AI agents & automation
Agentic systems that pursue a goal, use your tools and data, and act in your systems, with the evaluation and guardrails to run in production.
AI engineering company
We build production AI systems with your team.
Our model is forward-deployed AI engineering. Nazmi works inside your team and owns the technical path, from the first architecture to the running system.
What Nazmi does
AI agents, integration, and production engineering.
We build AI applications for your workflows and connect them to the systems your team already uses.
AI integration & production engineering
We connect AI applications to your data and systems, deploy them in your environment, and leave your team able to run them.
Experience behind Nazmi
Isaac Kargar, founder
10+ years building production AI and machine learning systems. His background includes roles as Principal AI Scientist at In Parallel, co-founder and Chief AI Officer at Resoniks, and AI engineer at Silo AI (now part of AMD), alongside PhD research in machine learning and robotics at Aalto University.
Selected writing
Depth you can read.
Recent technical notes on AI engineering, models, and production systems.
Before an AI agent touches customer data: six production gates
A demo shows that an agent can complete a task. These six gates ask for evidence that it can operate within a bounded workflow, with limited authority and a recovery path.
Read →Context Compaction in LLM Agents: Part 2 - Learning to Compact
SelfCompact, CompactionRL, and ACON use different ways to decide when and how an agent should compress its context.
Read →Context Compaction in LLM Agents: Part 3 - Post-Hoc Compilation
How Lerim compiles completed agent traces into cited context records that can support later work, while online compaction keeps the current run within its context budget.
Read →Work with Nazmi
Bring Nazmi in on the work that has to ship.
Tell us what you are building, what exists today, and where your team needs help.
Start a conversation or book a 20-minute call →