Skip to main content
RADA Richness Co., Ltd. logo ไทย
About us Services Agentic AI Courses Work Articles ContactChat with us on LINE
Chat with us on LINE
AGENTIC AI WORKFORCE

Agentic Marketing Workforce
& Operations System

We build an automated marketing team of 9 AI agents, all running on one shared Central Knowledge Base — they pass work to each other across functions, from market research to content, ad campaigns, and results summarized into LINE. Your people only press approve.

DELIVERED BY RADA Richness Co., Ltd. POWERED BY AIYA AI agent platform

Designed, built, trained, and supported by the RADA Richness strategy team · Powered by the AIYA AI agent platform

Coach Orn, Rusada Noisong, founder of RADA Richness Coach Boyd, Atchariya Daroj, founder of AIYA.AI
Coach Orn RADA RICHNESS · FOUNDER Coach Boyd AIYA.AI · FOUNDER
01 · EXECUTIVE SUMMARY

Make marketing a system, not a set of people

We design, build, and hand over an automated marketing team (Agentic AI Office) and an ad operations system that runs from campaign setup through to reporting. It solves 3 problems: a headcount bottleneck, knowledge walking out with staff who resign, and ad budget leaking unnoticed.

TARGET AUDIENCE

Built for companies and growing businesses with ad spend from THB 500,000 per month or more or THB 2–10 million in monthly sales

3 problems eating your marketing margin

!

Content cannot keep up with ad fatigue

You cannot produce new ad angles fast enough for audience fatigue. Cost per result climbs and sales fall with no clear reason.

People leave, knowledge goes with them

Media buyers and creatives leave often. The strategies that worked were never kept as an asset, so the system stalls every time someone changes.

High agency fees

You pay a percentage of ad spend every month, yet reports arrive late and campaigns are not adjusted in time.

What your company gets back

COMPANY ASSET

A system your company owns

Knowledge and strategy stay in your company's system for good, and do not leave with the employee who resigns

PRODUCTION SPEED

Creative output many times faster

Writes dozens of scripts, captions, and ad angles a day, cutting turnaround from weeks to hours

DATA-DRIVEN ADS

Catches wasted ad spend 24 hours a day

Catches underperforming ads and analyzes ROAS / CPA in real time, outside office hours too

FOUNDERS

Advice from the developers and specialists who run the system themselves

This system comes from two founders working together — one from the AI technology side, one from the marketing strategy side, both with hands-on experience in real businesses.

Coach Boyd, Atchariya Daroj, founder of AIYA.AIAIYA.AI · FOUNDERCoach Boyd — Atchariya DarojFounder of AIYA.AI · Enterprise advisor on LINE Solutions and AI Data-Driven strategy

He has worked with retail, real estate, and food and beverage businesses, helping organizations raise the standard of their marketing and communication with technology that fits how the business actually runs.

He specializes in designing AI Agents and applying LINE Beacon together with the LINE API, so businesses reach the right customers more precisely, capture richer data, and deliver an O2O experience that works.

Coach Orn, Rusada Noisong, founder of RADA RichnessRADA RICHNESS · FOUNDERCoach Orn — Rusada NoisongFounder of RADA Richness · Specialist in Digital Marketing, CRM and MarTech Solutions

With more than 15 years of experience, Coach Orn helps growing businesses turn the data they already hold into strategy, and grow on a footing that lasts.

Her strength is spotting the data a business is sitting on but not using yet, and turning it into a way to sell more.

02 · SYSTEM ARCHITECTURE

Just 1 central brain
connecting all 9 agent roles

Every agent works on the same data from the Central Knowledge Base, so answers never contradict each other and work passes across functions automatically.

Research Strategy Content Social Report Ads Spy Ads Ops Analytics Chat Support
CENTRAL BRAIN

Central Knowledge Base

One central brain that all 9 agent roles draw from, so nothing contradicts, and it stays with your company for good.

Semantic search (Vector Database) · answers from your real documents (RAG) · agent memory (Memory Schema) · rules the AI cannot cross (Guardrails) · per-person access rights (Role-Based Access Control)

MARCOM TEAM · 5

Marketing Communication

  • 1Market Research — trends, viral topics, competitor data
  • 2Market Strategy — turns campaign strategy into an Action Plan
  • 3Content Creator — articles, scripts, captions in your Brand Voice
  • 4Social Media Admin — queues and schedules publishing
  • 5Report & Analytics — Engagement · Reach · Response
PERFORMANCE · 3

Ad operations

  • 6Ads Spy & Angle — decode Winning Ads · Creative Hooks
  • 7Ads Operation — sets up campaigns, controls budget
  • 8Performance Analytics — ROAS · CPA · Conversion + alerts
CUSTOMER RELATIONS · 1

Customer Relations

  • 9Chat Support — answers customer chats, filters questions, and hands over cases that need a person
Included — a personal AI secretary on LINE for every employee

Connections: Facebook Page API · LINE Official Account · Facebook Ads · Google Ads · CRM / ERP

The full system diagram

From the moment your people give an instruction, through the central brain and the AI agent team, out to the platforms and systems you already use, and back as an asset your company owns.

Where people approve HUMAN-IN-THE-LOOP ● Approve plan ● Approve content ● Approve ad budget Your people PEOPLE Executives Instruct · Read reports Marcom team Brief · Review Ad operations team Budget · Approve campaigns Staff Personal AI secretary Instruction channels INTERFACE LINE OA Instruct from your everyday chat Back office Review · Configure · Track Per-person access rights Sees only permitted data First 20 accounts included in setup Central brain and AI agent team AGENTIC CORE Central Knowledge Base Product data · prices · business rules · Brand Voice · SOPs — every agent reads the same set CENTRAL KNOWLEDGE BASE Marketing Communication MARCOM · 5 1 Market Research 2 Market Strategy 3 Content Creator 4 Social Media Admin 5 Report & Analytics Ads team PERFORMANCE · 3 6 Ads Spy 7 Ads Operation 8 Analytics Customer care HUB · 1 9 Chat Support Agents hand work to each other across functions · people step in only to approve Connected systems INTEGRATIONS Platform channels Facebook Page LINE Official Account Facebook Ads Google Ads Internal systems CRM ERP Internal systems with an API What you get back OUTPUT Content ready to publish Scripts · Captions · Concepts Campaigns with budget control Set up · Monitor · Adjust budget Summary reports into LINE Daily · Event-based A knowledge base that grows daily A permanent company asset Owned by your company Stays when employees leave Data back Rules and security across the system GOVERNANCE LAYER Rules the AI cannot cross Per-person data access Standard output formats Full audit trail of actions

Scroll sideways to see the full diagram on a small screen

Automatic handoff flow across functions

STEP 1 Research Analyze trends and competitors
STEP 2 Strategy Turn into briefs and Action Plans
STEP 3 Content Write scripts, captions, concepts
STEP 4 Ads Ops Structure and run campaigns
STEP 5 Report Report into LINE via AI secretary

Your people only press approve at the points defined in the Human-in-the-Loop Process Map.

03 · DELIVERABLES

The 9 AI agent roles we deliver

Each role is trained on your business data, your rules, and your Brand Voice — not a general assistant that answers anything.

Function / Team # Agent name Key responsibilities
Marketing CommunicationMARCOM TEAM 1 Market Research Agent Researches market trends, tracks viral topics, and gathers competitor intelligence
2 Market Strategy Agent Reads market direction, sets campaign strategy, and turns ideas into an Action Plan
3 Content Creator Agent Writes articles, video scripts, captions, and graphic concepts in your Brand Voice
4 Social Media Admin Agent Schedules publishing, sets post times, and manages the social media content queue
5 Report & Analytics Agent Analyzes Engagement and Reach, and summarizes how content performed
Ad operationsMARKETING PERFORMANCE 6 Ads Spy & Angle Agent Decodes competitors' Winning Ads and develops new Creative Hooks
7 Ads Operation Agent Helps set up campaigns, checks campaign status, and keeps spend under control
8 Performance Analytics Agent Analyzes ROAS, CPA, and Conversion Rate, and alerts you when an ad drops below target
Customer RelationsCUSTOMER RELATIONS 9 Chat Support Agent Answers customer chats around the clock, filters out repeat questions, and hands over cases that need a person with the full context attached.
04 · STATEMENT OF WORK

Scope of work we deliver

The business goal is to cut hidden headcount costs, stop ad budget leaking, and build knowledge that stays with your company, not with the employee who leaves.

01

Discovery & Business Learning

We interview your team, collect Business Logic, Brand Guidelines, SOPs, product data, and Customer Personas, and produce the Human-in-the-Loop Process Map

02

System & Workflow Architecture

We design the Central Knowledge Base structure, the Agent Memory Schema, the Guardrails, and the automatic handoff flow across functions

03

Knowledge Base & Model Tuning

We install semantic search and document-grounded answering (Vector Database + RAG) so answers never drift from the facts, then write the System Prompt and output standards for all 9 roles.

04

Integrations & Multi-Channel

We connect the Facebook Page API, LINE OA, and Ads Accounts, then install the personal AI secretary on LINE with Role-Based Access Control.

05

Testing, Training & Handover

We run full system testing and formal acceptance with you (UAT — User Acceptance Test), plus a 6-hour training workshop across 1 full day.

30 days of standby support (30-Day Hyper-Care)

RADA Richness specialists stay on standby and tune the prompts through the first 30 days after go-live, until the system runs stable.

05 · ENGAGEMENT WORKFLOW

16 steps, from the first conversation to a system that runs steady

Five phases. Every phase has something you can review and sign off, so you don't wait until the end to see the work.

  1. 1Phase 1Discovery & assessmentPRE-SALES & DISCOVERY1Hear the leadership briefInitial Discovery & AlignmentBusiness goals, ad budget, expected results2Audit how work runs todayOperational & Pain Point AuditFind bottlenecks, repeat work and ad budget leaks3Pair your people with AIWorkforce & Co-Pilot MappingYour staff direct the AI and approve its work4Your decision pointReceive the proposalProposal & Solution BlueprintWith a solution blueprint and a cost comparisonProposal + solution blueprint
  2. 2Phase 2Contract & kick-offCONTRACT & KICK-OFF5Sign the SOW and contractSOW Agreement & Contract SigningReview the scope and the agreement before signing6Grant system accessReadiness & Access GrantingAccess to Facebook / LINE OA / Ads7Project kick-off meetingOfficial Kick-off MeetingMeet the team and agree the timelineAn agreed project timeline
  3. 3Phase 3Build and system setupDEVELOPMENT & TRAINING8Load your business knowledgeDeep Business LearningTeam interviews and SOP collection, about 3 working daysBRD + HITL Process Map9Build the central knowledge baseKnowledge Base & Vector DB SetupGuardrails keep the system from answering wrongSystem architecture blueprint10Train the 9 AI Agents9 AI Agents Prompt EngineeringTuned so the output meets your standards9 trained AI Agents
  4. 4Phase 4Integration & testingINTEGRATION & UAT11Billed as an add-onConnect external platformsAPI & LINE Gateway IntegrationLink the AI secretary on LINE to the Central HubA working integration12Test the full systemEnd-to-End & Edge Case TestingCheck accuracy and safety before it runs live13Your decision pointUAT sign-offUser Acceptance Testing (UAT)You test the system and sign it offSigned UAT acceptance document
  5. 5Phase 5Training, go-live & careENABLEMENT & GO-LIVE14Train your marketing teamIntensive Marketing WorkshopA 6-hour, full-day workshop your team can useSlides + prompt library + recordings15Go liveOfficial Go-LiveThe system runs live and the care period beginsA live system + user manual1630-day Hyper-Care30-Day Hyper-Care SupportOur team monitors and tunes for the first 30 days30 days of hands-on support

SOW = Statement of Work · BRD = Business Requirement Document · HITL = Human-in-the-Loop · Guardrails = Zero Hallucination Guardrails · LINE OA = LINE Official Account · UAT = User Acceptance Testing · Central Hub = your central knowledge base

06 · ENABLEMENT

A 6-hour workshop makes your team the operators

Intensive AI Marketing Team Workshop for your marketing communication team, ad operations team, and the executives involved

09:00 – 12:00 · 3 hours

Morning — foundations and using the Marcom AI Team

1 hr
Module 1 — Introduction to Agentic Workflow Understand how to work with an AI agent as a Co-Pilot, and how to reach the Central Knowledge Base
2 hrs
Module 2 — Mastering Marcom Agents in Practice Briefing the Market Research & Strategy Agent · how to brief and quality-check the Content Creator Agent · approving Social Media Admin work and reading Report Agent output
13:00 – 16:00 · 3 hours

Afternoon — ad operations, coaching, and real cases

1.5 hrs
Module 3 — Marketing Performance & Ads Optimization Directing the Ads Spy Agent · working with the Ads Operation Agent to set up and launch campaigns · reading the Dashboard to adjust ad budget
1 hr
Module 4 — Real Case Simulation & Secretary on LINE We simulate a real end-to-end marketing brief (Research → Content → Ads → Report) and practice giving instructions through the AI secretary on LINE
0.5 hr
Module 5 — Q&A, Feedback & Evaluation Best practices, common pitfalls, and hand-over of Standard Prompt Templates with an evaluation checklist
DELIVERABLES
  • Slides and training handouts
  • Standard Marketing Prompt Cheat Sheet & Templates
  • Recorded video of the training for later review
07 · BUSINESS CASE

Hire every year, or invest once

A straight comparison between adding 3–4 headcount and investing once in an Agentic AI Marketing Team

OTHER OPTION

Add 3–4 headcount

  • Media buyers and creatives leave often, and what your team learned about Winning Ads walks out with them
  • Real cost runs above salary — social security, bonus, benefits, equipment, software
  • Interviewing and retraining costs you time every time someone changes
  • 1–2 pieces of content a day, ads checked only during working hours
  • Human error in budget changes or audience selection burns ad money for nothing
RADA × AIYA

AGENTIC AI MARKETING TEAM

  • You get a system that is a company asset — knowledge and strategy stay in the Central Knowledge Base permanently
  • One investment, with no per-head costs rising every year, such as bonuses, benefits, and training new hires
  • Writes dozens of script and caption variants in one pass
  • Ads are monitored 24 hours a day, so less budget burns outside office hours
  • Decisions run on data, not on gut feel

Accuracy and standards you control

AI delivers work in your Brand Voice and Business Logic every time, so you do not review the same thing twice

Your people become the operators

Nobody is laid off. Routine work is cut, and your people move into strategist and AI operator roles that are measured on business results.

Handoffs that never stall

The system pulls data across Research, Content, and Ads, and reports into LINE immediately

9 hires versus one Agentic system

To cover all 9 functions with people, how many roles would you hire and what would it cost — against a one-time system investment?

With human hires With AI staff
# Role to hire Market salary (THB/month) Replaced by AI staff AI staff fee (THB/month)
1Market ResearcherMarket Research25,000 – 35,000Market Research Agent3,000
2Marketing StrategistMarket Strategy40,000 – 60,000Market Strategy Agent3,000
3Creative / ContentContent Creator25,000 – 35,000Content Creator Agent3,000
4Social Media AdminSocial Media Admin18,000 – 25,000Social Media Admin Agent3,000
5Content AnalystReport & Analytics30,000 – 40,000Report & Analytics Agent3,000
6Ad CreativeAds Spy & Angle30,000 – 40,000Ads Spy & Angle Agent3,000
7Media BuyerAds Operation35,000 – 50,000Ads Operation Agent3,000
8Ad Performance AnalystPerformance Analytics35,000 – 50,000Performance Analytics Agent3,000
9Chat SupportChat Support20,000 – 28,000Chat Support Agent3,000
All 9 roles 258,000 – 363,000 All 9 AI staff roles 27,000
HIRE 9 STAFF

First-year cost

4,020,000 – 5,660,000THB

12 months of salary plus around 30% in hidden costs — social security, bonus, benefits, equipment, software, and recruitment

  • A cost that repeats every year and rises with salaries
  • Works office hours only, takes sick leave and holidays, and can resign
  • Knowledge sits with people, not with the company
AGENTIC SETUP

First-year cost

874,000THB

System setup THB 550,000 + monthly AI staff fee THB 27,000 x 12 months — add-on fees for the channels and systems you actually connect are not included.

  • From year two you pay only the monthly AI staff fee, with no setup fee again
  • Works 24 hours a day, no leave, no resignations
  • Knowledge and strategy stay in your Central Knowledge Base permanently

Note: salary ranges reference Bangkok market rates for mid-level roles · hidden costs estimated at about 30% of salary · these figures compare cost structures and are not a guarantee of returns · the Agentic system is designed to cut routine work, not to replace your entire staff

08 · INVESTMENT STRUCTURE

2 main fees, plus add-ons

We break the fees out so you see what you pay for, instead of one lump sum. There are 2 main parts: a one-time setup fee and a monthly AI staff fee. Platform connections and external API integrations are add-ons, charged only for what you actually use.

ONE-TIME

Core Setup

Main system setup, one-time flat fee

From 550,000THB For all 9 AI agent roles
  • Central Knowledge Base architecture
  • Build and train all 9 AI agents
  • Security and the rules the AI cannot cross (Guardrails)
  • 1-day training + 30 days on standby
  • 20 user accounts included (add more, see add-on fees)
RECURRING

Monthly AI staff fee

Priced by the number of agents you switch on, from THB 3,000 each

From 3,000THB/ agent / month All 9 roles active = THB 27,000 / month
  • Ongoing system and integration maintenance
  • Standard quota of 10,000 Token per agent per month (a Token is the unit that counts the text an AI processes) — top up if you go over quota, see add-on fees
  • Continuous accuracy tuning for every agent
Included

A personal AI secretary on LINE for every employee — give instructions, look up information, and receive reports in the chat app your team already uses every day, connected straight into the Central Hub

Add-on fees

Charged only for what you actually use, separate from the 2 main fees above — platform connections, external API integration, extra user accounts, and Token top-ups

ADD-ON · RECURRING

Platform Connect Fee

Platform Connect Fee · priced by the number of channels you switch on

300 THB / channel / month
Channels you can connect
  • Facebook Page
  • LINE OA
  • Facebook Ads
  • Google Ads
ADD-ON · PER USER ACCOUNT

Extra user accounts

User Account Fee · for admins added to the back office beyond the 20 accounts already included in the setup fee

300 THB / user account
What each account gets
  • Access to the Agentic back office
  • Brief and review agents within your permissions
  • Set data access rights per person

The personal AI secretary on LINE for every employee stays inside the original scope, at no extra cost

ADD-ON · PER WORKING DAY

External system integration

System Integration · priced by team working days (Man-day)

From 18,000 THB / Man-day

Minimum 3 Man-day = THB 54,000

Example integrations
  • API connection to your existing CRM
  • API connection to your existing ERP
  • Any other internal system with an open API

The actual number of Man-days is estimated from system complexity and stated in your quotation

ADD-ON · PAY AS YOU USE

Token Top-up

Token Top-up · for months when you go over the standard quota

From 1,500 THB / top-up
Conditions
  • Use it when the standard 10,000 Token per agent per month is not enough
  • Charged per top-up, separate from the monthly fee
  • In months you stay inside the quota, you pay nothing here

The Token volume per top-up is stated in your quotation

SCOPE CLARIFICATION

Terms and scope of service

The standard package covers the system architecture, the knowledge base, and training the AI Agents as set out in the contract.

Not included in the base package
  • Strategic AI Consulting — business consulting and marketing strategy on a quarterly or annual basis
  • Comprehensive Agentic Audit — an in-depth audit of security, model accuracy, and Agent performance

Talk to our team to scope the work and get a quote for the add-on services your organization needs.

09 · FAQ

Questions executives ask

The questions executives actually ask us — from how this differs from ChatGPT to how your data is kept safe

Still no answer? Ask us
How is Agentic AI different from letting the team use ChatGPT?

ChatGPT is a separate chat box. Every new session starts from zero context, and nothing is handed on to the next task. Here, all 9 agents read from the same Central Knowledge Base, remember your business context, and pass work to each other across functions along a designed flow. Your people step in only where an approval is required.

Do we have to let marketing staff go?

No. The system is built to cut repetitive routine work and move your existing people up to running it — as strategists and AI operators who brief, review, and measure business results. That is why we include a full 1-day workshop in the scope of work.

Could the AI give a wrong price or promotion and cause problems?

This is exactly why we use a Vector Database and RAG — agents answer from your real documents, not from guesswork — and why Guardrails define which topics they must never answer alone and must pass to a person. We run a Stress Test & Edge Case Simulation before every go-live.

How safe is the company data we put in?

The knowledge base belongs to your company, and Role-Based Access Control sets exactly who can see which set of data. We put this in place in Phase 2, before any real data enters the system.

How big does a business need to be for this to pay off?

It fits companies spending from THB 500,000 per month on ads, or with THB 2–10 million in monthly sales. The payback comes from two directions: the headcount you no longer add, and the ad budget you stop wasting. If your business is smaller than that, start with Performance Marketing or Marketing Communication first.

Who actually does the work, RADA or AIYA?

Your contracting party, responsible for all the work, is RADA Richness Co., Ltd. — strategy, system design, training, and support after handover. AIYA is the AI agent platform we use as the engine. You deal with, and sign off with, the RADA team only.

NEXT STEP

One hour with us before you commit

Tell us how your team and your ad budget look today. We will assess how many agents you should start with, which systems to connect, and give you a clear scope of work and quotation.

RADA × AIYA Delivered by RADA Richness Co., Ltd. · Powered by the AIYA AI agent platform