AI-Augmented CRO
Build your own AI tools for the CRO cycle
Two days of hands-on practice with Claude Code, applied to your teams' experimentation cycle: connecting AI to your tools, encoding your method into reusable skills and building a first tool.
The need
What you tell us
« My CRO teams already use generative AI daily, but on an ad hoc basis. I want them to connect AI to our tools (analytics, A/B test, backlog), encode our methodology into reusable assistants, and build the small tools the program needs themselves. »
- « My teams use AI on a case-by-case basis »
- « I want to connect AI to our tools »
- « I want to encode our method into reusable assistants »
Our response
- Mapping of automatable CRO tasks
- MCP, skills and CLAUDE.md on your stack
- A first tool built, from specification to launch
Method
Our method in 5 steps
Our stance
Your method, encoded
Each participant leaves with their skills, the context of their programme and a first tool running on their data.
- MCP
- Skills
- CLAUDE.md
- V1
Step 01 : Laying the foundations
Strengths and limits of AI, distinction between prompt, assistant, agent and automation, then mapping of CRO tasks scored by impact, feasibility and risk.
- Strengths and limitations of AI: invented figures, customer data
- Prompt, assistant, agent, automation
- CRO tasks scored impact × feasibility × risk
- Prompts and assistant on a recurring deliverable
Step 02 : Getting started with Claude Code
Installation, key commands, permission and supervision modes, context management up to the first commit.
- Installation based on your access method
- Key commands and session management
- Permission modes and supervision
- Context, compaction and first commit
Step 03 : MCP, skills and context
Read-only connection to GA4 and your A/B tool, test brief and results-reading skills with statistical safeguards, program CLAUDE.md.
- GA4 and A/B testing tool connected in read mode
- Test brief skill in your team's format
- Results-reading skill with statistical safeguards
- Program CLAUDE.md and scheduled task
Step 04 : Build a first tool
V1 spec on a real use case, implementation plan, build and test against the spec, then presentation to the group.
- Specification of the V1 for your use case
- Implementation plan before the build
- Build, test against the specification and iterations
- Presentation to the group
Step 05 : Embed the practice
30-day AI roadmap per participant, a measurable gain per action, and AI integrated into the team's CRO rituals.
- 30-day AI roadmap
- A measurable gain per action
- AI in the team's CRO rituals
Deliverables
What you get
CRO skills
In the format of your deliverables: test brief, results reading.
Program's CLAUDE.md
KPIs, naming conventions and decision rules for your tests.
A V1 tool
Built by each participant on their own use case.
30-day roadmap
Prioritized actions, each associated with a measurable gain.
Who is it for?
Who is this offer for?
Tools used
- Claude
- Claude Code
- MCP
- GA4
- AB Tasty
- Kameleoon
- Notion
- Jira
- Git
- CRO or growth team already using generative AI
- Context: connecting AI to the stack and building your own tools
- Sponsor: Head of CRO, Digital Director
To go further
Articles by our experts related to this offer.
How to parallelize your A/B tests?
The secret to growth isn't the single A/B test but parallelization governed by impeccable governance.
From simple FAQ to closing: how conversational commerce turns visitors into engaged buyers?
Faced with the paradox of choice, e-commerce is using generative AI to advise customers and thereby boost conversions.
How can UX (and CRO) impact your SEO (GEO)?
UX directly influences your SEO and your visibility in generative AI: behavioral signals, readability, ...
Qualitative and quantitative analysis, how to choose?
Quanti or quali? Leverage both types of analysis to improve UX and boost your CRO strategy!
How to find the best CRO agency in 2026?
Finding a CRO agency suited to your needs can be a challenge. This article guides you through the process
What are the success KPIs of a CRO program?
An experimentation program is not just a succession of A/B tests launched in the hope that an uplift will appear.
Opinion piece: Omnichannel and CRO: A natural synergy?
Omnichannel has become a major challenge for brands seeking to optimise their customer experience. In a previous
CRO Maturity Audit: Methodology and Process
A CRO maturity audit assesses an organization's ability to optimize its performance through method
To go further
Often associated with
Agentic commerce
AI agents for CRO
Orchestrate your AI agents in the CRO cycle
- Claude
- MCP
- GA4
- and 3 other tools