Home›People / Agents

Section 3 · 13 agents · 4 uplifted · 4 pending uplift · 1 pending creation · 3 not in current cascade · 2 pending Researcher structural eval

People & agents.

Each agent has a resume-style bio — research portfolio, significant project contributions, learnings authored, skills used. Click any card to drill in.

PO · strategy + requirements authority

PO · Product Owner

Jon's strategic partner and requirements authority. Conducts stakeholder interviews, grooms backlog, audits docs, triages issues, and gates all agent output against product requirements and the North Star.

Pending uplift

Worktree: aiuni-uplift-po

→ open profile

UX · evaluate against 20 heuristics + emotional arc

UX

UX review agent. Evaluates student-facing screens against 20 heuristics (Nielsen's 10 adapted + 8 education/AI-specific). Catches usability issues that PO and QA miss — wrong labels, inappropriate placeholders, mobile breakage, emotional regression, accessibility violations, cognitive load problems.

Uplifted · M-2 L-3 · M-3 done

Corpus: 053c171f · 10 primary-lit · 4 clusters

→ open profile

Designer · originate visual direction

Designer

Senior product designer agent. Owns the design PROCESS (requirements → brief → IA → tokens → review → handoff) for AI Uni marketing redesigns, brand identity work, and high-craft visual surfaces. Originates direction.

Uplifted · M-2 L-2 · M-3 done

Corpus: 6d571734 · 9 primary-lit · 6 clusters

→ open profile

Tester · blind agentic-coder UX testing

Tester

Blind agentic-coder UX testing — green-user persona simulation, 30-second-comprehension testing, 375px mobile-first verification, multi-session flow simulation, formal sign-off-block discipline. Closes a specific UX-validation gap that QA's runtime-evidence-focus does not address.

Uplifted · M-2 L-4 · M-3 file shipped

Corpus: 075fee57 · 11 primary-lit · 5 clusters

→ open profile

Researcher · evidence-based intelligence + landscape monitoring

Researcher

Evidence-based curriculum intelligence — learning science, market data, competitive analysis, tools landscape, and meta-research on agent effectiveness. The team's primary source of external evidence.

Uplifted · M-2 L-1 · M-3 done

Corpus: 9e61df0c · 11 primary-lit · 7 clusters

→ open profile

Validator · curriculum quality auditor (read-only)

Validator

Validates curriculum content for consistency, forbidden terms, products freshness, content drift, and instruction layer conflicts. Use proactively after any content change.

Pending uplift

Worktree: aiuni-uplift-validator

→ open profile

QA · runtime verification + 5 test modes

QA

Autonomous testing agent. Verifies fixes with evidence (logs, DB state, HTTP responses) before anything is marked FIXED. Runs MCP tool tests, web classroom API tests, lesson flow tests, curriculum experience tests, and personalization verification.

Pending uplift

Worktree: aiuni-uplift-qa

→ open profile

Developer · code review + platform builds

Developer

Reviews all code changes from agents and humans. Enforces codebase conventions, security, tutor instruction layer integrity, and deployment rules. Also owns Track B bug fixes and platform code.

Not in current cascade

→ open profile

Code-PM · Tier 2a session-end active-verification

Code-PM

Tier 2a session-end active-verification + doc-maintenance currency-review enforcement + cross-terminal evidence aggregation. Owner of session-end-verification skill (Phase 3b S74 atomic ownership transfer per R-EXTRA-1 TWO-phase). Pattern A direct-instance per AGENT-OPERATING-MODEL.md §4.

Pending uplift

Worktree: aiuni-uplift-codepm

→ open profile

Planner · curriculum architecture + sequencing

Planner

Designs and authors complete session content — syllabi, seed data, exercises, resources. Use for course creation and overhaul.

Not in current cascade

→ open profile

Auditor · curriculum-currency caretaker

Auditor

AIUni's curriculum-currency caretaker. Continuously monitors curriculum + agent corpora + skills for staleness vs latest research. Critical given real-time-update frequency goal.

Pending Researcher structural eval

→ open profile

Administrator · AIUni academic administrator

Administrator

AIUni's academic administrator. Expert in education + teaching + learning + classroom dynamics. Oversees curriculum delivery + classroom optimization from head-of-school perspective.

Pending Researcher structural eval

→ open profile

Tutor-Behavior · 4-layer instruction integrity

Tutor-Behavior

Owns tutor instruction quality across all 4 layers. Audits for conflicts, tests behavior against scenarios, reviews every tutor layer change. Invoke before any commit touching `tutor-base.ts`, `tool-reminders.ts`, `tutor-prompt.ts`, or `mcp-remote-instructions.ts`.

Not in current cascade

→ open profile
Card population legend. Uplifted agents render with real corpus data at canonical commits. Placeholder agents render with the same 8-section template populated from agent-file frontmatter, with badges marking pending uplift, pending creation, not in current cascade, or pending Researcher structural eval. Counts derive from agents/*.json + libraries/gaps.json single source of truth (no hardcoded numbers; closes Stage 5 R2 cross-surface count drift). Gated agents (qa · developer · code-pm · planner) require sign-in with intranet_access.