Moving the Malaysian mobile operator from human-prompted AI assistants to a coordinated team of agents that runs the network and subscriber base on a daily schedule and delivers a ranked decision list to the CEO every morning.
Your AI investment will not pay back until the AI stops waiting to be asked.
Most Malaysian deployments still treat AI as a faster search bar — a tool that produces value only when a human pulls it. The next operating model inverts that: a team of specialist agents consumes the firm's data on a fixed daily schedule, weighs the trade-offs (MCMC spectrum rules, ARPU vs. churn, RAN-share economics, dealer subsidy compliance), and delivers a ranked, ready-to-approve Decision List to the executive every morning.
The ShiftFrom copilots to a coordinated team of agents
The Problem
AI is reactive
Copilots and dashboards still require a human to formulate the question, pull the data, and synthesise the answer. Decision speed = human speed.
The Shift
From pull to push
Agents run on a schedule. They watch for variance, run the scenarios, and surface decisions before the executive knows to ask.
The Prize
Compounding daily edge
Decisions that used to take a week of cross-functional meetings arrive pre-staffed, pre-modelled, and ranked by RM-impact every morning at 06:00 MYT.
Slide 2 — Governing ThoughtAITraining2U · The Agentic Operating Model
The Paradigm Shift
03 / 13
Current State vs. Target State
Two operating models. Only one scales beyond the executive's calendar.
Today — Reactive AI
Humans pull. AI answers.
Trigger — A human notices a problem or asks a question.
Cadence — Ad-hoc; bounded by manager attention.
Synthesis — Performed in the analyst's head, slide deck, or spreadsheet.
Coverage — Whatever the executive thought to look at this week.
Output — A chart, a summary, a "this looks worth investigating."
Bottleneck — The bandwidth of the most expensive person in the room.
Target — The Agentic Operating Model
Agents push. Humans approve.
Trigger — A scheduled run (e.g., 04:00 MYT daily), or a signal crossing a pre-set threshold.
Cadence — Continuous; the team of agents never sleeps.
Synthesis — A dedicated Orchestrator agent does it before the executive opens their laptop.
Coverage — Every subscriber, tower, channel, cluster, and tier — every day.
Output — A ranked Decision List with modelled RM-impact and one-click approval.
Bottleneck — Removed. The executive becomes a judge, not a query.
The implication for the C-suite: the unit of work shifts from "running the business" to "ratifying the decisions the business has already surfaced." Span of control expands by an order of magnitude.
Slide 3 — Paradigm ShiftAITraining2U · The Agentic Operating Model
Case Study · Malaysia
04 / 13
A worked example — national Malaysian mobile operator
A Malaysian business where every variable moves every hour. The ideal stress-test.
A national mobile operator compresses every operational discipline of a large enterprise into a single subscriber-day: dynamic plan and roaming pricing against the other Big-4 telcos, spectrum and small-cell capacity under MCMC allocation rules, dealer compensation under PDPA and KPDN subsidy guardrails, 14,000 base-station uptime in tropical heat and monsoon, demand driven by F1 weekends, Hari Raya balik kampung, and the digital-bundle calendar. Multiplied across a national network — Klang Valley to Kuching — no human team can hold the full state of the business in working memory.
National
Network footprint — Peninsular Malaysia, Sabah & Sarawak · 14,000 base stations
MCMC
Spectrum, QoS & subsidy compliance · PDPA on subscriber data · MyCERT
Hourly
Workforce under Employment Act + EPF / SOCSO · OT-capped · retail + dealer + digital channels
The five operational tensions the team of agents must hold simultaneously
Tension 1
ARPU vs. Churn
Reprice the plan for margin, or hold the line and lose the high-value subscriber to a Big-4 rival?
Tension 2
Coverage vs. Capex
Pre-deploy small cells for the event-weekend surge, or absorb the drop-call churn?
Tension 3
Retail vs. Dealer
Tilt commissions to own-store digital, or hold the dealer footprint that owns Sabah and Sarawak?
Tension 4
Owned vs. RAN-share
Run the loss-making tower yourself, or RAN-share it with a rival to free the opex?
Tension 5
Scale vs. Decommission
Replicate the Klang Valley cluster build, or decommission the bottom-quintile sites in northern Perak?
Slide 4 — The CaseAITraining2U · The Agentic Operating Model
The Team of Agents
05 / 13
Five specialists, one chief of staff
Each agent owns one operational tension. The Orchestrator owns the trade-off between them.
Think of each agent as a digital department head who never sleeps, never takes leave, and reads every tower's and every subscriber's data every hour. The chips at the bottom of each card show the kind of expertise the agent embodies — detailed on the next slide.
Watches: dealer footfall, own-store productivity, commission tiers, subsidy compliance under KPDN, skill matrix across channels.
Decides: the next-best action for every channel sales rep and dealer — compliant with subsidy rules, weighted to high-ARPU acquisition.
Dealer footfall forecastingCompensation tuningCompliance on subsidy rulesSkill matrix
NetOps Agent
Network Operations
The Network Reliability Manager
Watches: tower uptime, diesel-genset health, drop-call anomaly across cells, energy spend, predictive-maintenance telemetry.
Decides: which towers to service before they fail, when to shift load off-peak, and where genset injectors are trending toward failure.
Tower uptimePredictive maintenanceEnergy managementDrop-call anomaly detectionGenset health
Cluster Agent
Cluster Portfolio
The Network Strategist
Watches: cluster-level (state) ARPU tier, traffic share, dealer density, tower utilisation, and what the other agents report per cluster.
Decides: classifies every cluster as Overperform / On-Target / Underperform vs. its peer cohort, and triggers the right tier action — including RAN-share or decommission.
Watches: what all five specialists are recommending, plus the P&L, ARPU and cash flow.
Decides: reconciles conflicts, ranks the day's calls by expected RM-impact, and presents the shortlist to the CEO.
Decision synthesisCausal attribution
Slide 5 — The Team of AgentsAITraining2U · The Agentic Operating Model
The Build Team
06 / 13
What sits inside each agent
The skill stack. Each agent bundles a named set of business capabilities.
An agent is not one trick — it is a stack of discrete business capabilities working together. Column 2 lists the capabilities you must build (or already partly run today, fragmented across functions). Column 3 tells you who to hire. Column 4 is the promise each agent makes to the others — the contract that lets the team operate as a team, not as a collection of dashboards.
Agent
Capability stack
Who you hire to build it
What it commits to deliver every run
Pricing AgentCustomer Demand & PricingThe Plan & Tariff Strategist
Plan & bundle recommendationSubscriber × cohort × month, refreshed daily — which postpaid / prepaid bundle fits.
Churn propensity scoringHow likely each subscriber is to port out in the next 30 days — and what would hold them.
Roaming & data-pack pricingSurge pricing for Hari Raya and balik kampung travel; ASEAN roaming bundles.
Cross-sell to fixed line / enterpriseFamily-plan and fibre attach propensity from device and usage patterns.
Promotion uplift testingWhat a Concert Pack or weekend bundle actually lifts vs. baseline — not what marketing claims.
Pricing strategist · churn analytics lead · data engineer for CRM / billing feeds.
"For the next 30 days, here is what each subscriber cohort will buy at every channel, and the bundle that maximises ARPU net of retention cost."
"Here is where capacity will be under-served this week, which sites to densify, and how much spectrum to re-farm — with the MCMC paperwork pre-staged."
Peer cohort matchingGroups clusters by state, urbanisation, ARPU tier, demography — apples to apples.
Composite performance scoringARPU, market share, tower utilisation, churn, energy cost per Mbps — rolled into one score.
Tier classificationOverperform · On-Target · Underperform vs. true peers — at the state and cluster level.
Intervention uplift testingOnly triggers actions (densify, RAN-share, decommission) that have moved similar clusters before.
Decommission & RAN-share diligenceSurfaces the evidence pack and modelled opex savings for each tower-rationalisation case.
Network / portfolio strategist · analytics lead with causal / experimentation background.
"Across the national network of clusters, here are the Overperformers to replicate, the Underperformers to RAN-share or decommission, and the action proven to work on clusters like these."
Chief of StaffChief of StaffThe Synthesis Layer
Multi-criteria decision rankingWeighs RM-impact, confidence, risk, strategic fit.
Conflict reconciliationWhen DDPA wants a promo but HCOA can't staff it — adjudicates.
Risk-appetite calibrationLearns the CEO's actual risk tolerance from approval history.
Causal attribution to source agentEvery recommended call traces to the agent that surfaced it.
Executive narrative draftingThe one-sentence "why" the CEO sees on each decision.
Decision-science lead · chief of staff with analytics fluency · senior orchestration engineer.
"Here are the 3–5 calls only you should make today, ranked by RM-impact, with the reasoning and the source agents."
How to read this slide: column 2 is the skill stack — the named business capabilities the agent automates. Many of these capabilities exist somewhere in your org today, fragmented and run monthly. The shift is bundling them into one agent that runs them daily, together. Column 3 is the small, cross-functional team that builds and owns it. Column 4 is the contract that makes the agents a team, not six dashboards.
Slide 6 — The Build TeamAITraining2U · The Agentic Operating Model
Architecture
07 / 13
The Information Pipeline
The diagram is the operating model. Read it top-to-bottom.
Raw signals feed the five specialist agents. The specialists' outputs cascade — Pricing Agent's forecast is the input to Channel Agent, Capacity Agent, and Cluster Agent. The Orchestrator consumes all five and emits one artefact: a ranked decision list for the executive.
Layer 1 · Raw Signals (refreshed every 15 minutes to 24 hours)
External
Competitor plan scrape · MCMC filings · roaming partner rates
3–5 ranked, RM-quantified decisions awaiting one-click approval (see slide 10)
Human-in-the-loop
Raw signal source Specialist agent Orchestrator (synthesis) Executive decision artefact
Slide 7 — Architecture DiagramAITraining2U · The Agentic Operating Model
Unified Data & Memory
08 / 13
How the sub-agents feed the master — and what binds them together
Five sub-agents feed one master. All six share one unified data & memory layer.
The five specialists are not isolated silos. They all read from — and write back to — a single shared layer of data, memory, and learned context. That shared layer is what lets the swarm behave as one coherent operating system, not six dashboards on a Teams channel.
Sub-agent (specialist)
Master agent (orchestrator)
Shared operational data
Shared long-term memory
Slide 8 — Unified Data & MemoryAITraining2U · The Agentic Operating Model
The Information Cascade
09 / 13
How the agents talk to each other
The agents are not peers — they are linked. Each link is where the leverage lives.
The diagram on slide 7 shows the wiring. This slide shows the conversation — exactly what each agent tells the next, in plain English. No human team has ever held this whole conversation end-to-end. That is the point.
FromPricing Agent · Plan & Tariff Strategist
→tells
ToChannel Agent · Channel & Salesforce
"38k Klang Valley subscribers are in the upper-churn quintile. Bundle the Concert Pack at +RM 18/sub/month and send it through the dealer + own-store channels on Friday at 11:00."
FromCapacity Agent · Bandwidth Planner
→tells
ToNetOps Agent · Network Reliability
"Forecast congestion at 220% across 14 Bukit Bintang sites for the F1 weekend. Pre-deploy the cell-on-wheels and small cells; the permits are already cleared. Schedule no field maintenance in that cluster from Friday 06:00."
FromNetOps Agent · Network Reliability
→tells
ToCluster Agent · Network Strategist
"18 towers are showing diesel-genset injector wear that will fail within 14 days. Service before the Aidiladha long weekend — and flag whether the four northern Perak sites are even worth servicing given they're already on the decommission watchlist."
FromCluster Agent · Network Strategist
→tells
ToChief of Staff · Chief of Staff
"24 northern Perak towers have sat in the bottom quintile of their cluster cohort for 12 weeks running. RAN-share with Cellcom on this footprint is modelled at RM 6.4M/yr opex saving. Diligence pack ready — needs board sign-off Q3."
FromChannel Agent · Channel & Salesforce
→tells
ToPricing Agent · Plan & Tariff Strategist
"Last quarter's dealer compensation tweak in Sabah lifted gross-adds by 8% without breaching subsidy rules. Replicate the same comp structure to Sarawak dealers this quarter — and tilt the bundle mix toward family-plan attach to lock in the lift."
FromChief of Staff · Chief of Staff
↺loops to
ToAll agents
"Last week's Concert Pack offer lifted retention on the targeted cohort by 3.2 points. Continue prioritising Pricing Agent's upper-quintile churn-risk targets. The CEO's revealed risk appetite on RAN-share has shifted — Cluster Agent, push the bottom-quintile cases harder this cycle."
Slide 9 — The Information CascadeAITraining2U · The Agentic Operating Model
The Loop
10 / 13
Why this compounds — and a reactive copilot does not
Every approved decision teaches the system how to be smarter tomorrow.
09:00 onwards · Decisions execute through existing systems (CRM / billing, OSS, dealer-comp engine, RAN orchestrator, HRIS).
23:59 · Outcome data flows back as ground truth. Forecasts and tier moves are scored.
Why It Compounds
The reactive copilot has no memory of yesterday's bet
Forecast scoring — every prediction is measured against what actually happened. Drift is detected and the agent self-corrects.
Risk-appetite learning — every CEO approval teaches the Orchestrator how aggressive the boss really is, not what the policy doc says.
Playbook validation — Cluster Agent only triggers a tier action (densify, RAN-share, decommission) when matched-peer evidence says it has worked on similar clusters before. Each triggered action retrains the evidence base.
Compounding edge — Year 1 you replace meetings. Year 2 the system out-forecasts the team that used to run them.
Executive takeaway: a reactive copilot is a productivity tool — it makes today faster. The agentic operating model is a learning institution — it makes tomorrow better than today, on schedule, without anyone asking.
Slide 10 — Optimisation LoopAITraining2U · The Agentic Operating Model
The Artefact
11 / 13
What the CEO actually opens at 06:00 MYT
The Daily Prioritised Decision List.
Five decisions, ranked by expected RM-impact and risk. Each pre-staffed across pricing, network capacity, channel, operations, and cluster portfolio. The CEO judges the trade-off — the answer is already assembled.
RunFri · 22 May 2026 · 04:00 MYT
Generated byChief of Staff · Orchestrator
Scope14,000 towers · 8M subscribers · all channels
Cluster Agent · Portfolio tier snapshot · every cluster benchmarked against its peer cohort today
OverperformTop decile
1,820clusters
Trigger: replicate the top-tier Klang Valley densification playbook across the matched On-Target cohort — meaningful per-cluster quarterly ARPU + capacity lift modelled.
On-TargetMiddle 80%
11,200clusters
Trigger: maintain and tune. A small group approaching the upper band — pre-qualified for the Overperform densification playbook next cycle.
UnderperformBottom decile
980clusters
Trigger: RAN-share / decommission diligence where the northern Perak cluster has sat in the bottom quintile for 12 consecutive weeks.
#
Recommended decision
Modelled impact
Source agents
Action
1
Boost the Concert Pack offer to high-churn-risk subscribers — Klang Valley cluster
Pricing Agent: 38k subscribers in the upper-churn quintile; matched-uplift on the bundled offer +RM 18/sub/month. Channel Agent confirms dealer + own-store + digital channels ready. Send Friday 11:00 — retention + ARPU lift compounds across the festive cycle.
+RM 4.1MARPU + retention · High confidence
Pricing Agent · Channel Agent
P0Approve
2
Add small-cell capacity at 14 Bukit Bintang sites ahead of the F1 weekend
Capacity Agent: forecasted congestion +220% Fri–Sun on the F1 corridor. Cell-on-wheels and small-cell permits already cleared with MCMC; 48-hour install window. NetOps Agent confirms no field maintenance scheduled in cluster.
+RM 2.3MAvoided drop-call churn · High confidence
Capacity Agent · NetOps Agent
P0Approve
3
Portfolio action — decommission 24 underperforming towers in northern Perak · RAN-share with Cellcom on the footprint
Cluster Agent: the northern Perak cluster is in the bottom quintile of its peer cohort for 12 weeks running; densification playbooks have not moved similar clusters. RAN-share deal modelled at +RM 6.4M opex saving/yr against negligible ARPU impact. Board approval Q3.
+RM 9.6MAnnualised opex · Medium-high confidence
Cluster Agent · Capacity Agent
P0Approve
4
Predictive maintenance on 18 towers with diesel-genset injector wear — service before Aidiladha
NetOps Agent: fuel-consumption anomaly on 18 genset-backed towers suggests injector wear within the 14-day failure window. Schedule the service window before the Aidiladha long weekend to avoid an outage in low-coverage zones.
+RM 740kAvoided downtime · High confidence
NetOps Agent
P2Approve
5
Escalate to CEO — 700MHz spectrum re-farm dispute with MCMC blocking 5G rollout in 3 states
Capacity Agent + Chief of Staff: regulatory uncertainty on the 700MHz re-farm is deferring 5G capex in three states and capping ARPU upside on the premium plan tier. Needs SVP-level engagement with MCMC before the next council meeting.
−RM 12MDeferred capex / opportunity if unresolved
Capacity Agent · Chief of Staff
EscRoute
Slide 11 — The Daily Prioritised Decision List · Illustrative · MalaysiaAITraining2U · The Agentic Operating Model
The Implementation Path
12 / 13
From a single channel sales rep to the full operating model
Four phases. Hire as you go. Right-size for your maturity.
Telcos don't begin at the agentic operating model — they walk there. Each phase adds agents, decision rights, and value. The entry bar matches where you actually are today, not the end-state you aspire to. Most Malaysian operators should start at Phase 1 — a single agent in one channel sales rep's pocket.
Phase 01 · AssistCSR Co-pilotMonths 0–2
One agent in the channel sales rep's pocket. A daily action checklist on their phone — not a dashboard, not a report.
Entry bar — your starting maturity
Connected CRM / billing plus dealer-tier data. Channel manager runs comms over WhatsApp.
A daily insights email at 06:00 MYT: 1–2 surfaced churn / ARPU anomalies for the consumer marketing team.
Illustrative first project
Pricing Agent stood up as the plan & tariff advisor for the consumer marketing team. Plan-mix recommendations scored daily against CRM activations.
Build team3 people
Phase 03 · WalkCoordinated OpsMonths 6–12
The operational trio. Agents start talking to each other and to existing systems — managers still approve every action.
Entry bar — your starting maturity
Phase 2 live and trusted. Executive used to daily insights. Small data team in place.
Agents activated
Pricing AgentCapacity AgentNetOps AgentChannel AgentCluster AgentChief of Staff
Mode: Coordinated. Pricing Agent's forecast cascades into Capacity Agent & NetOps Agent. Actions auto-drafted; line managers approve.
What the CEO sees
A weekly cross-agent scorecard plus same-day escalations when agents disagree or capacity thresholds are crossed.
Illustrative first project
Subscriber-to-network loop live on the top 12 metropolitan clusters. Cascade: demand forecast → capacity plan → field service in one flow.
Build team8–12 people
Phase 04 · RunFull Operating ModelMonths 12–24
All sub-agents + the master orchestrator + the unified data & memory layer. The CEO opens the Daily Decision List at 06:00.
Entry bar — your starting maturity
Phase 3 producing measurable RM-lift on each agent. Cross-functional data team. Executive ready for one-click approval.
Agents activated
Pricing AgentCapacity AgentChannel AgentNetOps AgentCluster AgentChief of Staff
Mode: Full agentic operating model. Autonomous synthesis; CEO ratifies the daily list; system learns from every approval.
What the CEO sees
The Daily Prioritised Decision List (slide 11). 3–5 ranked, RM-quantified calls awaiting one-click approval.
Illustrative first project
National operating system live across 14,000 towers + 8M subscribers — including Sabah and Sarawak. Year 2: the system out-forecasts the team it replaced.
Build team15–20 people
Slide 12 — The Implementation Path · IllustrativeAITraining2U · The Agentic Operating Model
The Mandate
13 / 13
What the board must decide
Stop buying copilots. Start designing the operating model that runs while you sleep.
The technology is no longer the constraint. The constraint is whether the executive team is willing to redefine its own job — from asking the questions to ratifying the answers a team of agents has already prepared.
01
Pick one P&L line, not a platform
Start with the agent that owns your biggest tension — pricing, inventory, labour, assets, or portfolio. 90-day pilot, one Malaysian region.
02
Hire to the discipline, not the job title
Slide 6 is your org chart. Each row is an existing business discipline you already partly run somewhere — fragmented and monthly. Digitise it and put it on a daily cadence.
03
Instrument the decision, not the model
Track modelled vs. actual RM-impact on every approved decision. That single metric is the only one that matters in year one.
04
Re-write the executive job description
Move the C-suite calendar from "status meetings" to "decision reviews." The agents give back the time. Spend it on the bets only humans should make.
End · Slide 13 · The Agentic Operating Model · Malaysia EditionAITraining2U · aitraining2u.com · hi@aitraining2u.com
←→ Slides↑↓ SlidesF Fullscreen
Build It Yourself
Spin up your National Mobile Operator agentic operating model.
Run these prompts in order in Claude (or ChatGPT, Lovable, Bolt, v0, Claude Code, n8n). They are pre-filled with the National Mobile Operator archetype, the 5 specialist agents from this case study, and example decisions — paste them into a session and you will get a working scaffold for a multi-agent dashboard and control panel tailored to your business. Iterate from there.
Synthetic data shaped exactly like what the agents would read in production. Use it to scaffold Step 4 (Daily Decision List schema), all 5 prompts in the Knowledge Graph section, or to seed a local Obsidian vault — no production access required.
You are designing a multi-agent operating system for a Malaysian National Mobile Operator business.
Archetype: A Malaysian national mobile operator — ~8M subscribers, ~14,000 base stations, postpaid + prepaid + fixed-line bundle, retail + dealer + digital channels nationwide.
Build a team of 5 specialist sub-agents + 1 master orchestrator named Chief of Staff:
- Pricing Agent — Customer Demand & Pricing Agent: The Plan & Tariff Strategist
- Capacity Agent — Network Capacity & Planning Agent: The Bandwidth Planner
- Channel Agent — Channel & Salesforce Agent: The Retail & Dealer Planner
- NetOps Agent — Network Operations Agent: The Network Reliability Manager
- Cluster Agent — Cluster Portfolio Agent: The Network Strategist
- Chief of Staff — Chief of Staff: synthesises the 5 specialists' outputs into a ranked Daily Decision List for the CEO every morning.
The team holds these 5 operational tensions simultaneously: ARPU vs Churn, Coverage vs Capex, Retail vs Dealer, Owned vs RAN-share, Scale vs Decommission.
For each of the 6 agents, write a system prompt that includes: persona, decision authority (what it can recommend vs. approve), data it reads, tools it can call, output schema, and how it talks to the next agent in the cascade. Output 6 system prompts in markdown.
Step 2 of 6
Data inputs, memory layer, and compliance
I need to map the data inputs and memory for the National Mobile Operator multi-agent system you just designed (agents: Pricing Agent, Capacity Agent, Channel Agent, NetOps Agent, Cluster Agent, Chief of Staff).
Real-time signals available in this industry: Subscriber CRM, charging system (CCS/OCS) data, network performance KPIs (RAN OSS), cell-tower congestion, MyEG/digital channel conversions, dealer footfall, MCMC filings, churn-risk predictors.
Regulatory and compliance feeds we must honour: MCMC, PDPA, MyCERT, KPDN (subsidy/marketing rules).
For each of the 5 specialist agents, output a YAML schema that lists:
- data_sources: with source name, refresh cadence, access method (API / message bus / file drop), authentication style
- shared_memory_writes: what this agent commits back to the unified data + memory layer (decisions, forecasts, outcomes, learned context)
- shared_memory_reads: what it reads from the other agents' write-backs
- pii_or_compliance_flags: which fields require PDPA/regulator-specific handling
Also output a Chief of Staff section that defines the shared "Long-term Memory" (decision history, forecast vs. actual, approvals, playbook lift), the shared "Learned Context" (CEO risk appetite, peer cohort definitions, policy rules, tier-action playbooks), and the read/write rails between the specialists and the master.
Step 3 of 6
Inter-agent cascade and nightly retraining
Design the inter-agent communication cascade for the National Mobile Operator multi-agent system (agents: Pricing Agent, Capacity Agent, Channel Agent, NetOps Agent, Cluster Agent, master: Chief of Staff).
Daily flow: Pricing Agent → Capacity Agent → Channel Agent → NetOps Agent → Cluster Agent → Chief of Staff, then Chief of Staff emits a Daily Decision List. Add one nightly feedback loop where Chief of Staff writes back to all 5 specialists with the outcomes of yesterday's approved decisions so they retrain their priors.
Deliverables:
1) A JSON message envelope schema for inter-agent messages (fields: sender, recipients, intent, payload, refs_to_data, decision_authority_request, expected_action).
2) Six worked-example messages — one for each link in the cascade — written in plain English for a Malaysian National Mobile Operator context. Reference real signals (monsoon, festive windows, BNM/MCMC/MoH/JAKIM/JPJ/DOSH where relevant) so a CEO would find them credible.
3) The schema for the Chief of Staff's nightly retraining message back to each agent.
Step 4 of 6
Daily Decision List output schema
Build the Daily Decision List output schema for the Chief of Staff orchestrator in the National Mobile Operator multi-agent system. This is the single artefact the CEO opens every morning.
Each list entry has:
- priority: one of P0 (immediate), P1 (this week), P2 (this month), Esc (escalate to CEO)
- decision: one-sentence description
- agents_involved: list of agent codes from Pricing Agent, Capacity Agent, Channel Agent, NetOps Agent, Cluster Agent
- rm_impact: signed number in RM (millions or thousands), positive for upside / negative for risk if unresolved
- why: one-line rationale tying the recommendation to the signals it came from
- recommended_action: one of approve / defer-24h / escalate
- proof_links: pointers to the data the agents consulted
Pre-fill 5 example entries from this case study: (1) Boost Concert-Pack offer to high-churn-risk Klang Valley subs, +RM 4.1M; (2) Add small-cell capacity at 14 Bukit Bintang sites ahead of F1, +RM 2.3M; (3) Decommission 24 northern Perak towers, RAN-share with peer, +RM 9.6M annualised; (4) Predictive maintenance on 18 diesel-genset towers, +RM 740k; (5) Escalate: 700MHz spectrum re-farm dispute with MCMC, RM 12M capex deferred.
Also output the portfolio tier snapshot the CEO sees above the list: ~1,820 over-performing clusters, ~11,200 on-target, ~980 under-performing (over-performing / on-target / under-performing clusters).
Step 5 of 6
Executive dashboard (Next.js + Tailwind)
Build a working executive dashboard for the National Mobile Operator Daily Decision List from Step 4. Use Next.js (App Router) + Tailwind + shadcn/ui. The user is the CEO.
Top of the page: portfolio tier snapshot card showing the clusters over / on / under count and the 24-hr P&L tally.
Below: the ranked Daily Decision List. Each card shows priority pill, decision, agents involved, RM-impact, one-line why, and three buttons:
- Approve (logs the approval, writes back to Chief of Staff, dispatches downstream actions)
- Defer 24h (snoozes; agent re-evaluates next cycle)
- Escalate (opens a thread to the CEO's chief of staff)
Right rail: agent activity feed showing which of the 5 specialists (Pricing Agent, Capacity Agent, Channel Agent, NetOps Agent, Cluster Agent) surfaced what overnight.
Mobile-responsive. Use Plus Jakarta Sans. Use a pink → orange brand gradient on primary actions. Output the full file tree and the code for: app/page.tsx, components/DecisionCard.tsx, components/TierSnapshot.tsx, lib/types.ts.
Step 6 of 6
Tools, actions, and approvals
Specify the tools and downstream actions each specialist agent in my National Mobile Operator system can call. The agents are: Pricing Agent, Capacity Agent, Channel Agent, NetOps Agent, Cluster Agent, plus Chief of Staff. Industry-relevant integrations: CRM + charging system APIs, RAN OSS APIs, MyEG/dealer portal APIs, MCMC e-filing, churn-risk model (in-house ML), GIS/tower-database.
For each agent, output an MCP-style tool registry in JSON, listing tools as:
- name
- description (1 line)
- input_schema (JSON schema)
- side_effects (read-only / advisory-write / commit-write / external-action)
- approval_required_from: one of "self" / "human" / "CEO"
Also define a router contract for Chief of Staff: which agent owns which decision class, what triggers escalation to a human, and how the agent learns from approve / defer / escalate outcomes. Output as a markdown spec ready to paste into a Claude project knowledge base or n8n workflow description.
Knowledge Graph & Memory
Backbone for your National Mobile Operator agentic system.
After Step 6 of the previous section you have agents and a dashboard. This section sets up the shared memory layer the agents read and write to every cycle — an Obsidian vault for human-readable notes and a Pinecone vector index for fast semantic retrieval. Every approved decision teaches the system how to be smarter tomorrow. The 5 prompts below are pre-filled for a Malaysian National Mobile Operator.
The shape: Obsidian markdown vault (human-readable, version-controlled in git) ↔ Embedding pipeline (Voyage 3 large or text-embedding-3-large, 512-token chunks) ↔ Pinecone hybrid index (one namespace per agent) ↔ MCP server (the agents’ only API into memory) ↔ Nightly outcome sync that stamps results back onto the original notes so the system learns. The result is a living knowledge graph that the agents and the executive share, in one place, version-controlled, fully auditable.
Step 1 of 5
Obsidian vault structure
You are setting up an Obsidian vault to act as the human-facing knowledge layer for a Malaysian National Mobile Operator multi-agent operating system. The 5 specialist agents are Pricing Agent, Capacity Agent, Channel Agent, NetOps Agent, Cluster Agent; the orchestrator is Chief of Staff. The CEO reads from this vault every morning.
Generate the vault structure:
- Folder hierarchy: /agents (one folder per agent code), /decisions, /playbooks, /learned-context, /regulatory, /operations, and the National Mobile Operator-specific entity folders for: cell sites, clusters, subscribers, dealers, spectrum bands.
- Frontmatter schemas (YAML) for each note type: decision, playbook, agent-writeback, entity-profile, regulatory-change, outcome.
- Tag taxonomy: priority::P0/P1/P2/Esc, agent::(Pricing Agent, Capacity Agent, Channel Agent, NetOps Agent, Cluster Agent), status::approved/deferred/escalated, outcome::win/loss/pending, regulator::(MCMC / PDPA / MyCERT / KPDN).
- Dataview queries the CEO uses at 06:00 daily: (a) today's Decision List, (b) this week's escalations, (c) agent-by-agent RM-impact tally, (d) decisions whose outcome::pending is more than 7 days old.
Output a clear directory tree + one fully written sample note per note type (6 notes) with realistic National Mobile Operator-flavoured content.
Step 2 of 5
Pinecone vector index schema
Design the Pinecone vector index that backs the agents' shared memory for the National Mobile Operator system from the previous prompts. The agents are Pricing Agent, Capacity Agent, Channel Agent, NetOps Agent, Cluster Agent (plus Chief of Staff orchestrator). Scale: national operator (8M subscribers, 14,000 towers).
Requirements:
- One Pinecone namespace per agent (Pricing Agent, Capacity Agent, Channel Agent, NetOps Agent, Cluster Agent) plus a shared 'orchestrator' namespace and a 'regulatory' namespace.
- Vector dimensions: 3072 (Voyage 3 large or OpenAI text-embedding-3-large). Justify whether to downscale to 1024 (matryoshka) for cost.
- Per-vector metadata fields: doc_id, agent (one of Pricing Agent, Capacity Agent, Channel Agent, NetOps Agent, Cluster Agent | Chief of Staff | regulatory), entity_type (one of cell sites, clusters, subscribers, dealers, spectrum bands), entity_id, ts (unix), decision_class (forecast | decision | playbook | outcome | regulatory-change), priority, rm_impact (signed float), outcome (win | loss | pending), tags (array).
- Hybrid retrieval: sparse + dense. Include BM25 for exact lookup of entity IDs (National Mobile Operator-specific codes — e.g., branch IDs, project codes, SKU codes, tower IDs).
- Settings: serverless vs pod-based — recommend one for national operator (8M subscribers, 14,000 towers). Justify replica count and metadata-index choice.
- Chunking: 512-token windows, 64-token overlap, but also one vector per H2/H3 section so the agents can cite a specific section back to the CEO.
Output as: (a) a Terraform module that provisions the index, (b) a Python pinecone-client setup script that creates the namespaces, (c) a JSON schema validator for the metadata fields, ready to enforce on every upsert.
Step 3 of 5
Embedding & ingestion pipeline
Build the embedding and ingestion pipeline that turns Obsidian markdown notes into Pinecone vectors for the National Mobile Operator agents (Pricing Agent, Capacity Agent, Channel Agent, NetOps Agent, Cluster Agent, Chief of Staff).
Pipeline:
1. File watcher on the vault folder (chokidar in Node or watchdog in Python) that fires on save and on git-pull.
2. Parse YAML frontmatter and markdown body via python-frontmatter or gray-matter.
3. Chunk body by H2/H3 boundaries AND by ~512-token windows with 64-token overlap. Preserve heading path as chunk.section_path metadata.
4. Embed via Voyage 3 large (or text-embedding-3-large) — async, batched at 100 items, retry with exponential backoff on 429/5xx.
5. Extract metadata: agent_namespace (from path /agents/<code>/...), entity links (parse [[wikilinks]] from body and map to entity_id), decision_class (from frontmatter), regulatory mentions (regex hit on MCMC / PDPA / MyCERT / KPDN), rm_impact (from frontmatter), outcome (from frontmatter).
6. Upsert with deterministic IDs: sha256(file_path + chunk_index). Delete-then-upsert on save to avoid stale chunks.
7. Write back to the note's frontmatter: pinecone_ids[], last_embedded_at, chunk_count. Commit back to git for auditability.
Deliverables:
- A Python repo (FastAPI + Pinecone client + Voyage client + python-frontmatter + watchdog) with a docker-compose.yml that starts the watcher and a small admin UI for the CEO's chief of staff to trigger re-embed on stale notes.
- An on-failure alerter that posts to Slack/Telegram if any sub-step errors out twice in a row.
Step 4 of 5
MCP server for agent queries
Build an MCP (Model Context Protocol) server that exposes the National Mobile Operator Obsidian vault + Pinecone index as queryable tools for the agents (Pricing Agent, Capacity Agent, Channel Agent, NetOps Agent, Cluster Agent) and Chief of Staff.
Expose these tools:
- search_memory(query, agent_namespace?, entity_type?, entity_id?, date_range?, top_k=10) — hybrid Pinecone retrieval; returns chunks with source-note paths, section_path, and frontmatter metadata.
- get_decision_history(entity_id, days=30) — returns every Daily Decision List entry that touched this cell sites or other entity.
- get_playbook(name) — returns the most up-to-date playbook for a named scenario. Known playbooks for this industry include: churn-save playbook, small-cell deployment playbook, RAN-share diligence.
- get_agent_writeback(agent_code, since) — returns recent forecasts/decisions written by one agent.
- get_outcome(decision_id) — returns the actual outcome of an approved decision; used by the nightly Chief of Staff retraining loop.
- write_note(path, frontmatter, body) — writes a new markdown note to the vault (triggers re-embedding via the Step-3 watcher).
- propose_playbook_update(playbook_name, diff, evidence_decision_ids) — drafts a markdown PR to the playbook with linked evidence.
Implement as a TypeScript MCP server using @modelcontextprotocol/sdk. Configure manifests for: (a) Claude Desktop, (b) Claude Code, (c) n8n's MCP node so the agents can call it as part of the cascade. Output the full source code + a 1-page how-to-install.
Step 5 of 5
Nightly knowledge-graph sync
Wire up the nightly knowledge-graph sync from production operations to the Obsidian vault and Pinecone for the National Mobile Operator multi-agent system (Pricing Agent, Capacity Agent, Channel Agent, NetOps Agent, Cluster Agent, Chief of Staff).
Each night at 02:00 MYT:
1. Pull yesterday's outcomes from production: for each Daily Decision List entry, fetch what the CEO actually approved / deferred / escalated, the realised RM-impact, and any downstream effect.
2. Stamp outcomes onto each decision note's frontmatter (outcome::win | loss | pending, actual_rm_impact, time_to_outcome).
3. Generate a 'daily writeback' note per agent (Pricing Agent, Capacity Agent, Channel Agent, NetOps Agent, Cluster Agent) summarising what it saw, what it recommended, what was approved, and the delta vs forecast. Save under /agents/<code>/writeback/YYYY-MM-DD.md.
4. For every new or updated note, the Step-3 pipeline re-embeds and upserts to Pinecone.
5. Run a "lessons learned" extractor: prompt the Chief of Staff model with the day's outcomes and ask for 3-5 playbook updates. Append as drafts to /playbooks/_drafts/ for CEO review.
6. Push a Slack/Telegram digest to the CEO's chief of staff: the top 5 lessons, plus any decisions stuck at outcome::pending for >7 days.
Deliverables: (a) an n8n workflow JSON, (b) a Claude Code skill, or (c) a Python cron job — pick the best fit for a national operator (8M subscribers, 14,000 towers) and explain why. Include error handling, retry, and a fail-open mode that alerts a human on any failure.
