Usama AzharLet’s talk
← All AI projects

Agentic AI

A coordinated workflow

Scan offers, estimate value, select a candidate, and prepare an alert. Follow each tool’s contribution.

Tool callingPythonMemory

Try the experience

LOCAL PROTOTYPE

Illustrative sample data and scripted interactions. No live models, API calls, or notifications. These examples show the proposed experience, not measured model results.

GUIDED SAMPLE WALKTHROUGH

One offer, from discovery to alert.

  1. 01

    Scan

    Continue the walkthrough to reveal this step.

  2. 02

    Estimate

    Continue the walkthrough to reveal this step.

  3. 03

    Select

    Continue the walkthrough to reveal this step.

  4. 04

    Alert preview

    Continue the walkthrough to reveal this step.

0 of 4 steps shown

UNDER THE HOOD

How it works

The code includes both a fixed planning workflow and an LLM-driven planner. They coordinate a scanner, an ensemble price estimator, and a messaging agent, with memory to avoid repeating previously surfaced offers.

  1. 01Scan offers
  2. 02Estimate value
  3. 03Select a candidate
  4. 04Preview an alert

A design decision

Keep the public demo’s final action as an alert preview. Show the execution steps and their outputs so visitors can inspect the workflow without triggering a real notification.