About

Developer advocate passionate about Agentic AI, AI developer tools, and building products that empower engineers to ship faster. I love exploring autonomous AI systems, developer ecosystems, growth strategies, and emerging AI workflows while connecting with builders across the tech community.

Badges

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

Forums

Why AI agent workflows still break in production (and what we did about it)

We have been building agent infrastructure for a while. Three problems come up constantly in production multi-step workflows and nobody talks about them enough.

Pre-execution verification Agents build plans and execute them. There is no standard way to know a plan is cycle-free, type-compatible across every tool boundary, and policy-compliant before it runs. The first time you find out something is wrong is when a step fails halfway through.

10d ago

DataGrout Flow - Multi-step workflow orchestration with human oversight.

AI agents running multi-step workflows have no reliable way to pause for human approval, verify a plan before it runs, or handle missing data mid-run. DataGrout Flow solves all three. Four MCP tools. Works with Claude, Cursor, or any AI agent.

1mo ago

DataGrout Math - Deterministic numeric tools for AI agents, zero credits

Deterministic numeric tools for AI agents. Generate sequences, compute statistics, fit regressions, detect outliers, and normalize data, all in-process, no LLM, no credits. Every result is reproducible and verifiable. Works with any MCP-compatible agent.
View more