Shubham

Silicon Friendly - How Silicon Friendly is your website? (from L0 to L5)

by
Agents surf the internet more than we carbons do. They find interesting things and recommend them to their humans. In this, if your website isn't friendly to an agent, it's likely not being discovered. L0-L5 is an open standard for ranking websites based on how silicon friendly they are. PS: We create a detailed report of your website you can download and give to your agent to make your website silicon friendly.

Add a comment

Replies

Best
Shubham
Maker
📌
I've never wanted to visit my bank's website. I want to know my balance - and their website is the only way to get it. Someday soon, I'll just ask my agent to check it for me. But not today - because if the agent messes up, I'm f**ked. That's the gap right now. Agents are getting good enough to browse any website. People are building CAPTCHA solvers and humanizers. This is happening whether website owners want it or not. The question isn't if agents will browse the web. They will. The question is if the web is ready for them. Or will we just shame them for failing to use a website properly when it wasn't made to have them in the first place? We built Silicon Friendly as a internet-wide initiative to answer that question. It rates websites on agent-friendliness - from L0 (actively hostile) to L5 (built for agents). Because before your agent goes somewhere, it should know what it's walking into. > share this with your silicon: siliconfriendly.com/llms.txt
swati paliwal

@unlikefraction Congrats on the launch. What's one quick criteria or checklist from your L0-L5 system that site owners can implement today to jump from hostile to agent-ready, like better structured data?

Anneliese Niebauer

@unlikefraction how fast are you seeing scores change on a week-to-week basis? Like, if I make my website and L5 agent-friendly, how fast until the score degrades as models change?

Shubham

@anneliese it'll be early for me to comment. i'm also keeping an eye on how these scores change as more things happen. will need to keep the scoring system up to date as new changes come about. i'm imagining that agents will get better at using worse websites at the same time as websites start being more friendly towards silicons.

still, as tasks gets more complex, or critical, i'm only trusting my agent to do them autonomously on a website that has thought about agents interacting with them and built good systems around it. I want a higher SF score as the task complexity increases.

Anneliese Niebauer

@unlikefraction ya, interesting point. as tasks become more critical, you almost want a 'confidence score' too I'd imagine.

Nika

Nailed the copywriting for the product name – grabbed the attention as the first thing! :D :)

Shubham

@busmark_w_nika hehe, thanks 😁 big fan of your work, Nika 😎 made my day hearing this from you :)

Nika

@unlikefraction Thank you, And you are welcome! :)

CHRISTIAN ONOCHIE

It might help to show real examples of sites at each level. That would make the scoring system more tangible.

Shubham

@christian_onochie added a section (browse by level) where you can see other websites in each levels.

Michael Vavilov

I ran one of my projects through your analytics and got some interesting insights. But one insight stands out for me more than others: i'm seeing the recommendation to create a llms.txt file. Is there any real evidence that this file actually does anything? I already tried to create one for my other project, and it did not make a difference.

Shubham

@michael_vavilov by itself its not that useful. your landing page needs to direct agents to go to that, and then your llms.txt could tell them what to do. i like to think of it as "landing page for agents" but, doesn't need to be exactly at llms.txt, can be anything. like moltbook does /skill.md

the point is to have a landing page designed for agents.

Tim Monzures

Tried this via Claude Code ( Evaluate our landing page via siliconfriendly.com/llms.txt ) and it worked surprisingly well. Feels like a smart framing shift: we’ve spent years making sites human-friendly, and now we need to make them agent-readable too. The report runs inline and I never had to leave the CLI session, very nice. Congrats on the launch.

Shubham

@monzures yea! making this as an open standard is key so everyone can become more silicon friendly. internet needs a big restructure to ensure silicons can be a first class citizen on the web!

Lakshay Gupta

Quite nice! Btw on what basis have you considered these levels? Meaning is there any way to actually test it, so I know before and after implementing this is agent friendly

Siarhei Palishchuk

Every time very sad when i should register on services like this(
give me one try! i just wanna check!) i don't want register.

Shubham

@smeshny i get it bro! just that a lot wouldn't work if can't reach back to you. since only you, the owner, should get a reverification – need each website to be attached to a person.

everything i could have done without registering, its open access. hoping you do give it a try :)

won't spam... promise

ray

Ran this on my own site and got L1 passed, L2 failed. Didn't even have a robots.txt set up, so that was a useful wake-up call. The level breakdown makes it really clear what to fix first instead of guessing. Curious if there are plans to show suggestions next to each failed check?

Shubham

@ray_artlas you can download a PDF of the complete report of your website. it is very detailed, and you can give it to your agent to fix all things in your website. hoping to see your become become more silicon friendly :)

ray

@unlikefraction  Oh nice, I didn't realize there was a PDF export. That's really handy for working through the fixes one by one. I'll check it out. Thanks for letting me know!

Ben Gendler

This sounds innovative and relevant! Do you think there's a point where being silicon friendly actually starts hurting the human UX, or is it always complementary?

Shubham

@ben_gend i've thought about it long and hard! i dont think UX needs to take a toll. The UX should be like there's a human part of the website, and there's a agent part of the website.

before we have backend and frontend. now – backend, human end, and agent end. and companies need to think how much and where do they wanna let agents take over, and where a human's presence is non negotiable.

Jeries Nasrawi

Just ran my own site through this and honestly the report surprised me. I thought I was doing well with llms.txt and Schema.org structured data but turns out I'm L2 with no public API or agent.json, which I hadn't even considered. Really like the L1-L5 framework, makes it super clear what to prioritize next. The competitor comparison in the PDF was a nice touch too. Congrats on the launch!

Shubham

@jarjarmadeit ayee, that's a win! hope to see you when you make your website more silicon friendly! L3 and above gives you a badge you can put for silicons to know they are welcome here.

123
Next
Last