Pioneer in Offering CRM Solutions since 2010...

Variance Logo
Contact Us

How Mobile AI Agents Help Mobile CRM Users Complete Work by Conversation

How an AI agent was added to the mobile CRM so users can search records and create leads, contacts, tickets, appointments and tasks in one conversation, in English or Hebrew

Mobile CRM users often need to search for a record or create a lead, contact, ticket, appointment or task while they are away from a desktop. Doing that through menus and forms takes time, and switching to a separate AI chat loses the CRM context.

The conversation stays on one session, so a follow-up such as a title or a time continues the same request. The reply language follows the user’s message, English or Hebrew. Dates, times and picklists follow the signed-in user.

Mobile AI agent helping CRM users search records and create tasks by conversation
Executive Summary

The Project at a Glance

Mobile AI Agents brings a configurable AI agent into the mobile CRM. An administrator defines what the agent is allowed to do. The mobile app sends the user’s message to the CRM. The agent searches or creates the record, then answers with what actually happened: found, not found, created or not created.

The Business Challenge

The Challenge of Mobile CRM Data Entry & Search

Field and mobile users need the CRM while they are speaking or typing a short request, not while they are filling a long form.

Typical Mobile User Requests

Typical requests include: Find a contact by organization, email, phone or picklist value, Find a ticket by ticket number, Create a lead or a contact from a conversation, Open a support ticket, Schedule an appointment, Create a task and add the title or time in a later message.

Manual Form Filling Overhead

Doing this manually means opening the right module, searching the right field, and completing every mandatory value. Relative words such as “today” and “tomorrow”, a time such as “12:00 AM”, a Hebrew picklist label, or an organization name are easy for a person to say and easy for a plain text search to miss.

Context Gap & Core Requirement

A separate AI chat does not know the CRM schema, the user’s date format, the user’s timezone, or which records that user is allowed to see.

The business requirement was to let the mobile user ask in a conversation, and to let the CRM perform the search or the create and report the result.

The Solution We Built

An Administrator-Configured AI Agent for Mobile CRM

Mobile AI Agents was built as an administrator-configured agent for the mobile app.

Mobile app → Message → CRM agent → Search or create → Result message → Records
Mobile CRM AI agent configuration, execution and session continuity
1

Administrator Configuration in AI Settings

Administrators open AI Settings and create an agent. They choose the provider and model, write the main instructions, and turn on only the actions the business wants. Each create action can be limited to selected CRM fields.

2

Direct Mobile Execution via runAiAgent

The mobile app calls runAiAgent with the user’s message. The CRM runs the enabled actions and returns one message plus the records that were found or created.

3

Session Continuity (ai_session_id)

A follow-up uses the same ai_session_id, so the CRM keeps that conversation. This is separate from the mobile login session.

Why We Introduced AI

Why We Introduced AI into the Mobile CRM

The objective was not to let the model change the CRM on its own without a result the user can see.

The objective was to turn a short spoken or typed request into a CRM search or a CRM record, and to tell the user what was found or created.

01

Database Schema Search

Search entity modules, except Users and Settings, using the database schema.

02

Multi-Module Record Creation

Create a lead, contact, ticket, appointment or task.

03

Multi-Action Single Turn

Carry out more than one action in the same turn and return one message.

04

Context Continuation

Continue the same request when the user adds a title, a date or a time.

05

Native Bilingual Answers

Answer in English when the user writes in English, and in Hebrew when the user writes in Hebrew.

06

Contextual Clarification

Ask only when a value cannot be decided, such as a person or company name that was never mentioned.

System Capabilities

Mobile AI Agent Capabilities

Capability What it does
Search Records Finds records across CRM modules by any stored field, including ticket number, email, picklist and related organization name.
Create Lead Creates a lead from the conversation.
Create Contact Creates a contact from the conversation.
Create Ticket Creates a support ticket.
Create Appointment Creates an event. “Today” and “tomorrow” become real dates. A missing end is 30 minutes after the start.
Create Task Creates a task. A later title or time stays a task and is not turned into an appointment.
One Conversation ai_session_id keeps history for that conversation.
Result Message The message says found, not found, created or not created after the action finishes.
How It Works

How Mobile AI Agents Works

Mobile AI agent workflow from user message to CRM action and results

An administrator creates the agent, selects OpenAI, Grok or Gemini, and enables the allowed actions and fields.

The app calls runAiAgent with the message. On the next turn it also sends ai_session_id.

The agent reads the message and the saved conversation. It decides which enabled action to run. “Tomorrow” and “today” are converted with the user’s timezone. Hebrew and English picklist labels are both accepted.

Search runs against the CRM schema. Creates run as the signed-in user. Appointment times are stored in the database timezone, so 12:00 AM stays 12:00 AM for that user.

The response includes the message, the state, ai_session_id, the action, the full actions list, and any search results or created records.

AI in Real Mobile CRM Work

Mobile AI Agents in Real-World Scenarios

Example 1 — Find a Contact by Organization

The user says:
Find a contact whose organization name is New.

1

Account Name Matching

The organization field stores the related account, not the name itself. The agent matches the account name and returns the contact.

2

Blank Filter & Bilingual Search

A contact with a blank organization is not returned. The same request in Hebrew, such as a search for the organization name, uses the same field.

3

Result Reporting

The message is the result, for example: “Found 1 in Contacts: …” or “No records found.”

Mobile AI agent finding contacts by organization name

Example 2 — Create an Appointment From a Short Sentence

The user says:
Create an appointment tomorrow at 10:00 AM. End time is 11:00 AM.

1

Date & Timezone Handling

The agent does not ask the user to convert “tomorrow”. It uses the user’s date and timezone.

2

Intelligent Missing Defaults

If the user does not give an end time, the end is 30 minutes after the start. If the user does not give a title, the agent supplies one.

3

Database Timezone Storage

12:00 AM is saved in the database timezone so the calendar still shows 12:00 AM.

Mobile AI agent creating appointments with timezone-aware scheduling

Example 3 — Finish a Task In a Second Message

The user then says:
Title is Call the customer and the time is 10:00 AM.

1

Missing Input Prompt

The user first says “Create a task”. The agent asks for the missing title or time and returns state: awaiting_input.

2

Contextual Follow-Up Input

The user then says: Title is Call the customer and the time is 10:00 AM.

3

Task Preservation & Confirmation

Because the same ai_session_id is sent, this stays a task. It is not changed into an appointment only because a time was given. The message then reports that the task was created, or that it was not created.

Mobile AI agent completing a CRM task through a follow-up message
Conversation States

Mobile AI Agents: Conversation States

01

awaiting_input

Meaning: The agent still needs a value it cannot decide.

What the App Does: Show the question and keep ai_session_id.

02

Completed

Meaning: The search or create finished successfully.

What the App Does: Show the result message and the records.

03

Failed

Meaning: The action could not be completed.

What the App Does: Show that it was not found or not created.

The response always includes: message — the result, not “I am searching” or “I am creating”, ai_session_id — this conversation, not the mobile login session, action — the first action, or empty while waiting, actions — every action from that turn, search_results — matching records, when the action was a search

AI + CRM

AI + CRM: Working Together

AI Handles

→
Understanding the user’s sentence
→
English and Hebrew replies
→
Today, tomorrow and a missing title
→
Choosing a category or other decidable field
→
Keeping one conversation together
Connected Workflow

CRM Provides

→
Modules, fields and records
→
Picklist values and their Hebrew and English labels
→
The user’s date format and timezone
→
The fields the administrator selected
→
Permissions of the signed-in user

In simple terms, the user talks to the mobile app, and the CRM remains the system that searches and creates the records.

Solution Architecture

Mobile AI Agent Solution Architecture

Mobile AI Agent Solution Architecture
AI-Powered Mobile Automation

Mobile AI Agents for Automated CRM Tasks in Your Mobile App

Give every CRM mobile app user a personal AI assistant. Configure its instructions, conversation memory and enabled actions, and let users create, update and search CRM records, book appointments and manage tasks using simple voice or text requests.

Mobile AI Agents

Give every CRM mobile app user a personal AI assistant. Manage the assistant from one screen in CRM Settings, see its model, history and enabled actions at a glance, and switch it on or off in one click, with features such as:

Agents Managed in CRM Settings
One-Click On/Off per Agent
Available to All Mobile App Users
One Active Agent at a Time
Choice of AI Provider and Model
Adjustable Conversation Memory
At-a-Glance Agent Overview
Quick Edit and Delete
Manage mobile AI agents from CRM settings

Mobile AI Agent Builder

Set up the mobile assistant without code. Write its instructions in plain English, choose which actions it may take, and pick the exact fields it may fill for each one, from new leads to ticket updates, with features such as:

Plain-English Instructions
Search Across All CRM Modules
Create Leads, Contacts and Tickets
Update Leads, Contacts and Tickets
Book Appointments and Tasks
Add Comments to Records
Choose the Fields for Each Action
Several Actions in One Request
Configure mobile AI agent instructions and CRM actions

Live AI Assistant in the Mobile App

Users tap the assistant, say what they need in plain words, and the AI does the CRM work for them. One sentence can create a contact, add a note and schedule a follow-up task. The results come back as cards the user can open straight away, with features such as:

Speak or Type Your Request
Live Transcript While You Talk
Several Actions from One Sentence
Step-by-Step Progress While It Works
Asks Only for Missing Details
Never Invents Names, Numbers or Dates
One-Tap Open for Created Records
Multiple Language Support
Use a live AI assistant in the CRM mobile app
Manage mobile AI agents from CRM settings
Configure mobile AI agent instructions and CRM actions
Use a live AI assistant in the CRM mobile app
AI Providers

Multi-Provider AI Architecture

The API key stays on the server. The mobile app does not receive the provider key. The same conversation behavior is used whichever provider is selected.

OpenAI Icon

OpenAI

Grok Icon

Grok

Google Gemini Icon

Google Gemini

Before & After AI

How Mobile AI Agents Reduces Manual Effort

✕ Traditional Process
✓ With Mobile AI Agents
01 Search

Navigating module menus and manually configuring field-by-field filters on mobile screens.

Finds a record from a sentence instead of a field-by-field filter.

02 Hebrew and English

Typing exact database strings and dealing with mismatched language picklist values.

Matches the picklist label the user says, and answers in that language.

03 Related Records

Manual relational lookup where searching by organization name misses contacts with ID-only relations.

Searches an organization by its name, not by an empty id on the contact.

04 Appointments and Tasks

Calculating calendar dates, converting timezones, and entering mandatory start and end fields.

Accepts today, tomorrow and a spoken time, and keeps a task as a task.

05 Follow-Up

Context is lost between screens or turns, forcing users to repeat details and start over.

One ai_session_id carries the conversation, so the app does not rebuild the history itself.

06 Result

Silent saves or ambiguous errors leaving users uncertain if the record was actually created.

The user hears whether the record was found or created.

Benefits

Business Benefits

01

Faster Mobile Work

Users can search and create from one message instead of navigating several screens.

02

Fewer Wrong Records

Search uses the real field, including related names, picklists and the user’s date and time.

03

A Conversation, Not a Single Shot

The agent can ask for a missing name and then finish the same task or appointment.

04

Language That Matches The User

An English question receives an English answer. A Hebrew question receives a Hebrew answer.

05

Administrator Control

Only enabled actions run, and create actions use the fields the administrator selected.

06

A clear Result For The App

state, action and actions tell the mobile app whether to ask another question or to show the record.

Security & Governance

Security and Administration

The agent runs only for a signed-in mobile user. Search results are limited to records that user may view. New records are assigned to that user.

Administrators control:

Which Agent is Active
The Provider, Model and API Key
Which Actions are Enabled
Which Fields a Create Action may Fill
The Agent Instructions

The API key is stored with the agent configuration and is not returned to the mobile app. ai_session_id belongs to the user who started that conversation.

Future Enhancements

Future Enhancements

The same pattern can grow without changing the way the app holds a conversation.

Record Updates from Follow-up

Update an existing record from a follow-up

Expanded Module Support

More modules, using the same schema-based search

Voice Interaction

Voice: the spoken sentence is already a message, and ai_session_id keeps the next utterance on the same request

Administrator Analytics

Usage history for administrators

Richer Result Summaries

Richer record summaries in the result message

From Forms to a Conversation

From Forms to a Conversation

Traditional Mobile Workflow

Open Module
Search or Open a Form
Fill Fields
Save

With Mobile AI Agents

Say What you Need
CRM Runs the Action
Hear What was Found or Created

If something necessary is still missing, the agent asks, the app sends the next message with the same ai_session_id, and the original request continues.

Human Oversight

The User Remains in the Conversation

The agent does not silently invent a person or a company that was never mentioned. It asks.

It does decide the values a person would expect it to decide:

Today and Tomorrow
A Missing Appointment End, Set to 30 Minutes After the Start
A Missing Title
A Category or Other Selected Field When a Sensible Value Exists

The mobile user still sees the result and the record. The administrator still decides which actions exist.

The Business Outcome

The Outcome of Mobile AI Agents

Conversational Search & Create: Mobile AI Agents makes search and record creation part of the mobile conversation.
Everyday Actions: Users can find a contact by organization, create a ticket, schedule an appointment for tomorrow, or finish a task in a second message.
Language Matching: The answer matches the language they used.
User Timezone Stored: The time they asked for is the time stored for their timezone.
Structured Response State: The app can tell a question apart from a finished action because every response carries state, action, actions and ai_session_id.
Key Takeaway

The useful AI agent is the one that finishes the CRM action and says what happened.

By keeping the agent inside the mobile CRM, the organization gets search and create in the user’s language, on the user’s calendar, and in one conversation the app can continue.

We use cookies to provide better experience on our website. By continuing to use our site, you accept our Cookies and Privacy Policy.

Accept