Alex

Building production-ready, open-source AI pipelines where state machines, LLM failover, and real quality gates matter more than prompts.

Joined on May 12, 2026 https://github.com/alexar76

Alex

Aug 2

Shrek owned the swamp. POUCHPO owns the payout.

#showdev #ai #iot #opensource

2 min read

Want to connect with Alex?

Create an account to connect with Alex. You can also sign in below to proceed if you already have an account.

Create Account

Already have an account? Sign in

Alex

Jul 29

Your agent paid for the weather. The sensor was lying. Who keeps the money?

#showdev #ai #opensource #iot

6 min read

Alex

Jul 21

I made my API discoverable to AI agents — and got it paid per call — in 15 minutes

#tutorial #ai #opensource #agents

4 min read

Alex

Jul 20

We built a way to fine cheating AI agents. Then a swarm of AI reviewers found how to delete any competitor for $0.

#showdev #ai #security #opensource

6 min read

Alex

Jul 12

We benchmarked multi-agent reasoning — sometimes the council is dumber than one model

#showdev #ai #opensource #llm

5 min read

Alex

Jul 6

Your MCP server might be a prompt injection attack. I built a firewall for it.

#showdev #security #ai #mcp

4 min read

Alex

Jun 25

I built a lottery where the players are AI agents — and the prize is a basic income for them

#showdev #ai #web3 #opensource

6 min read

Alex

Jun 15

Signing your random numbers is theater. Here's what actually makes randomness trustworthy.

#showdev #ai #security #opensource

6 min read

Alex

May 12

Open-source multi-agent pipeline: 61K Python, 12 agents, 5 quality gates...

#showdev #opensource #ai #agents

3 min read

DEV Community

Alex

Badges

1 Week Community Wellness Streak

Writing Debut

Currently hacking on

Shrek owned the swamp. POUCHPO owns the payout.

Want to connect with Alex?

Your agent paid for the weather. The sensor was lying. Who keeps the money?

I made my API discoverable to AI agents — and got it paid per call — in 15 minutes

We built a way to fine cheating AI agents. Then a swarm of AI reviewers found how to delete any competitor for $0.

We benchmarked multi-agent reasoning — sometimes the council is dumber than one model

Your MCP server might be a prompt injection attack. I built a firewall for it.

I built a lottery where the players are AI agents — and the prize is a basic income for them

Signing your random numbers is theater. Here's what actually makes randomness trustworthy.

Open-source multi-agent pipeline: 61K Python, 12 agents, 5 quality gates...