_ | | | |===( ) ////// |_| ||| | o o| ||| ( c ) ____ ||| \= / || \_ |||||| || | |||||| ...||__/|-" |||||| __|________|__ ||| |______________| ||| || || || || ||| || || || || ------------------------|||-------------||-||------||-||------- |__> || || || || hit any key to continue Hi, I'm Kautuk
I like building LLM-powered systems that actually do things — especially around tool calling, agents, and end-to-end execution, not just chat.
- Tool-augmented LLMs: Designing schemas, orchestration layers, and safety rails that make tool calling reliable at scale.
- Agentic workflows: Multi-step plans, background execution, and feedback loops where models can observe, remember, and act.
- Evaluation & observability: How to measure agent quality beyond accuracy — latency, robustness, user trust, and "time-to-done".
- Human-in-the-loop control: escalate UX patterns so users feel in control while agents do the grind.
- Conscious Engines – exploring the boundaries of agentic AI, tool orchestration, and autonomous systems that learn and adapt.
- Felix – a proactive AI companion that sits inside your workflow, watches for patterns and commitments, and actually execute tasks without user intervention.
- Better agent memory & context: Turning raw event streams into structured memories agents can safely act on.
- Actionable > informational: Every model output should come with a next action, not just a paragraph of text.
- Observation without action is just surveillance. Action without observation is brittle automation.
- The interesting space is in the middle: agents that watch just enough, propose concrete, reversible actions, and learn from what users do.
- Great AI doesn't feel like a chatbot — it feels like someone quietly watching your back and taking care of the boring parts.
- Languages: TypeScript, Python, Rust, C++
- Frameworks: Full stack, I kinda do everything