0%
Rabbitron Lab for Professionals · Cohort #01

Cohorte Mai 2026

De l’assistant au système.

From assistant to system.

May 9 & 16, 2026 2 sessions · 10h00–13h00 36 professionals CNPG (near Gamal), Conakry, Guinea French
36
Professionals
2
Sessions
~10h
Hours saved per week (per pilot)
94%
Max productivity gain on a single task
Real Outcomes

Three professionals.
Three reclaimed weeks.

Documented during the cohort on real work participants brought into the room.

Section Chief — Livestock
National agricultural authority, Guinea
11h → 1h 20
a week of admin, compressed

Five real documents — technical notes, mission ToRs, budget analyses — taken from 11 hours of manual work to 1h 20min using Claude.

5 documents · max 94% gain on a single task
Chief Executive Officer
Industrial firm, Guinea
5 days → 3h
an executive week, compressed

Analysis, data reconstruction, budget control, and business plan work — a week of senior-leader output compressed to roughly three hours.

5 workstreams · avg ~95% gain
Founder
F&B startup, Conakry
3 Skills
running ops in production

Three production-grade Skills replacing manual work: WhatsApp order confirmations, customer-service replies, and supplier negotiation emails.

WhatsApp · SAV · Supplier outreach
See every documented task
Section Chief — Livestock
National agricultural authority, Guinea
TaskBeforeAfter ClaudeGain
Technical note — chick acquisition1h 3015 min94%
Mission ToR — poultry farmer identification2h10 min92%
Budget analysis — Beyla unit4h30 min88%
Professional email to WFP30 min5 min83%
Steering committee minutes (COPIL)3h20 min89%
Chief Executive Officer
Industrial firm, Guinea
TaskBeforeAfter ClaudeGain
Data analysis3 to 4 hours15 min~92%
Data reconstruction1 day15 min~97%
Budget controls2 days30 min~97%
Business planMulti-day1 hourMajor
Analysis review3 days30 min~97%
Founder
F&B startup, Conakry
TaskBeforeAfter ClaudeGain
WhatsApp order confirmationManual typing per orderSkill-driven messageHours/day
Customer-service reply (SAV / complaint)Free-form, inconsistentThree-block structured responseQuality + speed
Supplier negotiation emailAd-hoc draftingSkill with object + body + actionConsistency

Three modules. One arc.

Built on three frameworks established in Session 1, applied to production-grade workflows in Session 2.

5C

The 5C Frame

Every prompt = 5 layers: Casquette · Contexte · Commande · Contraintes · Calibre.

3L

3-Layer Memory

Personal Claude config: Profile (who I am) · Project (what I work on) · Style (how I write).

B

The BUILD Method

Besoin · Uploads/Instructions · Liaison/Déploiement. The assistant applied to a real task.

Module 01

Skills

Your prompts become buttons.

Each prompt is rebuilt into a Skill: a rôle ancré, an explicit method, input validation, a strict output format, reference examples, explicit interdits, and a quality criterion. Seven layers that turn fragile prompts into reproducible production tools.

Module 02

Connectors

Claude wired into Gmail, Drive, and Calendar.

Reading inboxes, writing into Google Docs, scheduling work — Claude operating directly on the tools each professional already uses, with the right permissions and posture.

Module 03

Claude Code

Industrial automation, without writing code.

From a one-shot assistant to orchestrated, file-aware workflows: financial models, business plans, multi-document analyses — all run through Claude Code as the execution layer.

In the room.

Two Saturdays at CNPG, Conakry — May 9 and May 16, 2026.

Cohort #02

Cohorte de juin 2026

Un métier. Un cas concret. Un assistant.

Your work. A real task. An assistant.

June 6 & 13, 2026 CNPG, Conakry, Guinea French

In person in Conakry · Online track on June 7 & 14

Finance, mining, data, reporting, commerce, administration and health: the June cohort adapts the fundamentals to different professional settings. The second session draws on participants’ practice feedback.

01

Structured prompts and the BUILD method

02

Seven professional assistant templates

03

Meeting minutes, quotations and presentations

04

Excel analysis and data reconciliation

Applied to everyday work.

Between sessions, the programme sets five uses over seven days, with a log of time spent and difficulties. Exercises include emails, meeting minutes, quotations, spreadsheets and communications.

The next step

Try it in your own work, record difficulties and improve your assistant using practical feedback.

In the room.

June cohort · Conakry, Guinea

Cohort #03

Cohorte de juillet 2026

Mieux guider l’IA. Aller plus loin.

Guide AI better. Take it further.

July 4 & 11, 2026 CNPG, Conakry, Guinea French

Two in-person sessions · CNPG, Conakry

The third edition develops request-writing skills and makes more room for guided practice. Exercises connect Claude’s tools with office tasks and working files.

01

9C: clarify audience, steps, examples and checks

02

Memory, Projects and BUILD assistants

03

Skills and connectors

04

Demonstrations with Claude Code and Cowork

Applied to everyday work.

Demonstrations cover spreadsheet anomalies and data reconciliation. A proposed 30-day follow-up challenge includes three Skills, one connector, one Code or Cowork project and a practice log.

The next step

A practice plan to consolidate learning after training. The 30-day challenge is a proposed goal, not a measured result.

In the room.

July cohort · Conakry, Guinea

Institutional training

Formation CNPG 2026

L’IA au service du travail institutionnel.

AI for institutional work.

June 2026 CNPG, Conakry, Guinea French

Institutional training · Conakry

Separate from the public cohorts hosted at CNPG, this programme focuses on the work of its teams: documents, finance, communications, administration and synthesis. Exercises illustrate uses adapted to institutional roles.

01

Financial dashboards and billing follow-up

02

Tender responses, procurement and contracts

03

Communications, archiving and synthesis

04

Human resources and administrative follow-up

Applied to everyday work.

The manual organises exercises around eight workplace Skills, using Word documents, Excel spreadsheets, correspondence and meeting minutes. Demonstration data is fictional or anonymised, with a human review step.

The next step

A shared approach to exploring AI across institutional roles, to be adapted and validated before operational use.

In the room.

CNPG team training · Conakry, Guinea

Bring a Rabbitron cohort
to your team.

We design cohorts for ministries, NGOs, and companies across Francophone Africa and beyond. Each cohort is built around your team’s actual work — and ships measurable outcomes.

Talk to us