Skip to main content
ar is a Hebrew-speaking, female agent for Partner TV, designed to assist customers with troubleshooting, pairing, and operating TV remote controls. The agent specializes in identifying remote control hardware through physical descriptions and guiding users through precise, model-specific technical flows.

View Agent

Open in Wonderful Platform

Overview

FieldValue
MarketIsrael - Telecommunications
VerticalTelecommunications
CompanyPartner (פרטנר)
Modelgpt-realtime-2025-08-28
LanguageHebrew
ChannelsVoice

Skills

  • Remote Control Identification — Identifies the exact remote model (S70, Jade, TopBox) using physical descriptions or visual confirmation via SMS\
  • Hardware-Specific Troubleshooting — Executes tailored pairing, reset, and recovery procedures per remote model\
  • Operational Guidance — Provides step-by-step instructions for Android TV navigation and app usage (Netflix, YouTube, Home screen)

Key Tools

ToolPurpose
get_jade_codes() / get_s70_codes()Retrieve TV manufacturer codes for RC-to-TV pairing
OnStart()Initializes the session (OAuth tokens, GMS call metadata)
pCRM()Submits call summaries and quality metrics to Partner CRM

Prompting Techniques

Hierarchical modular prompting — All remote control models share a mirrored prompt architecture to ensure consistency while allowing precise technical variation:
  • Each remote model has an identical prompt skeleton
  • Only model-specific steps differ
High-level execution constraints — Every skill enforces pacing and confirmation discipline: Execution: Step-by-step only Pacing: Wait for user confirmation after every step Terminology: Use predefined Hebrew technical terms only Atomic skill composition — Complex procedures are built from reusable technical blocks: Examples:
  • Pair RC to DTA
  • Unpair RC from DTA
  • Reset RC
  • Control TV Volume
Troubleshooting-first orchestration — Diagnosis always precedes action:
  • The agent must identify the symptom
  • Only then may it call the relevant Atomic Skill

The Troubleshooting - Skill Synergy

The core strength of Bar lies in the strict separation between diagnosis and execution:
  • Logical Mapping - Troubleshooting flows act as deterministic decision trees.
  • Precision - The agent never improvises technical steps; it executes predefined skills only.
  • Modularity - Pairing logic can be updated independently of diagnostic logic.

Example: S70 Logic Relationship

SYMPTOM: Volume and Power work, but Channels do not FLOW: Troubleshooting PATH B ACTION SEQUENCE:
  1. Unpair RC from DTA
  2. Pair RC to DTA

Lessons Learned

What worked
  • Single-feature identification (turquoise button) dramatically improved model detection accuracy\
  • Strict step confirmation reduced user errors during pairing flows\
  • Modular skills prevented hallucination of technical procedures
Challenges
  • Hardware identification over voice/chat is inherently limited\
  • SMS-based image galleries were required to compensate for lack of visuals\
  • Maintaining consistent Hebrew technical terminology required a strict internal dictionary

Deep Dive

1. Remote Control Identification - Physical Feature Classifier

Purpose: Identify the correct hardware model without serial numbers or device metadata. What it does
  • Asks the user about unique physical characteristics (button color, layout, labels)\
  • Optionally sends an SMS link to a visual gallery\
  • Confirms the remote model before allowing any troubleshooting
Key constraint
  • No troubleshooting is allowed before model confirmation

2. Troubleshooting Flows - Symptom-Based Decision Engine

Purpose: Diagnose the user’s issue and select the correct execution path. What it does
  • Classifies the issue (pairing, volume, channels, power, navigation)\
  • Maps the symptom to a predefined path (A—H)\
  • Determines the exact Atomic Skill sequence required
Key advantage
  • Eliminates random trial-and-error steps\
  • Ensures repeatable, support-grade diagnostics

3. Atomic Skills - Deterministic Technical Execution

Purpose: Execute hardware procedures safely and consistently. What they do
  • Provide exact button sequences\
  • Enforce wait-and-confirm pacing\
  • Use approved Hebrew terminology only\
  • Prevent skipping or reordering steps
Example logic for step in pairing_steps: instruct(step) wait_for_confirmation()

How They Work Together

User: “השלט עובד על ווליום אבל לא מחליף ערוצים”
  1. Remote Identification → S70 confirmed
  2. Troubleshooting Flow → PATH B
  3. Atomic Skill: Unpair RC from DTA
  4. Atomic Skill: Pair RC to DTA
  5. Confirmation → Issue resolved
  6. CRM() → Call summary submitted