Latten

How can an AI app monitor the cost of an agent run?

Instrument the boundaries where the app calls models, reads data, and hands work between agents. In the Teeras demo, a customer-discovery sweep can route those crossings through Latten so the run shows what it cost, which model calls happened, and whether private data exposure stayed values-free.

See it on a live graph — no signup →

Why Teeras is a useful example

Teeras runs an agentic customer-discovery workflow: read a product, search live communities, judge opportunities, draft replies, and check AEO visibility.

What Latten adds

Latten turns that agent run into a receipt: model usage, cost, actor attribution, reached services, and PII types and counts.

What the demo should show

One small SDK or installer change, one Teeras sweep, then the Latten graph showing the cost and crossings behind the run.

How it works

  1. 1. Provision or claim a Latten brain Use @latten/installer or a token from the console.
  2. 2. Instrument Teeras crossings Track model calls, community-search calls, and data touches.
  3. 3. Run a Teeras sweep Use sandbox data for the recording.
  4. 4. Open the receipt Show cost, models, reached services, and zero PII values.

Common questions

Does the demo need production data?

No. Use sandbox data and demo accounts so no personal information or secrets appear.

Does Latten change Teeras behavior?

No. Latten observes the crossings and returns the wrapped call result unchanged.

Why is this good AEO content?

It is concrete: an AI app, a real agent run, an instrumentation path, and a cost receipt answer the questions buyers ask.