UX Researcher. $0/14k MRR. Building: https://xitter.gq/t.co/jceNEfmdHd - Check AI readiness https://xitter.gq/t.co/jao4pfvDW8 - AI directory
Joined May 2023
- Tweets2.8K
- Following42
- Followers689
- Likes3.4K
AWS and Cloudflare now let you charge AI agents per request with x402.
It's worth mostly if you sell API calls.
Read more: genready.ai/blog/should-your…
ALT x402 agent payment protocol illustration
3/ Visual Context
Crawlers don't "see" bold hero text, layout contrast, or sleek cards. They see tokens.
Without clean, semantic markup (<article>, structured headings, table elements), an AI crawler can easily misinterpret your content.
If your brand isn't being cited accurately in AI answers (ChatGPT, Perplexity, Claude), it might not be an authority issue. It might be visibility issue.
Read the full breakdown on what AI crawlers can't see (and how to fix it): genready.ai/blog/what-ai-cra…
Your website might look flawless to users, but AI search crawlers are likely missing crucial parts of it.
Here are the biggest blind spots LLM bots hit when trying to read your site 👇
1/ Client-Side JavaScript
Most AI crawlers don’t read JavaScript because it is computationally expensive. Content created using client side JS is invinsible to most AI crawlers.
If you want AI agents to use your product successfully, marketing copy won't cut it. You need executable instructions.
Follow this simple 3-step formula to make your site agent-ready:
Write a simple instructions file (SKILL.md) and list it at /.well-known/skills/index.json.
It teaches tools like Cursor, Claude, and Copilot your exact APIs, workflows, and edge cases so they understand how to use your product.
If you run a SaaS, dev tool, or complex web app, this single standard makes you agent-ready across 40+ AI platforms overnight.
Read the full breakdown on how to publish your first skill here: genready.ai/blog/agent-skill…
Kris Lukanov retweeted
Introducing DecisionModels @decisionmodels_
I've spent the last four weeks benchmarking decision models (I run JevBench).
Today I'm launching the place to actually use the best ones:
decisionmodels.io
➡️Top open models
➡️Up to 4x faster on our own REAX engine
➡️From $0.019 per 1M input tokens.
Expect more reveals soon, and read 👇
Kris Lukanov retweeted
Official JevBench results:
Microsoft-Decision-1 scores #6 in its peer group of API provided decision models.
Compared with Jev it performs strong on many typical use cases, most notably on Recruiting, Risk assessment, Gaming, Advertising, Science and Moderation.
It's also the strongest API provided model in the top 10 in mixed-language tasks.
In our headline ranking for API offered models Jev superseeds it on #4 and Sage leads on #1.
Please be aware that JevBench seperates the leaderboards of
- API offerered models such as Microsoft-Decision-1
(found here: benchmarkheaven.com/jev-mode…) and
- open weights models
(found here: benchmarkheaven.com/jev-mode…),
because speed and cost can only be scored in a fair way within these seperate peer groups.
In a mixed leaderboard of open and API hosted models it lands #12 on the composite score.
It's a good model, and certainly will find its customer base, given Microsofts strong position in enterprise compliant cloud offerings.
Congrats @Microsoft!
Introducing Microsoft-Decision-1, our new model for fast decision-making.
It delivers top performance on structured decision tasks, outperforming both LLMs and other decision models in latency and quality.
We’re already testing it across Microsoft for everything from incident response and quality control to scientific discovery.
Kris Lukanov retweeted
Amzing, @satyanadella presenting @Microsoft s first decision model Microsoft-Decision-1, referencing JevBench all over their launch video. 🔥🔥🔥
I will immediately get going and benchmark it, can't wait to show you all the results!
Introducing Microsoft-Decision-1, our new model for fast decision-making.
It delivers top performance on structured decision tasks, outperforming both LLMs and other decision models in latency and quality.
We’re already testing it across Microsoft for everything from incident response and quality control to scientific discovery.
Which agentic commerce protocol should your store run? UCP or ACP?
Most stores need both. They do different jobs now, and your platform already decides most of the setup.
Here is what to check.
ACP gets you found in ChatGPT. You send a product feed, and the shopper pays on your own site.
UCP gets you bought. Agents in Google AI Mode, Gemini and Copilot fill the cart and check out for the shopper.
Neither one charges a fee. You pay normal card processing.
A 2-minute test: open yourstore.com/.well-known/uc…
JSON there = agents can find your UCP setup.
404 = they cannot buy from you through UCP yet.
Then check that robots.txt lets OAI-SearchBot crawl your product pages.
Full guide: genready.ai/blog/which-agent…
Pilot NLWeb only when your problem is conversational search over live data, and stale third-party indexes visibly fail your users. Events, listings, and inventory qualify.
Read more in GenReady blog: genready.ai/blog/three-ways-…