Skip to content

BPPE Career

School Administrator

All sections
Ask Otto AI
Help

What is this page?

AI usage ledger

Role aware

This page proves usage ledger rollups, school budgets, feature caps, per-user daily limits, and pre-call budget decisions before live AI metering is enabled.

Audience
Administrator
Current limits
It uses local invented AI usage and budget proof data only. It does not write production usage ledger rows, budget rows, AI runs, billing records, audit events, or student records; call providers; or activate AI features.

Related Otto Guide links

Review AI usagetaskAI usage ledger referencereferenceAI budget limit referencereferenceSettings, users, and rolesconceptOpen reference page placeholder

Support request boundary

Use Sev2 if an AI request could bypass budget checks, exceed a school or feature cap, skip per-user rate limits, write billing data incorrectly, or call a provider after a budget block; Sev3 if ledger, spend, or warning labels are unclear; and Sev4 for proof-copy feedback. This panel does not submit a support case.

Sev1: Critical outage or data-risk emergency

Target: 1-hour response, 24/7 paging during pilot

Sev2: Major workflow blocked

Target: 4 business hours

Sev3: Standard product question or non-urgent issue

Target: 1 business day

Sev4: How-to, cosmetic, or future enhancement

Target: 2 business days

These preview controls are placeholders. Real AI answers, search, walkthroughs, and support submission come in later tickets.

Notifications5

Static proof preview

Real notification feeds, delivery, and preferences arrive in a later ticket.

Sam Director

Sam Director

sam.director@otto-fixture.test

Switch local proof role

StudentInstructorSchool Administrator

This changes only the local shell proof. Production role changes remain server-validated future work.

Search is a keyboard-focusable skeleton. No real index or permissioned search results are implemented in this ticket.

Settings · AI usage

AI usage ledger

Review usage ledger rollups, school budgets, feature caps, per-user daily limits, and pre-call budget decisions.

Otto Fixture BPPE Career School · AI usage

School Administrator · Sam Director

AI usage ledger · Ticket 111

AI spend is checked before provider calls

This proof shows usage ledger rollups, school and feature budgets, per-user daily limits, and deterministic pre-call budget decisions for allowed, warning, and blocked AI requests.

AI settingsGuardrailsRead toolsEvalsPrivacy

Budget

$300.00

Monthly school cap

Spend

$214.70

Current ledger spend

Remaining

$85.30

Before hard stop

Ledger

26

Monthly rows

Allowed

1

Allowed proof cases

Blocked

4

Blocked proof cases

AI

Budget checks run before a provider call

Budget checks run before a provider call and use ledger totals from tenant-scoped usage rows. The proof keeps all spend local and deterministic.

Ticket 111

Budget checks run before a provider call, so blocked requests do not spend more tokens.

Tenant, user, feature, model policy, prompt version, tokens, cost, latency, and outcome are required for ledger joins.

Per-school monthly budget, feature budgets, per-user daily run limits, per-user token limits, and feature kill switches all participate in enforcement.

Warnings can allow a request while still surfacing spend risk before a hard budget block.

Budget limits

Monthly cap

$300.00

Warning threshold

$240.00

Daily runs per user

20

Daily tokens per user

120,000

Feature budgets

ask otto staff questions

$60.00

message drafts

$45.00

study with otto

$140.00

ai grading drafts

$55.00

Usage ledger

ask otto staff questions

run-staff-qa · ask-otto-staff-v1

succeeded

User

user-registrar

Provider

mock · otto-core-deterministic

Tokens

8,500

Cost

$18.40

message drafts

run-message-draft · message-draft-v1

succeeded

User

user-advisor

Provider

mock · otto-core-deterministic

Tokens

10,600

Cost

$24.20

study with otto

run-student-tutor · study-with-otto-v1

succeeded

User

user-jordan-student

Provider

anthropic-shape · provider-key-required

Tokens

49,500

Cost

$86.50

ai grading drafts

run-grading-draft · grade-suggestion-v1

succeeded

User

user-instructor

Provider

mock · otto-core-deterministic

Tokens

22,200

Cost

$38.00

study with otto

run-student-tutor-today · study-with-otto-v1

succeeded

User

user-jordan-student

Provider

anthropic-shape · provider-key-required

Tokens

16,000

Cost

$27.60

compliance copilot

run-blocked-compliance · compliance-copilot-v1

blocked

User

user-compliance

Provider

mock · otto-core-deterministic

Tokens

500

Cost

$0.00

Feature rollups

ai grading drafts

1 runs · 22,200 tokens

Tracked

Spend

$38.00

Blocked

0

ask otto staff questions

1 runs · 8,500 tokens

Tracked

Spend

$18.40

Blocked

0

compliance copilot

1 runs · 500 tokens

Has blocks

Spend

$0.00

Blocked

1

message drafts

1 runs · 10,600 tokens

Tracked

Spend

$24.20

Blocked

0

study with otto

22 runs · 119,500 tokens

Tracked

Spend

$134.10

Blocked

0

Per-user daily limits

user-compliance

Runs today

1

Tokens today

500

Spend today

$0.00

user-heavy-tutor

Runs today

20

Tokens today

54,000

Spend today

$20.00

user-jordan-student

Runs today

1

Tokens today

16,000

Spend today

$27.60

Budget decisions

Advisor drafts one absence check-in

Advisor · Ana Ruiz · message_drafts

allowed

The request stays under school, feature, and per-user daily limits.

Projected school

$215.70

Projected feature

$25.20

User runs

1

User tokens

1,400

Director runs a larger staff Q&A report

Director · Sam · ask_otto_staff_questions

warning

The request is still allowed, but it crosses the monthly warning threshold.

Projected school

$244.70

Projected feature

$48.40

User runs

1

User tokens

13,600

school monthly AI budget warning threshold would be reached.

feature budget warning threshold would be reached: ask_otto_staff_questions.

Analyst asks for a broad report spec

Analyst · Finance · report_specs

blocked

The projected school spend would exceed the monthly AI budget.

Projected school

$304.70

Projected feature

$90.00

User runs

1

User tokens

38,000

school monthly AI budget would be exceeded.

Heavy tutor user starts another session

Student · Heavy usage · study_with_otto

blocked

This user already reached the daily run cap for AI tutoring.

Projected school

$215.20

Projected feature

$134.60

User runs

21

User tokens

55,800

per-user daily AI run limit would be exceeded.

Student tutor request exceeds feature budget

Student · Jordan Lee · study_with_otto

blocked

The tutoring feature budget would be exceeded even though the school budget has room.

Projected school

$222.70

Projected feature

$142.10

User runs

2

User tokens

21,600

feature monthly AI budget would be exceeded: study_with_otto.

Compliance co-pilot is still switched off

Compliance · Marcus Webb · compliance_copilot

blocked

The feature kill switch blocks the request before any provider call.

Projected school

$214.80

Projected feature

$0.10

User runs

2

User tokens

1,600

feature kill switch is active: compliance_copilot.

Proof boundaries

This page uses local proof rows and does not write production usage ledger, budget, AI run, billing, audit, or student-record events.

No Anthropic, OpenAI, Bedrock, embedding, batch, file-retaining, or Private AI provider call is made.

Budget decisions shown here are deterministic proof evaluations, not production metering or customer billing.

No AI feature, tutoring session, grading draft, message send, refund, status change, dismissal, or admissions decision is activated.

Sources

AI-R-014

AI run ledger

Every AI run stores model, prompt version, input references, cost, user, and approval outcome.

PRD-09.3

Usage ledger

Every call records tenant, user, feature, model, tokens, cost, latency, prompt version, and outcome.

PHASE-13

Ticket 111

Adds usage ledger review and budget-limit proof before evals and PII minimization.