I build AI systems that let one person do a team's work.
I'm Stéphane Lepain, founder of CPLT. I build AI systems around your documents and processes, and you keep them.
Stéphane Lepain · founder and builder
What is one repeated task costing you right now?
Finding an answer, preparing a routine update, copying information between steps, checking a draft before it goes out. Count it the way you'd count any other cost: how many people, how many hours a week, at what they cost you per hour. That's the number a new way of working has to beat.
Assistance, automation, or a private workspace.
- An internal knowledge assistant
I build a workspace around your documents and processes. It can answer questions with source pages and prepare drafts for a person to check.
- Automation for repeated steps
I scope how information moves from a request to a checked result. Connections, permissions, exceptions and approval before actions are agreed for your task.
- Optional private hosting
When your requirements justify it, I build a workspace in your environment. I assess data access, operating responsibility and cost before choosing where it runs.
2 years
in my day-to-day work, one person
2,773 pages
read across 38 versions, Sep 2026
50/50
verdicts matched in a 50-case test
15 checks
run on every review before I see it
Duration: my own statement. Page count, verdict match and check count: measured, September to October 2026. My own working system, not a customer case study.
One person prepares what a team of specialists signs off.
I prepare alone the review that a team of 3 to 5 specialists signs off: security architects for each domain, a programme manager and a product owner.
I built this for my own professional work. It isn't a CPLT deployment, and I don't claim it is. One place that happened, and how I caught it →
See the full evidence →Tell me what keeps coming back.
The first 45-minute remote call is free, and you receive a one-page note on fit and next steps.
Request a free callAgree what to build and how to check it.
Describe today
Record the effort, delays, errors and cost of completed work.
Agree the checks
Name the reviewer, acceptable results and cases that need a person.
Bound the trial
Agree examples, scope, written price and criteria before paid work starts.
Decide what follows
Compare the results and full cost. Continue, revise or stop.
The business case
Is it worth the cost?
I compare a sample of real tasks, done today and done with the tool, at the same quality. Failed attempts count too. Read how I evaluate an AI pilot by cost per accepted result.
Keep control
Decide what the tool may do and what a person must check.
Before building, I agree what information may be used, which services may receive it, who approves actions and who handles missing or conflicting information. See the fictional source check and its limits →
Work directly with me
I scope it, build it and walk you through it.
I deliver paid projects with a written scope, price and checks. You work directly with me. I have run this setup myself, every day, for two years. I use an open-source LibreChat workspace, a LiteLLM gateway and Ollama for local open models. More about how I work →
Put AI to work. Make the business case.
In this 2 minute 46 second video, I explain how to choose one task, agree human checks and compare the full cost.
Made with AI: the presenter uses my AI likeness and voice. The examples are fictional, not customer results. Selectable captions are available in the YouTube player.
Watch on this site with the full transcript (opens the YouTube player).
Two fillable pages, free to download. Save it and email it to me, or bring it to the call. Leave out confidential information.
Loading the player connects to YouTube. Playback starts when you press play. You can also watch on YouTube.
Tell me what keeps coming back.
The first 45-minute remote call is free, and you receive a one-page note on fit and next steps.
Request a free callNotes on AI cost, choices and checks.
All essaysWhich AI Model Should Check Your AI's Work?
I sealed AI reviewers away from the answer key and scored what each found. Two providers' own filters stopped the review outright.
How Jev Speeds Up My Production AI Review Workflow
I use Jev, a small decision model, for four narrow calls in my AI workflow: model choice, ranking, bad-input checks, filing. A person decides.
Questions about working with CPLT
What can CPLT build for my business team?
I build custom AI assistants for questions, summaries and drafts using permitted information, and automations for repeated steps. I agree the task, connections, acceptance checks and human review before paid work starts.
What happens during the free scoping call?
The free 45-minute remote call starts with one recurring task, how often it happens and what you want to improve. You receive a one-page written note on fit and next steps; any paid work has a separate written scope and price agreed first.
Do I need private hosting?
No: private hosting is optional, and approved external APIs are another delivery choice. I assess the data boundary, actual processing routes, operating responsibilities and full cost before choosing the setup.
How do you assess whether an AI trial is worthwhile?
I compare representative work against agreed acceptance checks and count implementation, model/API usage, hosting, human review, correction, maintenance and support, including failed attempts. Time released is capacity; I do not promise cash savings, payback or an accuracy rate.
What happens after handover?
I document operating procedures and walk your team through the runbook, with responsibilities agreed before building. Ongoing support has its own agreed scope and price.
Tell me how your team works.
A free 45-minute remote scoping call, ending in a one-page written note on fit and next steps. Tell me what your team does and what you want to improve. I reply personally within one business day.
Request a free callEU-based · Remote delivery · Written scope first