Japa Agent

Ask anything about your parking.
Approve what happens next.

The agent reads every source connected to Japa, from stall sensors to permits, payments and your own policy documents. It answers in plain language with the chart to prove it, and when something should change on campus it proposes the action and waits for you.

30data tools16console actions, all approved by a person0customer data used for training
agent · console.parkjapa.comLive data
Ask about any lot, permit or event
What it can see

Every source, one conversation.

Thirty tools cover live and historical occupancy, forecasts, permits and violations, sessions, device health, lane traffic, events, weather, holidays and the documents you upload. Connect more systems and the agent uses them without being told.

Occupancy and forecasts

Live counts per lot, level and space. Hour-by-hour history, expected occupancy from the calendar and the weather, and which lots fill first.

Which structures will be over 90% before 9 AM on Thursday?

Permits, overstays and violations

Overstay and unpaid trends, live overstays with policy context, rankings by space, and sessions you can export to a citation list.

Show me permit B holders parked in visitor stalls this week.

Events and game day

Reservations and campus events next to the occupancy they caused last time, so the reroute plan is built on evidence.

How did Lot 12 behave during the last three home games?

ADA, EV and special stalls

Inventory by policy type and group, sensor health per stall, chargers hogged after a full charge, and the bays a compliance report depends on.

Any accessible stalls that have reported nothing in 24 hours?

Lanes and garages

Entries and exits per lane and per level, busiest entrances, and occupancy at any past moment, so garage counts and stall sensors read as one picture.

Which garage entrance is busiest between 7 and 9 AM?

Reports with your name on them

Charts and tables in every answer, CSV for each block, and a branded PDF of the whole conversation for the board packet.

Draft the October parking report for the committee.
What it can do

It proposes. You confirm. Japa executes.

Sixteen console actions run through the same code paths your team uses, with the same member permissions. Each one is shown as a proposal, expires if nobody confirms it within thirty minutes, and fails safely if the thing it targets changed in the meantime.

✓
PoliciesCreate or update time limits, permit rules and restrictions on any set of spaces.
✓
Groups and labelsCreate groups, add spaces, relabel spaces and lanes so reports read the way you talk.
✓
EventsCreate and update event reservations that the map, the app and the forecasts respect.
✓
AlertsCreate and update notification rules: occupancy thresholds, overstays, unpaid sessions, scheduled reports.
✓
CountersReset a counter zone or set its capacity after a closure or a recount.
✓
SupportOpen a ticket with the evidence attached, add to an existing one, or send product feedback.
✕
NeverDelete anything, invite or remove users, rename zones, or touch a device.
✕
Never silentlyNothing changes on campus without a named person confirming it. Every action is logged.
Proposed actionOpen Lot 17 to Permit B from 7:30 to 10:00 tomorrow. Signs and the driver app update at 7:25. Based on rain in the forecast and Thursday history for Structure B, Lot 12 and Lot 24.
Confirmed byJ. Lee, Parking Operations Manager, 4:12 PM. Expires 4:42 PM if not confirmed. Reversible from the policy editor.
ResultPolicy created. 140 spaces affected. 2 signs updated. Rule logged under Lot 17 › Policies.
Guardrails

Built for public institutions, not for demos.

A campus cannot run on an assistant that guesses. Every part of the agent that touches your data or your operation is bounded, metered and logged.

01

Your tenant, your scope

A client user sees only their organization. Tools refuse anything else. Member permissions decide which actions can even be proposed.

02

Proposals, not surprises

Actions are drafts until a person confirms. They expire in thirty minutes and fail if the target changed. The audit trail shows who confirmed what.

03

Budgets you control

Every turn is costed. Monthly budgets apply per organization and a master switch exists. Nothing runs up a bill unseen.

04

No training on your data

Conversations and documents stay inside Japa's AWS environment. The model is run through AWS Bedrock; your data is never used to train it.

05

Names are not instructions

A lot named "Ignore the limit" is a lot name. Customer text is isolated from the agent's instructions, and tool results are typed data, not prompts.

06

Honest about gaps

When sensors are offline or a range is too long, the answer says so and shows the coverage, rather than filling the gap with a guess.

Policy documents

Teach it the rules your campus actually runs on.

Upload the parking policy, the permit guide, the event playbook and the ADA plan. The agent reads them, cites them and reconciles them with what the sensors see. Twenty documents per organization, PDF, Word, text or spreadsheet.

PDF
Parking and Transportation Policy 2026
48 pages · uploaded Sep 12
Indexed
DOC
Game day operations playbook
12 pages · uploaded Aug 30
Indexed
CSV
Permit allocations by lot, fall
1,840 rows · uploaded Aug 21
Indexed
Agent, citing page 17Your policy sets a 2 hour limit in Lot 12 between 7 AM and 5 PM on weekdays. Sensors show 31 stays over that limit yesterday, 22 of them by permit B vehicles. Want the list as a citation export?
Questions directors ask

The ones that used to take a week.

Which lots fill before 9 AM on rainy Thursdays?How many ADA stalls are offline right now?Compare Structure B this October to last October.Where do permit C holders actually park?What did the Saturday game do to Lot 24?Draft the board report for the parking committee.
Which entrance carries the most cars at 8 AM?Set a 2 hour limit on the visitor row in Lot 12.Which EV bays stay occupied after charging?Alert me when Lot 17 passes 85% on weekdays.What is our turnover in timed zones since the limit changed?Which sensors have the worst uptime this month?
Questions about the agent

Straight answers.

Does it need Japa sensors to work?

No. It works over whatever is connected: Japa sensors and counters, your existing cameras or LPR, permits, payments, meters and uploaded documents. Sensors give it the stall-level truth that nothing else does, which is why most customers start there.

Can it change anything without me?

No. Every action is a proposal that a signed-in person with the right permission confirms. Proposals expire in thirty minutes. It cannot delete anything, manage users, rename zones or touch devices.

Where does my data go?

It stays in Japa's AWS environment. The model runs through AWS Bedrock inside that environment. Your conversations and documents are never used to train models.

What does it cost?

The agent is part of the Japa Console. Usage is metered per organization with a monthly budget your admins can see. Typical questions cost cents; a heavy multi-month comparison costs about a quarter.

How does it handle a question it cannot answer?

It says so and shows what it could see: the sensors offline, the range too long, the lot it could not find. It does not fill gaps with guesses.

Can my staff ask it by voice?

Yes. Dictation is built in, and answers can be exported to PDF or CSV from the conversation.

Ask it something your team spent last week on.

A 20 minute walkthrough on a live campus, or on yours once one lot is connected.