Agentic workflow consulting
We build agentic workflows that sit on top of systems that actually decide something. An LLM agent interprets the request, a solver or model produces the answer deterministically, and the agent explains the tradeoffs — so the output is correct, not merely plausible.
That pattern shows up in two places in our work: the optimization models underneath operational decisions, and the Databricks platform where the pipelines and agents are built and governed.
Two tracks
Operational Optimization
Network optimization, supply–demand matching, vehicle routing, scheduling, and predictive modeling — solved to provable optimality, then wrapped in an agentic layer an operator can actually talk to.
Databricks Certification
Preparation for the Data Engineer Associate and Generative AI Engineer Associate exams, mapped section by section to the official guides — including the agent and RAG material the GenAI track now tests.
See it work
A running optimization model you can change and re-solve — the pattern above, live.
Talk to a solver
Describe a supply-chain disruption in plain English. An agent rewrites the optimization spec, CVXPY re-solves it, and the shadow prices say what to do next.
How an engagement runs
- 01
Scope
Establish what decision is being made, how it is made today, and what a better one is worth. Short, and it ends with a written problem statement rather than a proposal.
- 02
Model
Formulate and validate against historical decisions. The model has to beat the status quo on data you already have before anything gets built around it.
- 03
Deploy
Ship it into your cloud and your data, with the pipeline, tests, and monitoring that make it survivable.
- 04
Hand over
Documentation, the reasoning behind the formulation, and enough transfer that your team owns it. No lock-in to the consultant.
Toolkit
Optimization & OR
- Linear & mixed-integer programming
- Network and supply–demand optimization
- Vehicle routing (VRP / CVRP)
- CVXPY
- Google OR-Tools
- Sensitivity & duality analysis
Machine Learning & Statistics
- Probability & statistical modeling
- Time-series analysis
- Feature engineering
- Model validation
- Scikit-learn
- Pandas / NumPy
AI & Agentic Systems
- LLM-driven workflows
- Agentic task orchestration
- Natural-language → structured model translation
- Tool-using agents
- AI-assisted development pipelines
Data & Cloud Engineering
- Azure Data Factory
- Databricks
- SQL / PostgreSQL
- Google Cloud Run & Cloud Build
- Python
- TypeScript / Next.js
Have a workflow worth automating?
The first conversation is about whether an agent belongs in the loop at all.
Start a conversation