Oakland, CA
Joined June 2018
- Tweets222
- Following728
- Followers321
- Likes467
Joe McKenney retweeted
hardcoding model names across your agents is a full-time job in 2026
we built virtual models so you can just change the config and everything updates. this is how agent infrastructure should work.
Introducing virtual models on AI Gateway.
Use a single virtual model ID across agents to:
• Centrally manage model strings and configs
• Immediately update to new models
• Enforce Zero Data Retention
Read the blog post → vercel.com/blog/ai-gateway-v…
Joe McKenney retweeted
Meet Glyph Cluster on AI Gateway.
𝚜𝚝𝚎𝚊𝚕𝚝𝚑/𝚐𝚕𝚢𝚙𝚑-𝚌𝚕𝚞𝚜𝚝𝚎𝚛
• Free while in stealth for a limited time
• Access restricted to paid users
• Use it for coding & agentic knowledge work
• Prompts may be used for model improvement
vercel.com/changelog/glyph-c…
Joe McKenney retweeted
I was so impressed with Vercel's AI SDK and Gateway I decided to write something up.
Link is below if you're interested 👇👊
Joe McKenney retweeted
1 line of code in @aisdk saves you 90% or more in DeepSeek v4 Flash AI Gateway tokens
DeepSeek v4 Flash via Novita is 90% off for Vercel Pro till 8/11.
𝚜𝚝𝚛𝚎𝚊𝚖𝚃𝚎𝚡𝚝({
𝚖𝚘𝚍𝚎𝚕: '𝚍𝚎𝚎𝚙𝚜𝚎𝚎𝚔/𝚍𝚎𝚎𝚙𝚜𝚎𝚎𝚔-𝚟𝟺-𝚏𝚕𝚊𝚜𝚑',
𝚙𝚛𝚘𝚟𝚒𝚍𝚎𝚛𝙾𝚙𝚝𝚒𝚘𝚗𝚜: {
𝚐𝚊𝚝𝚎𝚠𝚊𝚢: { 𝚘𝚛𝚍𝚎𝚛: ['𝚗𝚘𝚟𝚒𝚝𝚊'] }
}
})
vercel.com/changelog/deepsee…
Joe McKenney retweeted
Advanced spend budgets now on AI Gateway.
Cap and get alerted on spend by team, project, and API key.
𝚟𝚎𝚛𝚌𝚎𝚕 𝚊𝚒-𝚐𝚊𝚝𝚎𝚠𝚊𝚢 𝚋𝚞𝚍𝚐𝚎𝚝𝚜 𝚜𝚎𝚝 𝚝𝚎𝚊𝚖 \
--𝚕𝚒𝚖𝚒𝚝 𝟻𝟶𝟶𝟶 \
--𝚛𝚎𝚏𝚛𝚎𝚜𝚑-𝚙𝚎𝚛𝚒𝚘𝚍 𝚖𝚘𝚗𝚝𝚑𝚕𝚢
vercel.com/changelog/ai-gate…
Joe McKenney retweeted
We've been explaining AI Gateway as a C̶o̶n̶t̶e̶n̶t̶ Token Delivery Network. Like a CDN for AI models.
One great feature of CDNs is the ability to dynamically re-route or deny traffic without redeployment.
When Fable was suddenly retired, we worried about production workloads depending on it. Even Fable aside, models get retired quite often as GPU capacity is heavily contested. Yet our data shows people still having happy production traffic of older model versions!
We're solving this now with AI Gateway Rules. e.g.: you can now rewrite model "routes" on the fly!
𝚟𝚎𝚛𝚌𝚎𝚕 𝚊𝚒-𝚐𝚊𝚝𝚎𝚠𝚊𝚢 𝚛𝚞𝚕𝚎𝚜 𝚊𝚍𝚍 \
--𝚝𝚢𝚙𝚎 𝚛𝚎𝚠𝚛𝚒𝚝𝚎 \
--𝚜𝚘𝚞𝚛𝚌𝚎 𝚊𝚗𝚝𝚑𝚛𝚘𝚙𝚒𝚌/𝚌𝚕𝚊𝚞𝚍𝚎-𝚏𝚊𝚋𝚕𝚎-𝟻 \
--𝚍𝚎𝚜𝚝𝚒𝚗𝚊𝚝𝚒𝚘𝚗 𝚊𝚗𝚝𝚑𝚛𝚘𝚙𝚒𝚌/𝚌𝚕𝚊𝚞𝚍𝚎-𝚘𝚙𝚞𝚜-𝟻
This adds to the repertoire of capabilities and techniques AI Gateway brings to the table to recover lost tokens. If you drop tokens, you lose revenue and customers 💸
Kudos to @rtaneja_ @crowprose @shaper – we went from CLI design to production-grade capability very quickly!
AI Gateway now supports routing rules.
Migrate to new models by setting rules in the CLI, no code changes in your app or agent required. vercel.com/changelog/ai-gate…
Joe McKenney retweeted
Heartbreaking, what an articulation @crowprose
crowprose.com/blog/competenc…
So after all these hours talking about AI, in these last five minutes I am going to talk about:
Horses.
Engines, steam engines, were invented in 1700.
And what followed was 200 years of steady improvement, with engines getting 20% better a decade.
For the first 120 years of that steady improvement, horses didn't notice at all.
Then, between 1930 and 1950, 90% of the horses in the US disappeared.
Progress in engines was steady. Equivalence to horses was sudden.
ALT Engine efficiency over time, showing steady improvement
wake 0.5.0 is out 🌄
Terminal context for Claude Code. Now with LLM-powered summarization and tiered data retrieval—Claude gets the right level of detail without drowning in output.
`wake shell` → work → ask Claude → it already knows
github.com/joemckenney/wake
PTY capture + shell hooks + SQLite + MCP = Claude Code that can see your terminal history.
Wrote up how wake works:
crowprose.com/blog/wake/
@AnthropicAI
stop copy-pasting terminal output into Claude Code
github.com/joemckenney/wake
Annual rewatch of True Detective Season 1, the best show/season ever made. Time is a flat circle but at least Rust Cohle is there to guide me through it.
Joe McKenney retweeted
5 months ago I broke down Figma's new AI onboarding. They're back with a new iteration! The most interesting part: 𝗔𝗜 𝗽𝗿𝗼𝗺𝗽𝘁𝘀 𝗮𝗿𝗲 𝘁𝗵𝗲 𝗻𝗲𝘄 𝘁𝗲𝗺𝗽𝗹𝗮𝘁𝗲𝘀. An updated breakdown 👇
In the last iteration, an AI input form was presented side-by-side with pre-built usecase templates.
This makes sense, they both solve the cold start problem of helping users go from from 0 → .5 (they don't get users to 1 yet).
I wondered if, in the future, AI entry points and templates would merge.
With this new iteration, Figma has essentially made templates from pre-written, use case prompts!
Templates are great at presenting use cases (push). Prompting is great at capturing intent (pull).
This experience is starting to have the best of both worlds, where the entry point into prompting is structured and easy to understand, but I can still edit the prompt to fit my intent.
I like this and I think it points to a strong vision for AI-generated getting-started experiences (rather than just throwing me into an input).
Of course, templates still play a big role for Figma and Figma has a huge community with tons of helpful resources.
But now AI has a much larger in-product entry point than templates.
I could imagine other tools taking a similar approach!
Want a better TS package development toolchain?
Bootstrap your TS packages with pkg-tools!
You'll get a great set of 🛠️ to build|lint|format|clean|dev, all of which are customized via a single config file (pkg.config.ts).
Launch day 🚀
Today we're launching AI Assist, an in-product AI that actually works.
AI Assist automatically crawls your docs and leverages in-product context to deliver personalized and contextual assistance to your users.
Sign up on Producthunt to get notified when we launch
producthunt.com/products/dop…
Joe McKenney retweeted
Another incredibly polished Dopt powered @Superhuman product announcement went out today
Shoutout to primary CTAs that actually enable the thing instead of taking you on a wild goose chase through settings pages
