Nigel J. CaseyBA, BSc, MSc
Free diagnostic

An Operating Company Built in Eight Weeks

0 AI Specialists.
One operator. One Brain.

I built this in under 90 days. No co-founder, no engineering hires. 146 AI Specialists, each one a specialist role I designed, scoped and gave a voice, then wired into how the company runs. Some run on their own. A Brain agent audits the company every night, and production crons handle delivery, compliance and content dispatch without me touching them. The rest I direct. They execute on demand, at a standard and speed a much larger team would need to match. One operator, one Collective Brain, 146 specialised roles. You'll find every one below: name, role, collaborators, and the hours each saves me. The list grows as the operation grows.

Take the free diagnostic →The Build

Reading time: 6 minutes. The full inventory takes longer.

Built April 2026. Live and producing work daily. The numbers below update as new AI Specialists ship.

Build log
Every build that has shipped, oldest first. The operating company now stands at 146 specialist roles, some running autonomously and the rest executing on demand, all designed and onboarded by one operator.
  • 2 MarThe EFO platform10 agents
  • 3 MarThe course-production pipeline7 agents
  • 3 MarThe coaching + personalisation pipeline5 agents
  • 3 MarThe cross-cutting copywriters2 agents
  • 3 MarThe community + support pair2 agents
  • MarThe in-app practice surfaces3 agents
  • MarThe email-delivery runtime1 agents
  • MarThe customer-touchpoint runtime3 agents
  • MarThe assessment + placement engine6 agents
  • MarThe blog-rendering pipeline6 agents
  • MarThe trial + demo runtime3 agents
  • 17 MarThe daily content engine8 agents
  • 7 AprThe Fluency Clinic6 agents
  • 8 AprThe eduQua dossier10 agents
  • 12 AprTraffic recon & capture11 agents
  • AprThe branded transformation dashboard1 agents
  • AprThe productised Council8 agents
  • AprThe live QMS dashboard1 agents
  • AprThe conversion runtime4 agents
  • AprThe production tooling2 agents
  • AprThe Brain MCP server1 agents
  • 19 AprThe Brain Health agent1 agents
  • 19 AprThe Vault6 agents
  • 20 AprThe accounting pipeline6 agents
  • 26 AprThe internal Strategic Council8 agents
  • 26 AprThe compliance layer3 agents
  • 27 AprThe conversion engine8 agents
  • 30 AprThe Behind-the-Build feed2 agents
  • 5 MayBrain v2 financial reconstruction6 agents
  • 11 MayThe Conversation Pack engine3 agents
  • 13 MayBrain security + financial isolation2 agents
  • 17 MayClinic demos + auto blog analysis3 agents
  • 19 MayThe agent persona system3 agents
  • 20 MayThe talking-head video pipeline2 agents
  • 21 MayThe operating-company showcase2 agents
  • 22 MayThe organisation cartography system7 agents
  • 24 MayThe agent voice standard2 agents
  • 26 MayThe asset-production platform3 agents
  • 27 MayWord-synced agent-video captions1 agents
  • 28 MayThe founder walkthrough1 agents
  • 28 MayThe agent conversation runtime2 agents
  • 28 MayThe Brain Infrastructure read/write split4 agents
  • 28 MaySitewide roster propagationinfra
  • 28 MayThe 23:00 agent, hardenedinfra
  • 28 MayThe content-engine protective layerinfra
  • 29 MayThe Phase 2 conversational-avatars arc3 agents
  • 5 JunThe Council ↔ Dashboard integrationinfra
  • 5 JunMobile-first media discipline on the public rosterinfra
  • 6 JunThe product catalogueinfra
  • 7 JunThe self-hosted Studio recorderinfra
  • 10 JunEFO Command: the admin theme + Presentation Modeinfra
TodayTotal team146
0
AI Specialists
0
Departments
0
Divisions
~0
Human hours displaced
1
Operator (Nigel)

Human hours displaced is the sum of every build below, each valued at the human time a competent team would have spent to build and run it. Conservative by design, and auditable build by build in the log.

01 · The thesis

I transformed my entire business with AI in under 90 days.

I believe in a world where every ambitious person can operate beyond their human limits, through a human-led, AI-amplified intelligence that is grown from within, uniquely theirs, that they fully own, and that makes previously impossible outcomes inevitable.

Most business owners already know they should be doing something with AI. The problem is that almost everything they're shown is either too generic to matter, or too extreme to take seriously. On the one hand, there is lots of hype about prompts, chatbots, "ten AI tools every business needs." On the other, six-figure eighteen-month transformations that expect you to change your business model and rebrand around AI.

This is exactly what inspired me to build the Octopus Brain for my business.

Nigel Casey · Torricella, Ticino · Founder, Digital Professionals Academy Sagl

02 · The architecture

The Octopus Brain.
Not a swarm of bots.

A business architecture where a human Central Intelligence provides the vision and strategic gatekeeping, while a network of specialised AI Peripheral Intelligences, like the tentacles of an octopus, handles the local execution.

An octopus has one central brain and eight peripheral brains, one in each tentacle. The central brain coordinates identity, intention and direction. The tentacles execute, autonomously, with their own local intelligence. The whole organism is one coordinated being.

That is the architecture under everything in this operation. The Central Intelligence is one human (me) plus the Collective Brain. The Brain is the persistent memory that holds identity, principles, voice, and ecosystem context. The Peripheral Intelligences are 146 specialist roles across 4 divisions and 18 departments, each with its own scope, mandate and voice. A handful run unattended on schedules: the nightly Brain agent, the production crons, the compliance crons. The rest I convene when the work calls for them. Either way, none of them sets its own direction. That stays with the Central Intelligence.

The connective tissue is the Voice Bible, the strategic principles, the writer/reviewer separation rule, and the schemas. That is what lets the peripherals coordinate without being micromanaged. Neither tries to be the other. I lead. The AI executes.

This is what turns AI from experimental expense into structural multiplier. It is what makes previously impossible outcomes inevitable.

CentralIntelligenceEnglishFluency.OnlineDIVISION 01MyBusinessAcceleratorDIVISION 02Founder OperationsDIVISION 03DPA Sagl GroupDIVISION 04PERIPHERAL INTELLIGENCES · 18 DEPARTMENTS · 146 AI SPECIALISTS
The Octopus Principle is Strategic Principle #4 in the operating Brain, dated 15 April 2026: "a central intelligence coordinates identity and intention; peripheral intelligences handle local execution; neither tries to be the other." Every project in this operation is a manifestation of it. The eduQua dossier is a 9-tentacle deployment. The daily content engine is an 8-tentacle deployment. The Strategic Council is a 9-tentacle deployment. This is what AI looks like when it is engineered, not accumulated.

03 · The build

Eight weeks. One leader.

No team, no co-founder, no engineering hires. The dates are real, the artefacts are live, the cost was my time, my intellectual input, my vision and the cost of the Techstack I used to build it. Each row below is a project that is currently producing work in production.

2 Mar~1,200 hrs
The EFO platform
The app learners log into. Ten runtime agents serve traffic — voice lines, fluency scores, community spotlights — each with its own credit logic, rate limits and refunds.
3 Mar~600 hrs
The course-production pipeline
Seven agents turn one topic, CEFR level and pathway into a complete pedagogical package: structure, lesson grids, scripts, dialogues, assessments and QA.
3 Mar~400 hrs
The coaching + personalisation pipeline
Five agents turn raw learner activity into a personalised plan and a coaching narrative: profile, personalise, then review progress.
3 Mar~120 hrs
The cross-cutting copywriters
Two general-purpose marketing agents any other project can call when it needs copy in the EFO brand voice.
3 Mar~120 hrs
The community + support pair
Two agents: an inward briefing on what is happening in the community, and outward spotlights and replies. Both in Nigel's voice, neither sends without his review.
Mar~200 hrs
The in-app practice surfaces
Three more production agents inside the app — practice, drill and push — serving learners every day.
Mar~60 hrs
The email-delivery runtime
The runtime that pairs AI-drafted email content with Resend delivery.
Mar~150 hrs
The customer-touchpoint runtime
Three production agents handling the actual delivery of customer-facing support and welcome messages.
Mar~500 hrs
The assessment + placement engine
Six agents run in sequence when a candidate hits the assessment to produce a CEFR-aligned result. The gate every paying learner passes through.
Mar~300 hrs
The blog-rendering pipeline
Turns raw markdown into a fully shipped post: hero image, audio narration, floating bubble, OG image and learner-enrichment data.
Mar~180 hrs
The trial + demo runtime
The unauthenticated trial flow: own rate limits, self-contained, ending in a trial report. The surface every prospect touches before they assess.
17 Mar~800 hrs
The daily content engine
Eight agents shipping a blog post and four matched social posts a day, plus the Behind the Build stream — seven posts and twenty-eight socials a week, every week.
7 Apr~500 hrs
The Fluency Clinic
Six agent stacks running the premium Clinic in parallel: prep packs before, the recording flow during, the assets that ship after. Bilingual EN/IT throughout.
8 Apr~900 hrs
The eduQua dossier
A complete eduQua:2021 quality-management documentation suite, built in three weeks. A real institution would budget six to twelve months and a five-figure engagement.
12 Apr~600 hrs
Traffic recon & capture
Eleven agents in a strict SEO and AI-search pipeline. Adding a new target is a content-only task for the writers; the engineer only touches code for new features.
Apr~120 hrs
The branded transformation dashboard
One agent: a prospect submits a nine-question quiz and their URL; it fetches their site, applies their brand, and generates a personalised AI-transformation report.
Apr~300 hrs
The productised Council
The same eight Council agents, productised as a paid customer-facing assessment. We sell the council we use ourselves.
Apr~150 hrs
The live QMS dashboard
The live admin surfaces that turn the eduQua dossier into usable dashboards: corporate, documents, learners, quality and satisfaction.
Apr~250 hrs
The conversion runtime
Four production agents that run when a prospect hits the funnel — the implementation of the conversion spec.
Apr~150 hrs
The production tooling
Python build pipelines, not LLM agents, that turn agent-generated content into shippable PDFs and slides.
Apr~120 hrs
The Brain MCP server
Exposes the Collective Brain as a remote tool server over Tailscale, so any MCP client can consult it from anywhere — not only a session opened in the Brain folder.
19 Apr~100 hrs
The Brain Health agent
The Brain's immune system. Runs nightly at 23:00, audits pending updates, executes overnight writes and files a daily report — catching drift before it compounds.
19 Apr~700 hrs
The Vault
A Swiss recovery-grade financial-intelligence layer: three AI advisors plus a Creditor Claim Evaluator and subsystems. Decision support under financial constraint, not bookkeeping.
20 Apr~600 hrs
The accounting pipeline
A full double-entry pipeline scaffolded in one session: five source types into a routing engine, three-tier FX, validated entries against a 29-account chart. 2023 reconstructed in two days, zero unclassified.
26 Apr~300 hrs
The internal Strategic Council
The eight Council agents operating internally, used by Nigel on his own decisions across the ecosystem. This was the prototype; the MBA product was the lift.
26 Apr~200 hrs
The compliance layer
Three cron agents that turn the privacy policy into behaviour: audio-retention purge by article, lifecycle crons and client-error reporting. Retry-safe and secret-gated.
27 Apr~400 hrs
The conversion engine
Eight agents on five named levers — dashboard visibility, ad creative, diagnostic pre-qualification, show-up rate and dignified deflection — targeting consistent MASTERY enrolment month after month.
30 Apr~200 hrs
The Behind-the-Build feed
The public build feed and full /build post rendering: audio narration, three-language analysis and learning materials on every story.
5 May~700 hrs
Brain v2 financial reconstruction
2023 reconciled to the signed bilancio to the centime, and a full 2024 reconstruction from Stripe, PayPal, bank and payroll, with live P&L and balance-sheet pages.
11 May~400 hrs
The Conversation Pack engine
Personalised pack generation on Sophie's voice: key-phrase audio, a 'pack from notes' path, and re-takeable, ad-hoc diagnostics feeding each pack.
13 May~300 hrs
Brain security + financial isolation
MFA/AAL2 on the Brain, the financial brain moved to a dedicated allow-listed Supabase project, and full-funnel diagnostic visibility with a Loom review queue.
17 May~400 hrs
Clinic demos + auto blog analysis
Sophie clinic demos and a clinic library, automatic three-language blog analysis (vocabulary, grammar, comprehension), and assessment form-variant assignment.
19 May~500 hrs
The agent persona system
Portrait-first identity locking with Nano Banana Pro, locked agent-group ensembles and batch persona invention — the system that gives every specialist a consistent face.
20 May~400 hrs
The talking-head video pipeline
A HeyGen Avatar IV pipeline and team-card video studio that turn any specialist's portrait and script into a spoken introduction.
21 May~400 hrs
The operating-company showcase
The public /team and /agents pages: the live roster, the Strategic Council in their own words, today's specialist, and this build log.
22 May~150 hrs
The organisation cartography system
A seven-agent meta-team that maps the whole company to itself across six dimensions, registry, competency, consultation, accountability, work medium and customer journey, kept current as the org grows, with a value-stream overlay that groups every specialist by the outcome it serves.
24 May~160 hrs
The agent voice standard
A capability-not-authorship pitch standard and validation pipeline that gave all 143 specialists a public introduction in one consistent, accuracy-checked voice, generated graph-first from the cartography maps and verified against the Collective Brain.
26 May~60 hrs
The asset-production platform
The shared production engines registered as one platform team: a document render engine behind every PDF, an image library and alt-text pipeline, and the producer that turns each specialist's pitch into a team-page video.
27 May~90 hrs
Word-synced agent-video captions
Captions across the agent pitch-video library: Whisper word-level timestamps drive a WebVTT generator, a paginated backfill route caption-stamps the whole back catalogue, and the player reveals each spoken word in a rolling karaoke window. An accessibility and comprehension layer on every specialist's introduction.
28 May~120 hrs
The founder walkthrough
An interactive walkthrough of every active agent in the fleet, reading agent_personas live on every load. Four progressive layers per card — the agent speaks, the Brain's takeaway, an implementation brief, and a heartbeat probe against blog_posts, agent_videos and conversation packs that surfaces real ops findings. It caught the EFO content-engine silence on day one. Per-agent portrait, pitch, tier and team filters, search, founder notes that persist locally, and JSON export. The diligence surface for founder-mode reviews across the whole roster.
28 May~200 hrs
The agent conversation runtime
Phase 1 of conversational avatars: any active agent in the registry can now be spoken to from /admin/agents/[slug]/talk. Claude reply grounded in the agent's persona, ElevenLabs voice resolved through a HeyGen-to-ElevenLabs name-matching layer, transcripts stored against a new agent_conversations table. The static fleet becomes a working roster you can actually talk to.
28 May~120 hrs
The Brain Infrastructure read/write split
Four new LLM members in the Brain Infrastructure team, split clearly read-side and write-side. Brain Pulse Monitor and Daily Reports Compiler watch the Brain and read its pulse; PENDING-UPDATES Triager and Brain Git Steward make the writes. Same shape correction the Asset Production Tooling team got a day earlier — one ambiguous role becomes two named lanes. Carried the fleet from 142 to 146 specialists.
28 May~30 hrs
Sitewide roster propagation
Postgres triggers on agent_personas and agent_videos so any roster edit in /admin/team — a new portrait, a renamed agent, a swapped video — cascades to every public surface automatically. The plumbing behind the live counters and per-page reads on /agents and /team.
28 May~80 hrs
The 23:00 agent, hardened
The Brain Health agent migrated to the Max plan via CLAUDE_CODE_OAUTH_TOKEN and its launcher patched to call /Users/nigelcasey/.local/bin/claude on an absolute path — launchd's stripped PATH no longer breaks it. Proven by a launchctl kickstart in real production context, then by seven consecutive unattended nights from 29 May to 4 June. The self-heal loop the 19 April Brain Health entry opened is now closed.
28 May~100 hrs
The content-engine protective layer
The EFO publish queue restarted after the founder-walkthrough heartbeat surfaced a publish-gate stall. Seventeen drafts back-dated to their original schedule, three Weekly Challenges rolled forward to June, one strong-opinion piece deferred for personal review. A new /api/cron/editorial-review-reminder route plus a vercel.json schedule fires daily at 07:00 UTC — silent on healthy days, emails Nigel if the queue is stuck or the last publish is older than 24 hours. Drift catches itself now.
29 May~700 hrs
The Phase 2 conversational-avatars arc
Phase 2 of conversational avatars, closed end-to-end in a single day. Any group from the registry convenes at /admin/meeting-room — each member speaks in its own ElevenLabs voice across sequential turns, reasoning from a Brain-cached standing brief (Phase 2.5), with prompt caching and tier-based model selection cutting per-meeting cost by about 85 percent (Levers 1+2). PDF, DOCX, TXT and MD attachments are read in as text and held in a cached static block so the documents are part of every agent's context (Phase 2.6). The Chairman synthesises the discussion at the end (Phase 2.7); an eight-template dispatch engine turns the decision into ready-to-apply downstream actions, alongside meeting titles, soft-delete and outcome categorisation (Phase 2.8). The whole arc shipped Cowork direct-write at zero Claude Code spend. The company can now hold its own meetings.
5 Jun~150 hrs
The Council ↔ Dashboard integration
Designed today. When a prospect dashboard is unlocked at dashboard.nigelcasey.com/preview/[id], the eight-member Strategic Council deliberates server-side on that prospect's analysis and the audio replay embeds in the unlocked dashboard. Productises the 30 April manual precedent — Nigel ran his own business through the Council and surfaced the FADP exposure that became the Audio Purge cron. PWA side and dashboard side both named; build follows.
5 Jun~40 hrs
Mobile-first media discipline on the public roster
The agent video cards on /team and /start now ship a lazy <img> overlay over a posterless preload='none' video, and the caption track only mounts on first tap — off-screen cards cost nothing until scrolled to, and sound still plays on iOS because the video element stays in the gesture. The /team roster's filter taps smooth-scroll to the chosen team's heading under the sticky header. /start ISR dropped from one hour to 60 seconds so persona regenerates land on the marketing page within a minute. The blog hero on /build/<slug> took fetchPriority='high' as the LCP element. The public roster loads fast on phones now.
6 Jun~90 hrs
The product catalogue
A public /products catalogue on nigelcasey.com: a listing page and per-product pages reading from a single products.ts model that mirrors the Brain's productisable-assets register, wired into the desktop and mobile nav. Each card and detail page carries a live portrait strip of the delivery team pulled from agent_personas on a 60-second refresh, and the detail pages surface 45 blog angles across origin, mechanism and transformation.
7 Jun~100 hrs
The self-hosted Studio recorder
A browser recording studio inside the EFO admin under Pipeline & Leads, replacing Loom for review videos. A MediaRecorder capture component with a teleprompter overlay that is shown but never recorded, recordings written to Supabase storage with a backing table plus rename and delete, camera access opened via Permissions-Policy with real media errors surfaced, and a tokenised /loom/[token] playback page. Review videos are produced in-house now.
10 Jun~80 hrs
EFO Command: the admin theme + Presentation Mode
The whole EFO admin unified on a dark navy command-centre theme through a scoped CSS remap, with the nav restructured into EFO Command modules and a home launcher at /admin. A new Presentation Mode hides internal detail and pseudonymises PII, backed by a DOM-wide blur layer for emails, phone numbers and free-text containers, so the admin can be demonstrated live without exposing learner data.

04 · The structure

Four divisions. 18 departments. One mission.

Each division is an actual operating function with its own AI Specialists, its own outputs, and its own measurable work. Not a marketing chart.

DIVISION 01
EnglishFluency.Online
The core operating business: premium English coaching for non-native professionals.
Sophie. The always-on AI practice partner who replaces a full-time coach by serving every learner, every hour, in voice and chat.
10Departments106AI Specialists
DIVISION 02
MyBusinessAccelerator.io
Productised AI advisory funnel for SME owners: the Council, packaged.
The Chairman. Synthesises five anonymised advisor opinions plus a peer-review round into one dashboard. Honest, citation-anchored, never flattering.
1Departments4AI Specialists
DIVISION 03
Founder Operations
Internal cross-business tooling: the private mirror of the Council, used on Nigel's own decisions.
The Red Team. Whose job is to dissent. The schema rejects unanimity. If it agrees with the others, it is failing.
3Departments20AI Specialists
DIVISION 04
DPA Sagl Group
The parent legal entity: financial, accounting, compliance and data-protection infrastructure.
The Audio Purge cron. A daily Vercel job that enforces FADP-aligned retention on raw learner voice recordings. The privacy policy made into a behaviour.
4Departments20AI Specialists

05 · Specific proof

Numbers most operators of this size cannot tell you.

The cost of compliance. The speed of reconstruction. The unit economics of advisory. These are mine.

EduQua dossier

57 / 57 in three weeks.

A complete Swiss quality-management documentation suite, ten specialist AI Specialists producing audit-ready criteria documents across all eight eduQua principles. The traditional engagement runs CHF 25–60k and 6–12 months.

Built April 8 → April 28, 2026.
Accounting reconstruction

An entire fiscal year, in two days.

Five-source pipeline (Stripe, PayPal, two bank accounts, payroll) routed into a fully validated set of journal entries against a Swiss KMU chart of accounts. Zero unclassified. Layer-1 validation passing.

Reconstructed in two days from a cold start.
Strategic Council

Twelve minutes for a CHF 8–15k advisory.

Five advisors, one peer-review round (anonymised, shuffled), one Chairman synthesis, schema-validated output. The advisory engagement that would normally cost five figures and take three weeks runs in twelve minutes for a few cents of inference.

Productised as MyBusinessAccelerator. Used internally on every major decision.
The Collective Brain

A persistent memory layer, fully owned.

Thirty-plus governance files across twelve layers, exposed via an MCP server over Tailscale, audited nightly by an immune-system AI Specialist. Every other employee reads from it before it acts. Without it, every session starts from zero.

The substrate of human-led, AI-amplified intelligence.

From the Behind the Build series

Today's AI Specialist: The Chairman

The Strategic Council runs in two surfaces. The founder-facing one is chaired by the Chairman, who closes a process already disciplined by Red Team, Peer Review and schema validation. Here is how the seat actually works.

Read the post →

Behind the Build

How it's being built, in real time.

Dated field notes from inside the company. Wins, mistakes, and the architecture decisions in between.

See all Behind the Build posts →

06 · Work with me

Build the operating intelligence your business is missing.

Most consulting hands you a deck. This one hands you an operating company that runs your domain, grown from your business, uniquely yours, fully owned.

Take the free diagnostic →The Build

Engagements run from a single Council session up to a full four-week build of your divisional stack. Every engagement begins with a free 30-minute scoping conversation.

For the analytical reader

The full team report: every AI Specialist, every detail.

146 AI Specialists named, dated, with collaborators, work completed, and human-hours estimate. Compiled directly from the live codebase. The procurement-grade version of this page.

→