Dmitrii Konyrev

Dmitrii Konyrev

Making AI adoption cheap and reliable
#952149928 followers14 following
⚡️ 4 day streak
#3,148Last month
11 KP
>10,000All time
15 KP

About

CTO at Argmin AI. 12 years building ML and GenAI systems, 9 of them leading the teams behind them. I've spent the last few years on the hardest part of shipping AI: knowing whether the output is actually good. At SuperAnnotate I built LLM-as-a-judge evaluation and data-curation pipelines; before that, credit-risk models for banks. Now I'm building Judge Builder at Argmin AI: it lets any team create an evaluator calibrated to their own examples, so it scores AI outputs the way they would, not with a generic metric. Based in Barcelona.

Badges

Tastemaker
Tastemaker
Gone streaking
Gone streaking
Gone streaking 5
Gone streaking 5

Maker History

Forums

•

18d ago

Argmin AI - Test AI agent workflows without ML expertise

For teams and founders shipping agentic AI workflows and features. Generic metrics don't speak your product's language, so a new prompt, model, or RAG change can pass them and still ship real issues. A quick manual check catches even less. You don't need annotated data, an ML team, or a month to be safe from regression. Drop in your agent's task, business rules, docs, and examples, and Argmin AI builds an evaluation you run before every change.
•

5mo ago

Argmin AI / Cost Optimization for AI - Reduce AI agent costs by 10x while keeping quality stable

If your product runs on LLMs (API features, agents, RAG, copilots), cost becomes part of quality. At $5k+/month, optimization is no longer optional. Costs may spike unpredictably. ArgminAI optimizes prompts, context budgets, model routing, RAG, and agent workflows together, then checks quality with evals and guardrails (tests, gates, judges) tailored to your goals. Start with the cost calculator or a free savings assessment: https://app.argminai.com/signup
View more