Gil Raitses
Embedded delivery
Three programs I built and shipped, and how each one maps to embedding with an engineering team and owning delivery end to end.
I take a research problem from raw data through a working, deployed tool, get it adopted by the people who use it and run the agent work behind it so it stays coherent across many repositories and sessions. The same instincts carry to deploying a product inside a customer's environment. This page links the live demos so you can open them directly.
magniphyq
magniphyq is an experimental research platform, a node graph where a whole pipeline from raw data through analysis to simulation runs, can be inspected and can be cloned, turning raw capture into validated data. It is built, verified and deployed live on AWS, where it hosts a synapsin condensate phase-diagram campaign of 135 conditions with 109 collected runs.
Where it maps: I build and ship a full-stack product, deploy it into a running environment and design the integrations that carry it into a team's workflow, including a Slack path for shipping a run and a Cursor path for building modules and cloning a pipeline.
Central Casting
Central Casting is the method I run agent work through. It assigns a cast of agent lanes, each a role with explicit inputs, outputs and an escalation rule, records checkpoints as the unit of memory and runs an alignment check that flags when the structured record and the human-readable views diverge.
Where it maps: it is a working answer to the question a customer asks when they scale agents, namely how to trust and audit what the agents did. It doubles as a measurement surface for agent behavior across real, multi-repository work.
aimez.ai
aimez.ai is an applied research program that takes public traffic-camera frames through computer-vision models into a continuous stress field, then into pedestrian routing that respects measured burden. It carries the work end to end, from raw field data to a public site with notes, figures and validation briefs.
Where it maps: it is field deployment of the messy kind, turning ambiguous real-world data into a working system, with customer-facing documentation that explains the process to a non-specialist.
The throughline to the team's objectives
Stated plainly, here is what forward deployment needs and where I have already done it.
- Deploy and integrate in a real environment. magniphyq is live on AWS behind a stable address, with a roadmap of integrations into Slack and Cursor.
- Earn adoption against real resistance. I built retrovibez, a larval reverse-detection pipeline, and a mechanosensation group adopted it after I visualized every detected event so they could check the calls, demoed it in a lab meeting, trained new researchers and wrote the install and usage docs.
- Make agent work reliable at scale. Central Casting keeps long, multi-repository agent work coherent and auditable, which is the surface a team needs to trust agents in production.
- Translate an ambiguous problem into a shipped system. aimez.ai runs from raw camera data to a routing tool and a public, documented site.