Full Platform Roadmap

Decision Intelligence Platform
Complete Build Plan

Everything required to go from the current working system on the DGX to a fully licensed, production-grade multi-tenant product — all capabilities, all gaps, all costs, one picture.

190
Trusted books
Chunked, embedded, and retrieval-ready across 7 strategic schools
84,112
Searchable chunks
2.5GB local embedding index, cosine similarity retrieval
68
Cases generated
Real strategy outputs processed through the full pipeline
7-tier
Strategist architecture
Designed, schema-ready, profiling scenarios live — awaiting first enrollee

Live and operational

Corpus ingestion pipeline

Live

Book ingest → text extraction → chunking → trust classification → embedding. 298 books tracked, 190 trusted and embedded.

Semantic retrieval engine

Live

Cosine similarity over 84K chunks. Query-time embedding via qwen2.5:3b. Top-60 expansion, reranked to final-12 source pack.

GDELT live context injection

Live

Real-time geopolitical signals injected per case. Default-on. Non-fatal fallback if GDELT unavailable.

Local option generation

Live

qwen2.5:14b generates strategic options from retrieved context. Runs entirely on DGX — zero API cost.

Sonnet synthesis

Live

Anthropic Sonnet (customer key) synthesises final strategy output with source attribution and recommendations.

Queue-based job processing

Live

Cloudflare KV trigger → systemd queue watcher → pipeline → KV result. Browser polls every 8s. Event-driven, no polling loops.

Web interface + CRM

Live

visuals.professionalopinions.com.au. Scenario tester, 5 strategic modes, tension controls, tester enrolment. Attio CRM sync on registration.

Audience projection layer

Live

Segment-level heuristic audience responses. Scaffolded for future ABS/polling integration. Runs per case.

Attribution + compensation ledger

Live

Chunk-level influence tracking. Revenue split model: 30% strategist pool, distributed by influence weight × reputation multiplier.

Report rendering

Live

HTML, Markdown, JSON, and frontier report bundle. Export-ready artifacts per case.

Partial / in progress

Master strategist evaluation tier

Premium — ready, no enrollees

7-tier architecture designed. 10 profiling scenarios across 3 tiers operational. capture_deliberation.py and aggregate_strategist_profile.py built. Awaiting first strategist enrolment and session capture.

106 quarantined books

Partial

Content exists, not yet trusted. Phase 1-2-3 rehabilitation pipeline built. If rehabilitated: estimated +40,000–60,000 additional chunks, nearly doubling retrieval depth.

Live research bundle

Partial

build_research_bundle.py stores web summaries and notes per case. Not yet automated — web search/fetch done manually. Next step: auto-search + GPT synthesis.

Preference profile feedback loop

Partial

User preference profiles created on enrolment. Selection logging built (log_strategy_interaction.py, update_preference_weights.py). Not yet wired to option generation weighting.

Outcome feedback (30/60/90 day)

Partial

outcome_feedback.py built and schema-ready. Not yet integrated into the web interface or automated follow-up pipeline.

PDF export

Partial

render_capability_manual_pdf.py exists. Not yet integrated for per-case report export or canary-marked outbound briefing.

Not yet built (identified gaps)

ABS + polling data integration

Gap

Audience projection is heuristic-only. No ABS demographic data ingestion, no polling API connection, no sentiment trend ingestion. Required for quantitative projections.

Multi-tenancy + auth layer

Gap

No customer accounts, no isolated data namespaces, no per-customer API key vault. Single-operator system only. This is the primary blocker for licensing.

Token/cost dashboard (customer-facing)

Gap

No customer-visible usage or cost tracking. Required for licensed product where customers use their own Anthropic keys.

Strategist web portal

Gap

No web interface for premium tier strategists to review their profiles, see attribution, or track compensation. Currently CLI-only.

Voice transcription integration

Gap

Strategist profiling sessions require transcript file input. Voice-to-text not automated. Limits profiling to text-only sessions.

Multi-domain packaging

Gap

Platform architecture supports other decision domains beyond political strategy. No modular packaging system to deploy a second knowledgebase (e.g. insurance, finance, health policy).

Canary-marked briefing exports

Gap

Steganographic email fingerprinting for leak attribution exists in the workspace but is not integrated into the strategy report export pipeline.

The platform does not need to be complete before generating revenue. Twelve discrete milestones, each independently launchable and independently monetisable. Build in sequence — earlier milestones fund later ones and each one leaves the system better than before.

Key principle: No milestone waits for the next one to be started. Several tracks run in parallel — corpus work, strategist recruitment, and infrastructure build are all independent and can progress simultaneously.
M1 Week 1–2

Corpus rehabilitation

Run the Phase 1-2-3 rehabilitation pipeline on 106 quarantined books. Already scripted. Near-zero effort, high impact — expected +40–60K additional retrieval chunks, nearly doubling depth. Every case run after this is materially better.

$0
Cash cost
~130K chunks
After rehab
Unlocks: Immediately better outputs for all subsequent work. No customer needed to benefit.
M2 Week 2–4

Containerise + PDF export + canary reports

Dockerise all services. Integrate per-case PDF rendering. Add steganographic canary marking to all outbound briefings. The system now produces a professional, leak-attributable deliverable that looks like a real product.

$0
Cash cost (solo)
$7–13K
Contractor (AUD)
Unlocks: A professional PDF briefing you can physically hand to a client. Sets up all subsequent cloud deployment.
M3 Week 3–6 · First revenue

Pilot customer — single operator, manual billing

The system is already good enough to charge for. Identify one known person — political advisor, campaign director, consultancy — who has a live strategic problem. Run cases for them directly. Invoice manually. No licensing infrastructure required. This is the fastest possible path to paid validation.

$500–2K
Per case or retainer
Week 6+
Revenue starts
Unlocks: Paid feedback from a real user. Reveals what the product actually needs vs what you think it needs. Funds subsequent build work.
M4 Parallel — start Week 2

First master strategist — recruit and begin profiling

Start recruiting now. Profiling requires 4+ sessions over 4–6 weeks and cannot be compressed — you cannot start it later and have it ready sooner. This track runs in parallel with all infrastructure work. A single active strategist profile can be sold to the pilot customer as a premium add-on before multi-tenancy exists.

$2–10K
Session fees (AUD)
Week 8–12
Profile activates
Unlocks: Premium-tier output for the pilot customer. Immediately differentiates from any competing tool. The strategist compensation model becomes self-funding as soon as you have paying premium customers.
M5 Week 6–10

Automated live research + preference feedback loop

Upgrade build_research_bundle.py to auto-search and synthesise current context. Wire preference weight updates into option generation. The platform now learns each user's strategic style over time and removes manual research prep from each case.

$0
Cash cost (solo)
$5–10K
Contractor (AUD)
Unlocks: Faster turnaround per case. Qualitatively better outputs with current-context grounding. Can be positioned as a premium feature ("live intelligence layer").
M6 Week 8–14 · Customer 2 + 3

Auth layer + per-customer key vault

JWT auth, customer accounts in Postgres, AWS Secrets Manager for Anthropic key storage. This is the minimum viable multi-tenancy — enough to safely take a second and third customer without data bleed, even before the full customer interface is built. Manual onboarding, manual billing still acceptable at this stage.

$0
Cash cost (solo)
$11–19K
Contractor (AUD)
Unlocks: Customers 2 and 3. Revenue from 3 customers at $500–2K/mo begins to fund the rest of the build. You are no longer building speculatively.
M7 Week 12–18

AWS deployment + customer interface + token dashboard

ECS cluster, RDS Postgres multi-AZ, SQS queue. Customer-facing web portal with case history, usage dashboard, and token/cost visibility. Stripe billing. Self-service onboarding. This is the milestone that converts the system from an operator-managed service into a self-serve licensed product.

$200–400
AWS setup (USD)
$23–44K
Contractor (AUD)
Unlocks: General licensing. Customers self-onboard. Billing is automated. No manual intervention per customer. The platform is now a product.
M8 Parallel — Week 10–20

Strategist network at scale — 3–5 profiles + portal

Enrol 3–5 strategists across operative, academic, and specialist categories. Build the strategist web portal (view profile, attribution, compensation). Add voice transcription for session capture. Chunk-level attribution for higher compensation accuracy. Three active profiles is the minimum credible premium tier.

$6–30K
Session fees (AUD)
$1,500–3K/mo
Premium tier price
Unlocks: Premium licensing tier at 3–6× the base price. Strategist compensation becomes self-funding at ~5 premium customers. The network effect compounds — each additional strategist makes the tier more valuable.
M9 Week 20–26

Self-healing, hardening, load testing

Circuit breakers on all external APIs. Queue-based async throughout. PagerDuty alerting. Automated DB backup with tested restore. Load test at 10× expected peak. Security audit. This is the milestone that makes the platform genuinely mission-critical grade — required before selling to government or enterprise clients.

$500–2K
Audit/pentest cost
$10–18K
Contractor (AUD)
Unlocks: Government and enterprise contracts. Credible SLA commitments. Removes DGX single-point-of-failure risk via auto-failover configuration.
M10 Month 6–9

ABS demographic integration + polling data layer

Ingest ABS census and demographic data. Connect published polling (Newspoll, Essential, Resolve). Replace heuristic audience projections with population-backed estimates. This is a discrete data engineering module that can ship independently of everything else and be positioned as an "intelligence upgrade" to existing customers.

$500–5K/yr
Data licences
$13–24K
Contractor (AUD)
Unlocks: Quantitative audience projections. Shifts positioning from "advisory tool" to "political intelligence platform." Justifies a higher price point for all tiers and opens government contracts requiring empirical grounding.
M11 Month 8–12

Modular knowledgebase + second domain

Abstract the political strategy corpus and domain prompts into a pluggable module. Deploy a second domain knowledgebase (e.g. insurance risk strategy, financial services, health policy). Each new domain is a new product line on the same infrastructure, with its own corpus, its own strategist network, and its own pricing.

$32–60K
Contractor (AUD)
New market
Each domain
Unlocks: A second revenue stream on the same infrastructure. Given Doron's background in insurance and behavioural economics, an insurance/financial services domain is the natural second product.
M12 Month 12+

White-label enterprise deployment

Custom domain, custom interface, proprietary knowledgebase from client's own documents. Dedicated instance. One enterprise client at this tier covers the cost of 20+ base-tier customers. Target: major consultancies, political parties, government departments, financial institutions with proprietary research they want to make queryable.

$10–30K/mo
Enterprise price
$10–18K
Contractor to build
Unlocks: The highest-value contract type. A single enterprise client at $20K/mo generates $240K/yr — more than covering the entire platform build cost in one relationship.

Build cost and revenue unlock per milestone

Solo costs are near-zero cash (your time). Contractor costs are AUD at $150–250/hr senior DevOps/fullstack. Strategist session fees are additional. Running infrastructure: $165–1,370 USD/month depending on scale (see Deployment page).

MilestoneWhenSolo cashContractor (AUD)Revenue unlocked
M1 · Corpus rehabWk 1–2$0$0Better outputs — no direct revenue yet
M2 · Containerise + PDF + canaryWk 2–4$0$7–13KProfessional deliverable; fundable as consulting
M3 · First pilot customerWk 3–6$0$0 extra$500–2,000/mo first revenue
M4 · First strategist (parallel)Wk 2–12$2–10K session fees$3–5K facilitationPremium add-on to pilot customer
M5 · Auto research + feedback loopWk 6–10$0$5–10KQuality uplift; premium feature positioning
M6 · Auth + key vault (min. multi-tenancy)Wk 8–14$0$11–19KCustomers 2 + 3: +$1–4K/mo
M7 · AWS + customer UI + billingWk 12–18$200–400 AWS$23–44KGeneral licensing: self-serve onboarding
M8 · Strategist network (parallel)Wk 10–20$6–30K session fees$18–31KPremium tier: $1,500–3,000/mo per customer
M9 · Self-healing + hardeningWk 20–26$500–2K audit$10–18KGovernment + enterprise contracts unlocked
M10 · ABS + polling dataMo 6–9$500–5K/yr data$13–24KHigher price justification; govt contracts
M11 · Second domainMo 8–12$0$32–60KNew market: insurance / finance / health
M12 · White-label enterpriseMo 12+$0$10–18K$10–30K/mo per enterprise client
Full platform (M1–M12)24–36 months~$9–47K AUD~$132–242K AUDMulti-domain licensed product + enterprise tier
To first revenue (M1–M3)6 weeks~$0$7–13K$500–2,000/mo pilot revenue
To licensed product (M1–M7)18–24 weeks~$200–2,400$46–86KGeneral availability, self-serve, automated billing

What runs in parallel

Infrastructure track

M2 → M6 → M7 → M9

Sequential build. Each milestone depends on the previous. This is the critical path. Cannot be parallelised internally.

Strategist track

M4 → M8 (parallel)

Completely independent of infrastructure. Start recruiting Week 2. Profiling sessions run while engineers build auth and AWS. Profile activates Week 8–12 regardless of infrastructure state.

Corpus + quality track

M1 → M5 (parallel)

Corpus rehab (M1) is immediate. Automated research and preference feedback (M5) can follow independently. Both improve output quality for any customer at any point.

Revenue ramp by milestone

Milestone reachedTimelineCustomersMonthly revenue rangeGross margin
M3 — First pilotWeek 61$500–2,000/mo~90%+
M4 — Premium add-onWeek 121 premium$1,500–5,000/mo~85%
M6 — Customers 2+3Week 163$3,000–9,000/mo~90%
M7 — General licensingMonth 65–15$5,000–30,000/mo~94%
M8 — Premium network liveMonth 6–85 base + 3 premium$10,000–50,000/mo~93%
M10 — Empirical layerMonth 9–1210–30$15,000–75,000/mo~95%
M12 — EnterpriseMonth 12+1 enterprise + base$30,000–100,000/mo~95%
Break-even: If M1–M6 are built solo (zero cash cost), first revenue arrives at Week 6. Three customers by Week 16 covers all running infrastructure costs. Contractor investment ($46–86K for M1–M7) is recovered within 3–6 months of reaching M7 at 10+ customers.

Do first — blocks everything

M1: Corpus rehab (Week 1)

Immediate

Zero cost. Massive quality improvement. Do this before anything else — every subsequent case benefits.

M4: Start strategist recruitment (Week 2)

Cannot defer

Profiling takes 4–6 weeks minimum and cannot be compressed. Every week you delay recruiting is a week later the premium tier activates. Start now, run in parallel.

M2: Containerise (Week 2–4)

Infrastructure foundation

Nothing can be reliably cloud-deployed without Docker. All subsequent infrastructure milestones depend on this.

M3: First customer (Week 3–6)

Revenue + feedback

Real customer feedback before M6 and M7 will materially change what you build. Do not over-engineer before you have validated what customers actually want.

Key risks

Strategist quality and willingness

High risk

M4 and M8 are relationship challenges, not engineering ones. The premium tier is only as strong as the strategists who agree to participate and complete profiling. Start early, expect slow recruitment.

Skipping M3 and building M7 first

Critical failure mode

The most likely mistake: building the full licensed platform before validating that anyone will pay. Get one customer at Week 6. Use that revenue and feedback to inform M7.

ABS/polling data complexity (M10)

Medium risk

Real data sources are always messier than expected. M10 is Phase 4 — do not let it block M7. It can be launched independently as an intelligence upgrade after the platform is live.

DGX single point of failure

Medium risk

Until M9 (hardening), a DGX failure takes all inference offline. Acceptable for pilot customers; not for enterprise. Colocation or cloud GPU fallback added during M9.