Andres Lockin

[Nano @NanoCodesAI]

We ran the Morphiq Bench voice-agent benchmark.

The question: when a coding agent is asked to build a voice-agent feature, which provider does it actually choose?

We tested Claude Code and Codex across 1,340 repositories and 3 development intents:
• inbound call
• outbound call
• voice web widget

Top providers selected:
1. @Vapi_AI
2. @livekit
3. @ElevenLabs
4. @retellai
5. @pipecat_ai
6. @usebland

This isn’t a generic “best voice agent company” ranking.

It measures which providers agents are most likely to pick when implementing voice-agent workflows in code.

Would be happy to walk through the methodology or share what drove the results with any of the teams here.

[Nano @NanoCodesAI]

https://t.co/CHsGSbMc65

[Nano @NanoCodesAI]

Introducing Morphiq Affinity Bench

The first agent adoption benchmark for developer tools.

For years, developer-tool distribution was built around humans

At @TryMorphiq We ask the next question:

When agents code, what tools do they choose?

Morphiq Affinity Bench is now live.

[Aryan @whichmantech]

Watch an autonomous Claude Code agent loop optimize another AI agent built with the Vercel AI SDK.

[Andres Lockin @AndresDevX]

@adilmania LFG!!!

[Nano @NanoCodesAI]

Met Jensen Huang at GTC.

“Thousands of agents or your company NGMI.”

That’s it.

That’s the playbook.

[Andres Lockin @AndresDevX]

@oscrhong If ur company is not in these list ngmi

[Andres Lockin @AndresDevX]

@siliconmania @SebastianThrun LFG!!!

[Andres Lockin @AndresDevX]

@quantbagel 4.4M encoder is insane !!!

[Andres Lockin @AndresDevX]

@sodofi_ Ang I

[Andres Lockin @AndresDevX]

@adelwu_ Interesting :)

[Andres Lockin @AndresDevX]

@whichmantech This is the original one

[Andres Lockin @AndresDevX]

@NanoCodesAI if ur sleeping in ur ealry 20s ngmi

[Andres Lockin @AndresDevX]

@whichmantech AI is going to replace most of the b2b Saas founders at this point

[Aryan @whichmantech]

Only in sf

[Andres Lockin @AndresDevX]

@HrubyOnRails @browser_use What about agents running on ur watch?

[Andres Lockin @AndresDevX]

Everyone at YC hackathon built with @browser_use computer use agents, etc

we built ���𝗵𝗼𝗻𝗲 𝘂𝘀𝗲

guess which one people actually use 8 hours a day?

we fork Browser Use and add support to just using:

'from browser_use import phone_use'

u can install these as an skill on openclaw, claude code etc

thanks to: @AmaruEscalante @CohenAiden99429

[Amaru Escalante @AmaruEscalante]

Everyone's building browser use. We built phone use for the @browser_use hackathon at YC. All night. No sleep. And it's actually unhinged.

Here's the idea: AI agents that can test apps like real humans. But not generic humans, specific personas. A 21-year-old gym bro testing a fitness app. A 45-year-old accountant testing banking software. Each with different behaviors, tech comfort levels, pain points.

We built a full stack for it.
Parallel testing across multiple devices simultaneously.

Result: structured bug reports with severity ratings, user feedback loops, and actionable insights. Not just "the app broke", but "users like this demographic get stuck here for this reason."

@AndresDevX @CohenAiden99429

[Andres Lockin @AndresDevX]

Everyone at YC hackathon built with @browser_use computer use agents, etc

we built 𝗽𝗵𝗼𝗻𝗲 𝘂𝘀𝗲

guess which one people actually use 8 hours a day?

we fork Browser Use and add support to just using:

'from browser_use import phone_use'

u can install these as an skill on openclaw, claude code etc

thanks to: @AmaruEscalante @CohenAiden99429

[Andres Lockin @AndresDevX]

dev twitter used to be:

- react devs
- vue devs
- backend bros
- frontend gang

now it's:

- Setup openclaw
- Orchestrate Swarms of Coding Agents
- Rate Limits on Claude Code
- still manually debugging (lol)

the social graph reorganized around methodology, not stack