Applied lab behind Taylor Sando's consulting on AI-agent control planes, reliability, and research-driven system design.
This is the proof layer for that work: live systems, ontology research, product experiments, and current threads around dispatch, knowledge curation, and interface design.
Teams adding AI agents, automation, or orchestration to real workflows and needing clearer boundaries before scale.
Reviews, advisory, and build support around routing, auditability, approval paths, ontology, and operator visibility.
taylorsando.com is the concise consulting entry point. Sandolab is where the live systems, research threads, and public proof surfaces stay inspectable.
Most teams do not need a generic AI strategy deck. They need a clearer control plane: what the agents can do, how work is routed, where approval belongs, and how failures are audited.
Best for teams piloting coding agents or workflow automation and needing boundaries before scale.
I trace the current workflow, identify missing approvals, hidden reliability risks, and the control-plane surfaces that need to exist.
Deliverable: written review, risk map, and prioritized next steps in about 2 weeks.
Best for teams that already know the problem and want routing, auditability, or operator tooling built.
I implement the missing control-plane pieces: work isolation, review hooks, agent lanes, knowledge surfaces, and monitoring paths.
Deliverable: working implementation plus handoff. Usually 2 to 4 weeks.
Best for teams making repeated architecture and agent-policy decisions under shipping pressure.
Ongoing technical leadership around agent adoption, ontology design, workflow reliability, and execution sequencing.
Deliverable: recurring reviews, decision support, and implementation guidance over 3 to 6 months.
This site is where the consulting claims connect to live systems and current research. It is not the short pitch; it is the surface you open when you want to inspect how the work thinks.
Mesh, Orchestrator, OCC, and Console cover file activity, routing, policy, and operator-facing workflows.
Browser Bridge and the research lanes turn browsing, capture, and deep-research workflows into part of the stack.
Digital ontology, payment ontology, and belief maintenance keep vocabulary, delegation, and evidence coherent.
WinWar, tracking and overlay systems, Hockeypedia, QEDViz, and community experiments act as live proving grounds.
Worktree isolation, task routing, review hooks, operator visibility, and the surfaces needed to keep agent work defensible.
Seed, collect, synthesize, and follow up on research topics without losing the thread between source material and decisions.
Ontology work for control planes, payments, and broader digital systems when the vocabulary itself is part of the architecture problem.
Game systems, overlay tools, analytics, and proof tooling give the architecture pressure from real interfaces instead of staying abstract.
Use taylorsando.com for the concise consulting version. Stay here when you want to inspect the proof layer in public.
Public systems and experiments that show the range of the lab. They are supporting proof, not the main consulting offer.
sando-tracker, learning-overlay, personal-usability
Current attention and overlay work across a monitor-focus service, world-model editor, X11 HUD experiments, and desktop attention services.
Strategy-game engine, replay, projection, and tutorialization
A strategy-game research project built around a TypeScript engine and browser projection layer, focused on legality, consequence, replay, inspection, and guided onboarding for complex state.
Layered thesis, belief maintenance, and stack-model research
A living ontology research corpus mapping delegation, authority, retrieval, trust, and control surfaces across the digital stack, with Mesh-backed belief maintenance around the long-form thesis.
Proof visualization and study workspace
A proof and study system with shared proof routes, activity surfaces, compute/verification services, and Cloud Run deployment paths.
Neighborhood demand aggregation and cooperative logistics
An applied experiment in local coordination: aggregate household demand, help small grocers run batch orders, and build the adapter layer between community relationships and lightweight logistics systems.
Trade lineage and NHL data work
Hockey data project focused on trade lineage, player/game ingestion, and public analytics surfaces.
One public proof thread is the research workflow: notes, deposits, and open questions turning into a repeatable loop of collection, synthesis, and follow-up.
Topics can be researched by Claude, Gemini, and Codex in parallel, with synthesis capturing agreement and disagreement.
The workflow uses deposit counts, source variety, and review steps before a topic is treated as synthesis-ready.
Each synthesis surfaces new follow-up questions that can spawn the next topic. The system gets more useful as the loop continues.
Current research tooling includes literature-scanning work tied to active topics so external sources stay connected to the control-plane agenda.
These are the research threads feeding the control-plane work, product experiments, and consulting decisions in public.
Ongoing work to keep the lab's ontology, notes, task history, and evidence layer coherent as new work lands.
Treats knowledge curation as a live control-plane concern rather than static documentation.
A living thesis on delegation, authority, identity, retrieval, trust, and control surfaces across the digital stack, with Mesh-backed belief updates around the long-form corpus.
Treats digital infrastructure as an ontology and governance problem rather than just an app or protocol inventory.
Exploring the vocabulary, flows, and failure modes around payment systems so the lab can reason about money movement with less ambiguity.
Focuses on semantics and operational edges, not just integration plumbing.
Testing a neighborhood-scale coordination system for shared demand, local grocer relationships, batch ordering, and co-op style logistics.
Treats community commerce as a systems problem with explicit workflows, adapters, and governance edges.
Experiments in monitor focus, room/world models, overlay surfaces, and desktop attention routing across sando-tracker, learning-overlay, and personal-usability.
Treats attention and overlays as connected system surfaces rather than as a standalone headset product.
Research into how a complex strategy game should expose state, legality, consequence, replay, and inspection without fragmenting truth across engine and UI layers.
Uses a live game project to study pedagogy, projection, and explanatory interfaces instead of treating them as afterthoughts.
QEDViz work around proof routes, activity views, study panels, and verification workflows.
Connects formal proof and study surfaces back to compute, verification, and knowledge workflows.
Sandolab is the applied research lab of Taylor Sando. Public work here points to the proof layer behind the consulting: control-plane tooling, research notes, and selected software experiments.
Relevant background includes University of Manitoba research in psychology and computer science, software work at SkipTheDishes, Datomar Labs, and ReLease/Cios, and current private control-plane development.
Based in Winnipeg, MB.