Program overview

TritonAI

A shared AI ecosystem for service, instruction, development, and everyday campus work.

TritonAI brings together TritonGPT, live campus data tools, a growing model hub, developer APIs, embedded assistants, reusable workflows, and the early scaffolding for supervised agents so campus teams can build on governed infrastructure instead of starting from scratch.

UPDATED

June 2026

CONTEXT

University of California, San Diego

Executive summary

A platform program, not a single chatbot.

TritonAI is UC San Diego's approach to making AI useful across the university. It now spans secure infrastructure, task-specific assistants, live campus-aware tools, instructional pilots, developer access, and shared workflows in one governed campus ecosystem.

TritonGPT remains the platform layer at the center of that work: a secure, SDSC-hosted environment available to more than 73,000 students, staff, and faculty. The current arc is broader than chat: model choice, on-prem and approved cloud routes, API access for builders, embedded website support, and the building blocks for agentic workflows.

TritonAI program architectureKnowledge and memory, a developer surface, model access, and workflow agents all connect to one shared, governed TritonAI core.01Knowledge & MemoryDocs, data, retrieval02Developer SurfaceBuild & extendModel AccessHosted models, APIsWorkflow & AgentsAutomated workTritonAI core

01

Knowledge

Curated campus context, uploaded documents, and live data tools

02

Model Access

Self-hosted and approved cloud models through governed routes

03

Developer Surface

APIs, credits, keys, endpoints, and usage reporting

04

Workflow

Assistants, embedded support, tools, and reusable agent scaffolding

Program parts

What TritonAI Includes

TritonAI includes the shared pieces needed to support campus adoption: a governed platform, embedded experiences, instructional tools, live data integrations, developer access, reusable skills, and a path toward supervised agent workflows.

Recorded work

TritonAI in Action

Examples from the TritonAI portfolio, built on TritonGPT and connected to everyday university work.

Job Description Helper

Helps HR and hiring managers draft clear, compliant job descriptions in minutes.

Fund Manager Coach

Guides grant and fund managers on compliance, allowable expenses, and spending restrictions.

UC San Diego Assistant

Answers campus policy and service questions using curated departmental knowledge and institutional resources.

Contract Reviewer

Auto-redlines third-party NDAs/contracts against UC San Diego and UC Terms & Conditions and Legal Position.

Measured signals

Early Signals from TritonAI

A few measures that show how the work is affecting administrative workflows, public support, and learning.

01

0%
Faster Contract Review
120 minutes to 11 minutes on average

02

0%
Faster Job Description Drafting
30 minutes to 5 minutes on average

03

0
Model Hub Breadth
Self-hosted and approved cloud models available through TritonAI

04

$0K
Projected Annual Savings
From replacing third-party public support tooling

Operating principles

How TritonAI Is Taking Shape

TritonAI is being built around a few practical principles: governed infrastructure for sensitive work, shared access instead of isolated pilots, tools designed around specific campus pain points, model choice without fragmented governance, and an architecture that can evolve from assistants toward supervised agency.

Trust Is Infrastructure

Sensitive work in HR, finance, legal, student support, and institutional operations needs governed infrastructure. TritonAI separates local/self-hosted capacity from approved cloud routes so projects can match model choice to data sensitivity, cost, and task complexity.

Make AI a Shared Utility

Shared infrastructure and zero-variable-cost access make experimentation easier for more people. The goal is not a small number of premium tools, but broad and equitable access to useful ones.

Solve Specific Pain Points

The strongest use cases have been concrete ones: contract review, public support, search, scheduling, performance review alignment, transcript workflows, and instructional support. Focused tools create trust faster than generic chat.

Meet People in the Workflow

TritonAI is showing up in Blink, public websites, teaching tools, mobile experiences, developer projects, and departmental applications. Adoption improves when AI appears where work is already happening.

Stay Model-Agnostic

The architecture is built around gateways, canonical model routes, connectors, usage reporting, and governance rather than a single provider. That keeps campus teams flexible as models, prices, and commercial terms change.

Prepare for Agency

The next step is moving from answering questions to completing supervised multi-step work. APIs, reusable skills, connectors, model observability, and access monitoring are the pieces that make that shift practical.

Assistant index

Examples Across the TritonAI Portfolio

These are not generic chatbots. They are focused tools built around specific service, instructional, research, and administrative workflows where grounded context and institutional trust matter.

01

UC San Diego Assistant

Cross-functional knowledge bridge drawing from 70+ curated department websites, hundreds of ServiceNow knowledge base articles, and UC San Diego policies.

02

General AI Assistant

Writing and editing support without UC San Diego-specific context or reference links.

03

Job Description Helper

Assists HR and managers in drafting comprehensive, compliant job descriptions with significant efficiency gains.

83% reduction in drafting time

30 min → 5 min average

04

Contract Reviewer

Accelerates NDA and Terms & Conditions review **for the UC San Diego Procurement team**, aligning vendor contracts with UC Legal Position and university template terms. Highlights potential issues for specialist focus.

91% time savings for NDAs/T&Cs

120 min → 11 min average

05

Fund Manager Coach

Expert guidance on grant compliance, spending restrictions, and financial management for research funds.

06

Phishing Analyzer

Scores suspicious emails for phishing risk and explains warning signs to protect campus data.

07

Deep Research Assistant

Synthesis and analysis across hundreds of research documents and institutional data points.

08

Triton Developer Assistant

On-demand coding support and documentation analysis for staff and administrators.

09

Socratic Tutor

Guided learning assistant that helps students master materials without providing direct answers.

10

Instructor AI Assistant

Automated generation of quizzes, summaries, and study guides directly from lecture content.

11

Internet Search Assistant

Conversational AI with internet access for real-time information and answers.

12

Expert Notetaker

Converts transcripts or notes into structured documentation focused on decisions and actionability.

13

Project Charter Assistant

Helps draft professional and comprehensive project charters.

14

AI Workplace Opportunity Assistant (v0.1)

Interviews users about daily tasks to suggest tailored AI use cases and prompts.

15

Performance Review Evaluator

Helps supervisors and HR teams assess whether performance ratings are supported by written comments, with stricter review of rating/comment alignment.

16

Data Dictionary Assistant

Provides definitions from specific UC San Diego data sources like the Activity Hub and Blink.

17

Supplier Search Tool

Assists in finding campus suppliers and explains the UCSD purchasing process.

18

UCSD Benefit Assistant

Answers questions regarding employee benefit packages.

19

UC San Diego Class Scheduling Assistant

Helps students build optimized schedules based on subject codes and availability.

Roadmap

Where TritonAI Is Going Next

The next phase expands beyond chat into a broader tools hub: richer model access for developers, more embedded campus experiences, workflow orchestration, observability, live data integrations, and new support for academic and administrative use cases.

01

Transcript Verification

OCR and transcript matching workflows for enrollment-related review.

02

Instructional AI Expansion

More course pilots, faculty tooling, and simpler assistant creation for instructors.

03

Developer API Expansion

Self-hosted model credits, approved cloud routes, usage reporting, and clearer paths from prototype to funded campus application.

04

Mobile Integration

Bringing TritonGPT-powered support into the UC San Diego mobile experience.

05

Model and Service Observability

Catalog monitoring, access checks, usage signals, and AI-assisted detection for service anomalies and operational risk.

06

Academic Advising Agent

Proof-of-concept support for tier-one academic advising questions and triage.

07

Agent Builder and Workflow Tools

Low-code orchestration, reusable skills, MCP-style connectors, and guardrails for supervised multi-step campus workflows.

Program lesson

What We're Learning Through TritonAI

The clearest lesson so far is that institutional AI works best when it is treated as shared infrastructure rather than a collection of disconnected demos. Secure hosting matters, but so do model choice, good knowledge sources, live tools, reusable connectors, governance, and close partnership with the people doing the work.

TritonAI is one way of learning how shared institutional AI can become practical, trusted, and reusable.

Want to Compare Notes?

If you're building something similar in higher education, I'd be glad to compare notes and hear what your institution is learning.

Start a Conversation