Moving the Malaysian national utility from human-prompted AI assistants to a coordinated team of agents that runs generation, transmission and distribution on a daily schedule and delivers a ranked decision list to the CEO every morning.
Prepared forBoard & C-Suite
FormatOnline Reference
Case StudyNational Utility · Generation · Transmission · Distribution · Malaysia
Your AI investment will not pay back until the AI stops waiting to be asked.
Most Malaysian utility 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 utility's data on a fixed daily schedule, weighs the trade-offs (heatwave load spikes, fuel-cost swings, ST tariff petitions, NIOSH high-voltage safety, renewable intermittency), 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 substation, feeder, generator, crew, and capex line — 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 — Malaysian national electricity utility
A Malaysian utility where every variable moves every minute. The ideal stress-test.
A national utility in Malaysia compresses every operational discipline of a continental enterprise into a single grid-day: load forecasting against industrial demand and weather, fuel-cost optimisation across gas, coal, hydro and solar, capex prioritisation under ST scrutiny, transmission and distribution reliability across 9.2M customers, field-crew rostering under NIOSH high-voltage rules, and renewable intermittency that swings minute by minute. Multiplied across 28,000 MW of installed capacity from Bakun to Pengerang — no human team can hold the full state of the grid in working memory.
28k MW
Installed capacity — gas, coal, hydro & solar across the national grid
Suruhanjaya Tenaga oversight · tariff petitions · Petronas IFC on gas
The five operational tensions the team of agents must hold simultaneously
Tension 1
Load vs. Reserve Margin
Run lean on reserves and risk load-shed, or hold capacity and burn fuel for nothing?
Tension 2
Fuel Cost vs. Tariff
Dispatch the cheapest fuel mix today, or smooth the cost curve into the next ST petition?
Tension 3
Capex vs. Reliability
Defer a substation refurbishment, or accept the SAIDI penalty when it trips?
Tension 4
Renewables vs. Baseload
Lean into solar & hydro intermittency, or keep gas peakers warm as insurance?
Tension 5
Scale vs. Decommission
Push a new Pengerang substation, or decommission a sub-scale Sabah asset?
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 substation's telemetry every minute. The chips at the bottom of each card show the kind of expertise the agent embodies — detailed on the next slide.
Load Agent
Demand & Load Pricing
The Load Forecaster
Watches: hourly grid load, industrial customer demand, MET Malaysia forecast, solar/wind output, festive-week peak patterns, time-of-use tariff windows.
Decides: the 48-hour load forecast and the time-of-use pricing signal everyone else dispatches against.
Load forecastingToU pricing
Fuel Agent
Fuel & Supply Chain
The Upstream Planner
Watches: gas & coal procurement contracts, Petronas IFC schedules, hydro reservoir levels at Bakun & Kenyir, fuel logistics to power stations, storage inventory.
Decides: the least-cost fuel mix and dispatch order; auto-flags procurement actions within policy.
Decides: classifies every station/substation as Overperform / On-Target / Underperform vs. peer cohort, and triggers the right capex action.
Capex prioritisationPeer benchmarking
Chief of Staff
Chief of Staff
The Synthesis Layer
Watches: what all five specialists are recommending, plus the P&L, fuel-cost variance and ST regulatory engagements.
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.
"For the next 48 hours, here is the load curve at each substation, the reserve margin, and the time-of-use signal everyone else should dispatch against."
Fuel AgentFuel & Supply ChainThe Upstream Planner
Fuel procurement & dispatchGas, coal, hydro, solar — least-cost merit order against the load forecast.
"Here is the cheapest legal crew roster that covers planned maintenance and emergency cover for the next 14 days — and the regions where coverage is at risk."
Peer cohort matchingGroups stations & substations by region, fuel type, vintage, demand profile — apples to apples.
Composite performance scoringCapacity factor, heat rate, SAIDI/SAIFI contribution, opex per MW — rolled into one score.
Tier classificationOverperform · On-Target · Underperform vs. true peers.
Capex prioritisationRanks capex projects by reliability uplift & demand-growth fit.
Decommissioning & renewable-siting diligenceSurfaces the evidence pack for both decisions.
Network / portfolio strategist · capex analyst · planning lead with causal / experimentation background.
"Across the national fleet, here are the Overperformers to replicate, the Underperformers to refurbish or decommission, and the capex projects that will move the SAIDI/SAIFI number most."
Chief of StaffChief of StaffThe Synthesis Layer
Multi-criteria decision rankingWeighs RM-impact, confidence, risk, ST-regulatory exposure, strategic fit.
Conflict reconciliationWhen Load Agent wants peakers online but Crew Agent can't crew the safety standby — 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 — Load Agent's load forecast is the input to Fuel Agent, Crew Agent, Asset Agent, and Network Agent. The Orchestrator consumes all five and emits one artefact: a ranked decision list for the executive.
Layer 1 · Raw Signals (refreshed every minute to 24 hours)
External
MET Malaysia · solar & wind forecast · ST tariff filings · Petronas IFC gas nominations
External
Industrial customer load schedules · Raya / CNY / Deepavali calendar · heatwave index
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.
FromLoad Agent · Load Forecaster
→tells
ToFuel Agent · Upstream Planner
"Heatwave forecast Friday + low solar generation = load +6%. Bring 2 peaking gensets online 17:00–22:00 — and tell me what that costs in fuel before I commit."
FromAsset Agent · Reliability Manager
→tells
ToCrew Agent · Field Crew Planner
"11 transmission transformers in the Klang Valley loop are trending toward failure on DGA. Crews needed Friday 22:00–05:00 — service window before Aidiladha shutdown."
FromCrew Agent · Field Crew Planner
→tells
ToAsset Agent · Reliability Manager
"HV-certified crew confirmed for 7 of 11 transformers — two crews need cross-state mobilisation from Penang and Johor. Either we sequence the remaining 4 across two nights, or you escalate for contractor cover."
FromAll five specialists
→feed
ToNetwork Agent · Network Strategist
"Sabah region is bottom-quartile for 9 months running; demand growth -2%. Defer RM 180M substation capex; reallocate to Pengerang where industrial demand is +12% on the petrochem build-out."
FromFuel Agent · Upstream Planner
→tells
ToLoad Agent · Load Forecaster
"Hydro at Bakun firmed; lowest-cost dispatch tonight 00:00–05:00. Pre-dispatch the overnight low-demand window — meaningful fuel savings if you can shape demand-response on the top-20 industrial accounts."
FromChief of Staff · Chief of Staff
↺loops to
ToAll agents
"Last quarter's load-shifting playbook saved a meaningful 7-figure fuel bill. Continue prioritising Network Agent's bottom-decile capex flags; the CEO's revealed risk appetite has shifted toward reliability over deferral — recalibrate."
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 (SCADA / EMS, dispatch engine, HRIS, ERP, capex workflow).
23:59 · Outcome data flows back as ground truth. Load forecasts, fuel-cost variance and capex calls 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 — Network Agent only triggers a capex or tier action when matched-peer evidence says it has worked 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 load, fuel, crew, asset reliability and network portfolio. The CEO judges the trade-off — the answer is already assembled.
RunFri · 22 May 2026 · 04:00 MYT
Generated byChief of Staff · Orchestrator
Scope28k MW capacity · 9.2M customers · national grid
Load Agent: load forecast +6% on a heatwave coupled with low solar; without peakers, load-shed in Selangor is likely. Fuel Agent confirms cheapest peaker dispatch given current gas price.
+RM 8.4M avoided load-shed penaltyHigh confidence
Load Agent · Fuel Agent
P0Approve
2
Predictive maintenance on 11 transmission transformers in the Klang Valley loop — service before Aidiladha
Asset Agent: dissolved-gas analysis trending toward failure on 11 transformers. Service window opens 22:00–05:00 ahead of the long-weekend shutdown. Crew Agent confirms HV-certified crews for 7 of 11; two crews mobilising cross-state.
+RM 4.2M avoided outageHigh confidence
Asset Agent · Crew Agent
P0Approve
3
Portfolio action — defer the Sabah substation capex by 9 months · reallocate to Pengerang where industrial demand is +12%
Network Agent: Sabah region in the bottom quartile for 9 months running; lower-than-forecast industrial demand. Defer RM 180M capex; reallocate to Pengerang petrochem corridor. Fuel Agent validates fuel-supply readiness on the Pengerang reallocation.
Chief of Staff: tariff petition with Suruhanjaya Tenaga is pending the next council meeting. Decision affects materially the next regulatory cycle; needs CEO-level engagement, not an automated submission.
−RM 14M if deniedIf unresolved before next ST council
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 substation operator to the full operating model
Four phases. Hire as you go. Right-size for your maturity.
Utilities 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 utilities should start at Phase 1 — a single agent in one substation operator's pocket.
Phase 01 · AssistOperator Co-pilotMonths 0–2
One agent in the substation / plant operator's pocket. A daily action checklist on their phone — not a dashboard, not a report.
Entry bar — your starting maturity
Connected SCADA plus a few asset-condition feeds. Control room runs shift comms over radio and WhatsApp.
Roll out to 24 substation operators in the Klang Valley; daily 06:00 priority brief on the phone. Regional manager sees per-substation completion rates roll up weekly.
Build team2 people
Phase 02 · CrawlFoundation PilotMonths 2–6
One specialist agent. The System Operator desk. Prove the daily-push cadence works before scaling anything.
Entry bar — your starting maturity
Phase 1 in production at a handful of substations. Operator teams have a daily completion habit.
Agents activated
Load AgentFuel AgentCrew AgentAsset AgentNetwork AgentChief of Staff
Mode: Read-only / advisory. Agent recommends; the System Operator decides and dispatches manually.
What the CEO sees
A daily insights email at 06:00 MYT: 1–2 surfaced load anomalies and reserve-margin risk flags.
Illustrative first project
Load Agent load-forecast advisor for the System Operator desk. Forecast scored every hour against SCADA actuals.
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
Load AgentFuel AgentAsset AgentCrew AgentNetwork AgentChief of Staff
A weekly cross-agent scorecard plus same-day escalations when agents disagree or reserve-margin thresholds are crossed.
Illustrative first project
Load-to-asset loop on the top 30 substations across the Klang Valley loop. Cascade goes live: load → fuel → outage scheduling 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
Load AgentFuel AgentCrew AgentAsset AgentNetwork 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 grid operating system across 28k MW of capacity and 9.2M customers. 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 — load, fuel, crews, assets, or network portfolio. 90-day pilot, one Malaysian region or substation loop.
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 Utility 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 Utility 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 Utility business.
Archetype: A Malaysian national utility — 28k MW capacity (gas, coal, hydro, solar), 9.2M customers, generation + transmission + distribution, ST-regulated tariffs.
Build a team of 5 specialist sub-agents + 1 master orchestrator named Chief of Staff:
- Load Agent — Demand & Load Pricing Agent: The Load Forecaster
- Fuel Agent — Fuel & Supply Chain Agent: The Upstream Planner
- Crew Agent — Operator Workforce Agent: The Field Crew Planner
- Asset Agent — Asset & Predictive Maintenance Agent: The Reliability Manager
- Network Agent — Asset Portfolio Performance 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: Load vs Reserve margin, Fuel-cost vs Tariff, Capex vs Reliability, Renewables vs Baseload, 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 Utility multi-agent system you just designed (agents: Load Agent, Fuel Agent, Crew Agent, Asset Agent, Network Agent, Chief of Staff).
Real-time signals available in this industry: SCADA + EMS load telemetry, weather forecasts, industrial-customer schedules, hydro reservoir levels, fuel commodity prices (gas, coal), substation/transformer DGA, customer outage reports, ST tariff filings.
Regulatory and compliance feeds we must honour: ST (Suruhanjaya Tenaga), DOSH/NIOSH, Petronas IFC (gas), Akta Pekalangan Air, MOSTI.
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 Utility multi-agent system (agents: Load Agent, Fuel Agent, Crew Agent, Asset Agent, Network Agent, master: Chief of Staff).
Daily flow: Load Agent → Fuel Agent → Crew Agent → Asset Agent → Network 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 Utility 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 Utility 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 Load Agent, Fuel Agent, Crew Agent, Asset Agent, Network 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) Bring 2 peaking gensets online 17:00–22:00 Friday, +RM 8.4M avoided load-shed; (2) Predictive maintenance on 11 Klang Valley transmission transformers, +RM 4.2M; (3) Defer Sabah substation capex by 9 months, reallocate to Pengerang, +RM 6.1M; (4) Pre-dispatch Bakun hydro overnight low-demand, +RM 1.8M fuel savings; (5) Escalate ST tariff petition pending CEO engagement, RM 14M revenue exposure.
Also output the portfolio tier snapshot the CEO sees above the list: ~4 over-performing regions, ~8 on-target, ~2 under-performing (over-performing / on-target / under-performing regions).
Step 5 of 6
Executive dashboard (Next.js + Tailwind)
Build a working executive dashboard for the National Utility 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 regions 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 (Load Agent, Fuel Agent, Crew Agent, Asset Agent, Network 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 Utility system can call. The agents are: Load Agent, Fuel Agent, Crew Agent, Asset Agent, Network Agent, plus Chief of Staff. Industry-relevant integrations: SCADA/EMS read-only API, fuel commodity feeds (CME/ICE), weather services (MetMalaysia, ECMWF), DGA test results, asset management (Maximo/SAP-PM), customer outage system, ST filing portal.
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 Utility 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 Utility.
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 Utility multi-agent operating system. The 5 specialist agents are Load Agent, Fuel Agent, Crew Agent, Asset Agent, Network 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 Utility-specific entity folders for: substations, generators, transmission lines, customers, fuel contracts.
- Frontmatter schemas (YAML) for each note type: decision, playbook, agent-writeback, entity-profile, regulatory-change, outcome.
- Tag taxonomy: priority::P0/P1/P2/Esc, agent::(Load Agent, Fuel Agent, Crew Agent, Asset Agent, Network Agent), status::approved/deferred/escalated, outcome::win/loss/pending, regulator::(ST / DOSH / Petronas IFC / MOSTI).
- 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 Utility-flavoured content.
Step 2 of 5
Pinecone vector index schema
Design the Pinecone vector index that backs the agents' shared memory for the National Utility system from the previous prompts. The agents are Load Agent, Fuel Agent, Crew Agent, Asset Agent, Network Agent (plus Chief of Staff orchestrator). Scale: national utility (28k MW, 9.2M customers).
Requirements:
- One Pinecone namespace per agent (Load Agent, Fuel Agent, Crew Agent, Asset Agent, Network 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 Load Agent, Fuel Agent, Crew Agent, Asset Agent, Network Agent | Chief of Staff | regulatory), entity_type (one of substations, generators, transmission lines, customers, fuel contracts), 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 Utility-specific codes — e.g., branch IDs, project codes, SKU codes, tower IDs).
- Settings: serverless vs pod-based — recommend one for national utility (28k MW, 9.2M customers). 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 Utility agents (Load Agent, Fuel Agent, Crew Agent, Asset Agent, Network 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 ST / DOSH / Petronas IFC / MOSTI), 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 Utility Obsidian vault + Pinecone index as queryable tools for the agents (Load Agent, Fuel Agent, Crew Agent, Asset Agent, Network 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 substations or other entity.
- get_playbook(name) — returns the most up-to-date playbook for a named scenario. Known playbooks for this industry include: peak-load dispatch playbook, transformer-health playbook, tariff-petition playbook.
- 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 Utility multi-agent system (Load Agent, Fuel Agent, Crew Agent, Asset Agent, Network 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 (Load Agent, Fuel Agent, Crew Agent, Asset Agent, Network 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 utility (28k MW, 9.2M customers) and explain why. Include error handling, retry, and a fail-open mode that alerts a human on any failure.
