Product judgement
Turn an ambiguous need into a workflow with explicit users, constraints, and success criteria.
I take AI agents from promising demos to products that hold up in real workflows.
Enter the work
From workflow modelling and agent behaviour to full-stack delivery, these are three products I helped move toward real users.
Turn an ambiguous need into a workflow with explicit users, constraints, and success criteria.
Design clarification, memory, tools, retries, and state recovery as one dependable loop.
Carry the product from interaction and APIs through asynchronous jobs and production behaviour.
A creative environment that keeps brand context, generation, and iteration in one product surface.
At Tezign, I worked on a commercial-research agent workflow spanning clarification, persona interviews, memory, and resilient asynchronous tool execution.
I worked across the product and full-stack workflow that helps an editing agent shape scripts, organise source footage, and move toward a deliverable cut.
Long-form essays and compact research notes from the things I am building and learning.
Original projects and contributions to products maintained by other builders.
4021+ GitHub StarsBuild an agent harness from first principles: loops, tools, memory, and multi-agent work.
Original project · LLM from scratchRebuild a small language model from Transformer through SFT, one experiment at a time.
Upstream contributor · 3 merged / 1 open
Contributed activity heatmaps, fresh provider sync, accurate reset windows, and compact token totals.
I’m open to AI agent and full-stack product engineering opportunities. Ask for my résumé, dig into a project, or tell me what your team is trying to ship.
What is your team building?
What is hardest to move forward?
What should this engineer deliver?