flash (1017) is now included in β² Token Pass.
Fast, mind-bogglingly cheap, and served with ZDR (zero-data retention).
It's a phenomenal model to run subagents that execute plans conceived by larger and more expensive models. You can port TypeScript to Rust 10 times and not run out of credits π
DeepSeek V4.1 Flash 1017 is now included in Vercel Token Pass.
β’ New weights from DeepSeek
β’ 1M context window
β’ No config change
Get $80 of tokens for $30/mo βvercel.com/changelog/deepseeβ¦
Daniel and 10 others retweeted
you can get a durable @eve agent session id from your web app before the user sends their first message by passing prewarm
it unlocks use cases like:
1. setting the chat url (e.g. /s/) from the start, so a refresh mid-reply reopens the same chat
2. files can upload under that session before the message that uses them goes out
3. a support widget can put the session id on the ticket the moment it opens
Daniel and 10 others retweeted
Introducing πππππππ-πππππππ. Run Pi, OpenCode, Codex, Claude Code, eve, fx, or your own harness durably on Vercel.
With πππππππ-πππππππ, agents automatically resume work after failures and run for hours, days, or months. vercel.com/blog/making-everyβ¦
Daniel and 10 others retweeted
Vercel AI Gateway
- Zero fees for BYOK
- Zero markup on list prices
- Zero payment fee with ACH
- Volume discounts available
[email protected]
Daniel and 10 others retweeted
Focus on the actual AI work.
Before @eve: "I'd say 60β70% of my time went into infra, and only the rest into the actual AI work: context engineering, data, evals."
I've been building ecommerce agents for a while and tried many AI frameworks along the way. I must say:
@eve is the first one that really clicked.
I told @shardara this recently and he asked me why, so I thought it was worth sharing publicly.
In my first AI consulting gigs (mostly custom shopping assistants) I was stunned by how much infra work it takes to ship an agent. I'd say 60β70% of my time went into infra, and only the rest into the actual AI work: context engineering, data, evals. That was insane tbh, because none of that infra felt custom to me. Most frameworks either didnβt help much with infra, or if they did, they forced clunky abstractions on the AI side, and I kept fighting the framework instead of doing my work.
That's probably why so many folks say "don't use a framework, just build from scratch." I felt that too (we all have our Claudes and Codexes, right?), but going framework-less never felt right either. Thereβs so much repeatable stuff, and way too many footguns, to rebuild it every time.
So for a long time I was looking for something very simple:
1. Pls pls handle infra for me. Durable execution, sandboxes, streaming, reconnects, subagents, file uploads that land in the sandbox, auth, web search, easy deployment.
2. LEAVE ME FREEDOM on the AI part. I want to own the harness, not have the framework own it for me.
@eve is just the first one that ticks all these boxes.
Bonus: every production agent quickly needs a UI and often a custom API. A playground, a context view, a domain-specific data viewer (inspired by @HamelHusain, highly recommend). With Eve + Next.js itβs all in a single repo (not even a monorepo!), deployed with one click. Framework-defined Infrastructure at its finest, it really feels good.
btw, I come from front-end world and I remember exactly how the world looked before and after nextjs. Now it feels like this again, just with AI.
Everything we do at the eCommerce AI Lab at @commerce_ui now runs on Eve: shopping assistants and analytics agents for our clients, plus our own company agent that lives in Slack. It all just works, and a huge amount of custom code just evaporated.
Highly recommend
Daniel and 10 others retweeted
Beam from @reflection_ai is free on AI Gateway for a limited time.
Until today it ran in stealth as πππππππ/πππ-πππ. It's a low-latency US open-weight model.
ππππππππππ/ππππ-ππππ
vercel.com/changelog/reflectβ¦
Daniel and 10 others retweeted
The tokens stream faster than I can ideate
Mercury 3 from @_inception_ai is live on AI Gateway at a 50% discount.
A high-throughput diffusion model with a 1M-token context window and support for tool calling and structured outputs.
πππππππππ/πππππππ’-πΉ
vercel.com/changelog/mercuryβ¦
Daniel and 10 others retweeted
Use Jev to ask questions about images in AI SDK.
Pass an image, define a boolean question, and get back the probability that it's true.
![Code snippet using Jev 1.14.0 to decide whether a cat is shown in an image.
import { experimental_decide as decide } from 'ai'
import { readFileSync } from 'node:fs'
const { answers } = await decide({
model: 'typesafe-ai/jev-1.14.0',
state: [
{
type: 'file',
mediaType: 'image',
data: readFileSync('cat.jpg')
}
],
questions: {
cat: {
type: 'boolean',
instructions: 'Does the image show a cat?'
}
}
})
console.log(answers.cat.probability)](https://pbs.twimg.com/media/HU_DZdmakAElgfE.jpg?name=orig)
ALT Code snippet using Jev 1.14.0 to decide whether a cat is shown in an image. import { experimental_decide as decide } from 'ai' import { readFileSync } from 'node:fs' const { answers } = await decide({ model: 'typesafe-ai/jev-1.14.0', state: [ { type: 'file', mediaType: 'image', data: readFileSync('cat.jpg') } ], questions: { cat: { type: 'boolean', instructions: 'Does the image show a cat?' } } }) console.log(answers.cat.probability)
composable images: Jev got eyes!!! eyes eyes baby.
not only are we enabling multimodality for future Jev models, weβre enabling it for the current Jev that you all know and love.
and images can go anywhere text could go before, in whatever combination you can think of. go wild.
deets in the docs: docs.typesafe.ai/go/images
Daniel and 10 others retweeted
Introducing Pixel - a library for building GUIs in the terminal
- 120 FPS pixel-perfect graphics
- Embeddable inside existing TUIs
- Built in chromium webview component
pixelgui.com
Daniel and 10 others retweeted
I've been building ecommerce agents for a while and tried many AI frameworks along the way. I must say:
@eve is the first one that really clicked.
I told @shardara this recently and he asked me why, so I thought it was worth sharing publicly.
In my first AI consulting gigs (mostly custom shopping assistants) I was stunned by how much infra work it takes to ship an agent. I'd say 60β70% of my time went into infra, and only the rest into the actual AI work: context engineering, data, evals. That was insane tbh, because none of that infra felt custom to me. Most frameworks either didnβt help much with infra, or if they did, they forced clunky abstractions on the AI side, and I kept fighting the framework instead of doing my work.
That's probably why so many folks say "don't use a framework, just build from scratch." I felt that too (we all have our Claudes and Codexes, right?), but going framework-less never felt right either. Thereβs so much repeatable stuff, and way too many footguns, to rebuild it every time.
So for a long time I was looking for something very simple:
1. Pls pls handle infra for me. Durable execution, sandboxes, streaming, reconnects, subagents, file uploads that land in the sandbox, auth, web search, easy deployment.
2. LEAVE ME FREEDOM on the AI part. I want to own the harness, not have the framework own it for me.
@eve is just the first one that ticks all these boxes.
Bonus: every production agent quickly needs a UI and often a custom API. A playground, a context view, a domain-specific data viewer (inspired by @HamelHusain, highly recommend). With Eve + Next.js itβs all in a single repo (not even a monorepo!), deployed with one click. Framework-defined Infrastructure at its finest, it really feels good.
btw, I come from front-end world and I remember exactly how the world looked before and after nextjs. Now it feels like this again, just with AI.
Everything we do at the eCommerce AI Lab at @commerce_ui now runs on Eve: shopping assistants and analytics agents for our clients, plus our own company agent that lives in Slack. It all just works, and a huge amount of custom code just evaporated.
Highly recommend
Daniel and 10 others retweeted
See every agent session in AI Gateway logs.
Sessions group requests by conversation, with cost, cache hit rate, and the agent that ran it. Session affinity keeps each one on the provider holding its prompt cache.
vercel.com/changelog/ai-gateβ¦
Cached token mechanics are the largest point of friction for harness building.
If we didn't care about cheap cache hits, harnesses would absolutely rip
Daniel and 10 others retweeted
New from Vercel Labs: tsc-ts
TypeScript was written in TypeScript
Then rewritten in Go
We ported it back to TypeScript
Compiled it with scriptc
And it's 2-4x faster than tsgo
Daniel and 10 others retweeted
If you missed @andrew_barba's @eve presentation yesterday at Ship, then be sure to catch up in this π§΅!
Daniel and 10 others retweeted
ROI maxxing in, tokenmaxxing out
The October 2026 AI Gateway Index is live.
1. Open weight ran over 70% of tokens, and took nearly 25% of spend, up 4x since June.
vercel.com/blog/ai-gateway-pβ¦
