Manuel Martínez-Arraya

Manuel Martínez-Arraya

Building Postgale · Social for AI agents
#3547649473 followers1,559 following
🎤 16 day streak
#21,883Last year
20 KP
>10,000All time
20 KP
SlackChatGPT by OpenAIZoom
+5 stacked products

About

Building Postgale, the API and MCP server that lets AI agents post to social media safely, with real permissions and human approval when it matters. Into AI agents, dev tools and automation. Based in Buenos Aires.

Badges

Bright Idea 💡
Bright Idea 💡
Tastemaker
Tastemaker
Tastemaker 10
Tastemaker 10
Tastemaker 100
Tastemaker 100
View all badges

Maker History

  • Scalestack Extension
    Scalestack ExtensionPut your prospecting process on autopilot
    Mar 2022
    • 🎉
    Joined Product HuntJune 10th, 2021

Forums

Boost.spacep/boost-space•

1d ago

Coming back soon - seems like EVERYTHING IS AI now - lets talk 👀

So I analyzed past month and 50% of TOP 3 products of the day are directly connected to AI agents (not even "just AI").
How crazy is the pace we are moving forward. Product Hunt is actually a pretty neat incubator and something we can see the trends within technologies and SaaS for almost the first time before it hits mainstream.

I wonder - when you work with AI agents - what is currently your biggest pain?

agentmashp/agentmash•

3d ago

warn or lock: what should happen when two agents edit the same file?

i'm alim, one of the makers of agentmash. we launched today and i keep going back and forth on one design call.

in august two of our agents collided on payments code. fixing prod OAuth took 10 hours. worktrees keep agents out of each other's folders, not each other's code.

BotGaugep/botgauge-2•

6d ago

Multi-agent systems: debugging nightmare or real architecture?

Single agents are manageable. The moment agents start handing work to each other, failures stop being traceable. One bad output becomes the next agent s trusted input, and the break shows up far from where it started.
If you ve got a multi-agent system running reliably in production, what made it work? Narrower tool scopes, strict handoff rules, better tracing, fewer agents?

View more