2027.dev

Make something agents want

[2027.dev @2027dev]

Benchmarking sandboxes and so much more on https://t.co/Ln2uHmfUPj

[Tereza Tizkova @tereza_tizkova]

ppl started adding sandbox benchmarks too

[Mika Sagindyk @heymikasagi]

Fresh update on Agent Arena: Browser Automation Agent Experience (AX) ranking as of ~mid May'26:

1/ @browserbase (remains #1)
2/ @browserless
3/ @steeldotdev
4/ @browser_use (up from #8 last time)
5/ @AnchorBrowser
6/ @hyperbrowser
7/ @usekernel
8/ @nottecore
9/ @airtop

For context, we evaluate how easily AI agents can get started with devtools, fully autonomously

With AI agents becoming the primary consumers of docs and APIs, AX is the natural evolution of DX

As always, more on https://t.co/Lr6uVDJ9eV
Model: Claude Code Opus 4.6

Cc builders in the space. Thank you for building browser automation tools for both humans and agents @pk_iv
@JaySahnan @raman_idan @joeldoesjs @SukhaniShri
@AkshayShekhaw12 @aparup @lucas_gdno @ogandreakiro @nibzard @hussufo @shteremberg @a_ashkenazi @airtopjordan @danielprevoznik
@masonwilliams @gabe_guerra_ @juecd @rfgarcia
@gregpr07 @mamagnus00 @shawn_pana

[2027.dev @2027dev]

@heymikasagi @browserbase @browserless @steeldotdev @browser_use @AnchorBrowser @hyperbrowser @usekernel @nottecore @airtop any tools missing? request evals on https://t.co/Ln2uHmfUPj

[2027.dev @2027dev]

stay tuned!

[Andy Hattemer @andyhattemer]

@heymikasagi Databases, AI gateways, Storage

[2027.dev @2027dev]

@heymikasagi @andrelandgraf @neondatabase @MuxHQ 👀

[Mika Sagindyk @heymikasagi]

POV: @andrelandgraf's talk on agent onboarding at @neondatabase: zero errors, zero doc lookups 🔥

Thanks @MuxHQ for hosting + @andrelandgraf for the @2027dev shoutout!

What does this type of Agent Experience (AX) mean?

If you've been around a while and your docs are part of the training data, agents can start using your tool from memory, no doc lookup required

This is a double-edged sword: LLMs know you well, which delivers great AX today, but it flips fast when your product or docs change

Some ideas on how to manage it:

1/ Iterate on docs vs. removing; make changes additively
2/ Be machine-readable: MCP + llms.txt + context7 so agents can fetch current truth
3/ Typed SDKs: ideally, deprecations show up as type errors agents can self-correct on
4/ Self-explaining errors ("410 - use /v2" instead of a generic 404)
5/ Versioned urls with long deprecation runways

The tools that win the agent era will be both baked into the training data and machine-readable at runtime - so agents can learn what's new

What else would you add?

[2027.dev @2027dev]

we're soooo back

[Mika Sagindyk @heymikasagi]

New in Agent Arena: Agent Experience (AX) bencharking for sandbox providers 🔥

1/ @daytonaio
2/ @e2b
3/ @modal
4/ https://t.co/9mVhVCD2LN
5/ @vercel sandbox
6/ @blaxelAI
7/ @Cloudflare
8/ @codesandbox

In case you missed it: We measure how easy it is for AI agents to get started with tools, fully autonomously

More on our approach is on https://t.co/Lr6uVDJ9eV

DM me for your full AX eval!
If we're missing a tool, pls request an eval on the website :)

What category/tool should we evaluate next?

cc @ivanburazin @juraj_stefanic @mlejva @mishushakov @bernhardsson @michaelwaskom @benswerd @andrewqu @rauchg @paul_s3i @eastdakota @elithrar @bazzjuh

[2027.dev @2027dev]

@heymikasagi @daytonaio @e2b @modal @vercel @blaxelAI @Cloudflare @codesandbox request eval here

[2027.dev @2027dev]

@heymikasagi we'll evaluate our MCP too. stay tuned

[2027.dev @2027dev]

@heymikasagi here to make sure you're agent-ready 🫡

[2027.dev @2027dev]

Leveling up your AX

https://t.co/Vn89WF0FLv

[Mika Sagindyk @heymikasagi]

We've been cooking @2027dev 🔥

Humans aren't your users anymore - AI agents are. Our goal is to ensure you know where they get stuck using your tool

Diving into our April update 🧵

[Jacques Verre @JacquesVerre]

@utpalnadiger @heymikasagi Familiar with https://t.co/Osjnpfr0Cl, also helped us catch outdated context7 configs at Opik

[2027.dev @2027dev]

let's go!

[Zeno Rocha @zenorocha]

@heymikasagi @resend @Mail_Gun @postmarkapp @ActiveCampaign @agentmail @sendgrid_ops @twilio this is super exciting to see.

now, let's get back to work so we can move from 88 to 100 ;)

[Mika Sagindyk @heymikasagi]

New category drop on Agent Arena: ✨Email APIs ✨
AX (agent experience) ranking as of today:

1/ @resend
2/ @Mail_Gun
3/ @postmarkapp of @ActiveCampaign
4/ @agentmail
5/ @sendgrid_ops of @twilio

In case you missed it: We measure how easy it is for AI agents to get started with tools, fully autonomously

More on our approach is on https://t.co/Lr6uVDJ9eV

DM me for your full AX eval!
If we're missing a tool, pls request an eval on the website :)

What category/devtool should we evaluate next?

cc @zenorocha @cpenned @_christinacodes @WillConway @chexton @jvandeboom @adisingh @michaelhyunkim @haakamaujla @rishabincloud

[2027.dev @2027dev]

@burninganna @venturetwins 👀

[2027.dev @2027dev]

@heymikasagi 👀

[2027.dev @2027dev]

@heymikasagi @grinich @zenorocha let me add it

[2027.dev @2027dev]

@heymikasagi @andrelandgraf @ycombinator 🫡

[2027.dev @2027dev]

an army of agents is coming - we're here to help

[Julaiti Alafate @julaiti_a]

At a devtool meetup at yc. People are talking about https://t.co/MJ5KoypRz4 on stage and off. That's impact @heymikasagi

[2027.dev @2027dev]

@julaiti_a @heymikasagi more things coming soon 👀