FIG. 01
active
AI systems that survive production
Patterns for shipping LLM systems that hold up under real load: multi-agent orchestration, incident response, cost, and sandboxing the agents themselves.
aLLMbAWScDocker
9 entriesOpen +
Writing1 live collection
Filed by the
problem it solves.
I sort by the problem, not the tool, because the tool is just the answer that happened to win. The production-AI collection is ready now; the rest earns its place when there is real work to show. Think in tech instead? Flip the lens. Want it gentler or deeper? Set your level and the writing follows.
Lens
Read as↳working implementation · tests
Get in touch
Working on a system
that has to hold up?
If you are wrestling with agents, ML infrastructure, or the operational trade-offs between them, tell me what you are building.
A real conversation
Email is the best way to reach me. I read every message and reply myself.
Email Asifcodewithnumbers@gmail.com