Taylor Sando

I make AI-agent systems reliable enough to ship. I run a supervised multi-agent development fleet — Claude, Codex, and Gemini behind a scheduler, a merge-queue, and a verify gate. In the last six months it shipped eight deployed applications and merged 10,000+ reviewed commits. I audit whether your agent setup can ship safely, or build the missing review-and-handoff layer with you.

Best fit

Engineering teams adding AI agents, orchestration, or internal automation to real product and workflow surfaces.

What I deliver

Reviews, advisory, and scoped implementation around reliability, auditability, routing, and system boundaries.

Why trust this

Control-plane tooling across Mesh, Orchestrator, OCC, and Console, the active Sitelayer product loop, product engineering at ReLease/Cios, and earlier HCI research at ACM APGV and IEEE PacificVis.

The public version of the work is narrower than the private stack behind it. This site is meant to answer the practical question first: should we talk about your system, and if so, what kind of engagement fits?

Where I Help

AI agent delivery systems

Move from ad hoc prompts and toolchains to governed workflows with clear boundaries, approvals, and operator visibility.

Control-plane reliability

Untangle routing, auditability, review hooks, knowledge surfaces, and failure paths before complexity hardens into production risk.

Ontology and semantic design

Use control-plane, digital, and payment ontology work when delegation, evidence, or system vocabulary needs to stay coherent across teams and tools.

The research and product threads lower on the page are proof of range. The top of the funnel is simpler: if you are shipping AI-assisted systems and want a clearer control plane, this is the part to pay attention to.

Common Work

AI Agent Readiness Review

For teams adopting coding agents or workflow automation but lacking clear boundaries. I map the failure surfaces, approval paths, and missing control-plane pieces before complexity hardens.

Best fit: shipping teams with AI in internal or customer-facing workflows.

Deliverable: written review, risk map, and prioritized next steps.

Control-Plane Audit

For teams that already have agents, queues, or orchestration in play and need clearer routing, auditability, and reliability. I focus on the seams where supervision, policy, and operator control start to fail.

Best fit: teams with live agent workflows, internal automations, or growing review overhead.

Deliverable: architecture readout, gap analysis, and implementation sequence. Scoped to the system.

Embedded Advisory

For founders and engineering leads who want ongoing help shaping architecture, agent policy, and execution decisions while the system is still moving.

Best fit: teams making repeated control-plane and AI adoption decisions under delivery pressure.

Deliverable: recurring decision support, reviews, and implementation guidance while the system is moving.

If you already know the problem and need implementation help, start with the Working With Me page. I usually prefer an architecture read before writing the implementation plan.

Writing

Experience

Control Plane 2025 – present
Private control-plane tooling spanning Mesh, Orchestrator, OCC, and Console. Current repos cover file activity tracking, agent orchestration via git worktrees, policy/config generation from org files, and web tooling for monitoring and operator workflows.
Cios / ReLease 2023 – 2026
Software engineering on a rent deposit insurance platform. Worked across the React/Redux frontend monorepo and supporting backend systems, with a focus on business billing, invoice reconciliation, auditability, and payment workflows across MongoDB, Firestore, GCP, and Stripe.
Datomar Labs 2019 – 2022
Software engineering across Datomar products and client work, including Brownie Points, Convai, DeutzFahr, Braise, Shopify integrations, and other MVP builds.
Freelance & Contract 2012 – 2019
Independent consulting across web apps, prototypes, and internal tooling for multiple clients. Work from this period includes Playbook Edge for InVision Edge, Pray4EveryHome, ScheduleAid / Reclaim.IO (2012–2013), scheduling and cancelled-booking recovery software for service businesses, NuOrder (2014), restaurant ordering and menu software, and other custom product builds.
SkipTheDishes 2014
Software development work at SkipTheDishes during 2014.
University of Manitoba B.Sc. Computer Science — 2007 – 2013
Worked in the HCI Lab under Pourang Irani on spatial cognition and 3D visualization research. Publications at ACM APGV and IEEE PacificVis.
University of Manitoba B.Sc. Psychology — 2002 – 2007
B.Sc. Honours Psychology, First Class, with a History minor. Research and teaching work across animal behavior and behavioral biology labs, including lake sturgeon physiological stress-response work with Gary Anderson and the Hotchkiss Brain Institute National Neuroscience Competition finalist designation before pivoting into computer science.

Publications

  • Effects of animation, user-controlled interactions, and multiple static views in understanding 3D structures (2009) — ACM APGV — with Melanie Tory and Pourang Irani
  • Impact of group size on spatial structure understanding tasks (2011) — IEEE PacificVis — with Melanie Tory and Pourang Irani

Earlier Research

  • Does the stress-axis in lake sturgeon undergo habituation? — undergraduate honours research with Gary Anderson, listed in 2009 CV material as a Prairie Universities Biological Symposium (PUBS 2008) presentation

Sandolab — Applied Research Lab

Attention Systems

Tracking & Overlay Systems

Work across sando-tracker, learning-overlay, Learn, and personal-usability: monitor-focus experiments, overlay surfaces, learning workflows, and desktop attention systems.

Agent Infrastructure

Control Plane

Current control-plane repos spanning Mesh, Orchestrator, OCC, and Console: file activity tracking, agent routing, policy tooling, and operator surfaces.

Sitelayer dashboard
Product Systems

Sitelayer

Construction operations platform for blueprint takeoff, estimates, crew scheduling, rentals, inventory, QBO sync, and feedback capture tied back to reviewable work.

Ontology Research

Digital Ontology

A living research corpus on delegation, authority, retrieval, trust, and control surfaces across the digital stack, with the thesis kept in sync with Mesh-backed belief maintenance.

Game Systems

WinWar

Strategy-game research around engine semantics, browser projection, replay, inspection, and guided onboarding for complex state.

Sports Analytics

Hockeypedia

NHL data project focused on trade lineage, player/game ingestion, and analytics surfaces.

Learning Workbench

Learn

Standalone Mesh-backed personal learning workbench: Today queue, library and PDF reader, spaced recall, glossary, ontology atlas, proof workflows, sessions, and diagnostics.

The full, git-mined account of the last six months is on the Six-Month Build Log. More current work and experiments at sandolab.xyz.

Research Threads

Control-plane ontology Vocabulary, belief layers, and auditability for agent systems
Digital ontology Delegation, authority, retrieval, trust, and stack-control surfaces across the broader digital environment
Payment ontology Mapping payment entities, flows, and state transitions before implementation details hide them
Sitelayer capture loop Product trace, capture sessions, support packets, and context-work handoffs in a real construction-ops product
Tracking & overlay systems Attention tracking, overlay surfaces, and desktop experiments across sando-tracker, learning-overlay, and personal-usability
WinWar interface research Legality, consequence, replay, inspection, and tutorialization for a complex strategy-game surface
Learn workbench Reading, recall, glossary, ontology, proof, session, and diagnostics surfaces connected to Mesh learning APIs
Belief drift Keeping notes, tasks, and code aligned as systems change

Background

University of Manitoba background in psychology and computer science, with research work in animal behavior and HCI. Published at ACM APGV and IEEE PacificVis before moving into consulting and product engineering.

Current work is split across consulting, control-plane tooling, Sitelayer, digital-ontology and payment-ontology notes, capture/product-trace research, and public experiments including sandolab.xyz, winwar.sandolab.xyz, and hockeypedia.org.

Read the full story →

© 2026 Taylor Sando · Winnipeg, MB