Skip to content
CPLT
Request a free call
Menu
Back to overview

Field Notes

Self-hosted AI, written down.

CPLT builds AI assistance for business owners and their teams. Stéphane Lepain’s notes carry dates, assumptions and limits.

One email when a new essay ships. No other use, unsubscribe by replying, or take the RSS feed.

Prefer video? Business video and transcript · All CPLT videos

What are you deciding?

supplier-quotessmall-businesshuman-review

How to compare supplier quotes with AI before buying

A purchase-quote checklist for comparing the same scope, checking the figures and keeping the supplier decision with a person.

5 min read
unstructured-datametadatasmall-business

How to make your unstructured data AI-ready

Much of what a small company knows sits in documents, emails and scans. AI answers go wrong when it cannot read the file, picks an old version or ignores who may see it. These are the four steps I use.

5 min read
invoicessmall-businesshuman-review

Can AI Process Your Invoices? What to Check First

AI can read an invoice and fill in the supplier, dates, totals and line items. I would check each result against your orders and records before anything is paid.

6 min read
ai-agentssmall-businessautomation

AI agent vs chatbot: what a small business gets

A chatbot answers in a conversation. An AI agent carries out the steps of a task in your tools. How to tell them apart, where each fits and what to ask a supplier.

5 min read
wrong-answerssmall-businesshuman-review

What to do when your AI assistant gives a wrong answer

Find out what the assistant was working from, fix the document or the instruction, keep the question for re-testing and decide who approves that kind of answer.

4 min read
copilotdocument-accesssmall-business

Can Copilot access all your company files?

Check the sharing rules your team already uses, the visibility of connected sources and what happens when someone’s access changes.

4 min read
ai-policychatgptsmall-business

Can I see what my team types into ChatGPT?

What an owner can and cannot see of staff AI chats depends on the plan and its admin settings. Decide what you want to see, then tell your team.

5 min read
knowledge-assistantcompany-documentssmall-business

How to train AI on your company documents

Most small businesses get what they want without training a model. The assistant looks up the right document when someone asks and shows the page it used.

5 min read
ai-adoptionemployee-trainingsmall-business

How to get employees to actually use AI

Many staff try AI on their own, quietly and without training. I would start from the work they repeat, approve the tools and agree who checks each result.

5 min read
customer-emailsmall-businesshuman-review

Can AI answer customer emails for a small business?

Yes, for routine questions your documents already answer. I would let AI prepare the reply and keep a person on every reply that commits the business.

4 min read
ai-automationsmall-businesshuman-review

Which tasks should a small business automate with AI first?

I would shortlist repeated work with clear sources and a named reviewer, then compare the full cost of completing it to the same standard.

4 min read
Françaischarte-iapme

Charte IA en entreprise : un modèle pour les PME

Neuf règles à copier et à adapter à votre PME, des exemples d’usages à écarter et un déroulement proposé sur une semaine.

6 min de lecture
ai-policysmall-business

AI acceptable use policy for a small business

Nine rules to copy and adapt, with everyday examples of unacceptable use and a suggested rollout over a working week.

5 min read
chatgptdata-privacysmall-business

Is It Safe to Put Company Data in ChatGPT?

It depends on the plan your people log in with and on what they paste. What OpenAI says it does with each plan, what to keep out of any chat, and the rules I would give a small team.

6 min read
Françaischatgptdonnéespme

Peut-on mettre des données d’entreprise dans ChatGPT ?

Tout dépend de l’abonnement utilisé par votre équipe et de ce qu’elle colle dans la conversation. Ce qu’OpenAI dit faire selon l’offre, ce qu’il vaut mieux garder pour soi, et les règles que je donnerais à une petite équipe.

6 min de lecture
ai-automationsmall-businesshiring

AI automation agency or independent consultant: which suits a small business?

Both can build AI that does real work for a small business. They differ in who you deal with, how much they take on at once and who runs the result afterwards. The questions I would ask either one.

5 min read
Françaisautomatisation-iapmeprestataire

Agence d’automatisation IA ou consultant indépendant : que choisir pour une PME ?

Les deux peuvent construire une IA qui fait un vrai travail pour une PME. Ils diffèrent par l’interlocuteur, la quantité de travail menée en parallèle et la personne qui fait tourner le résultat ensuite. Les questions que je poserais à l’un comme à l’autre.

5 min de lecture
ai-governanceai-trusthuman-review

Why Enterprise AI Needs More Than a Smarter Model

Can you trust AI with your enterprise decisions? For some of them, yes, with six controls around the model. For the rest, no. A smarter model gives you none of the six.

7 min read
private-aiself-hosted-aichatgpt-enterprise

What Is a Private AI Stack vs ChatGPT Enterprise?

A private AI stack runs in a workspace your business owns: the interface, documents, indexes and logs stay in systems you control. Here is how that differs from ChatGPT Enterprise.

6 min read
security-questionnairecaiqcompliance

I Tested AI on GitLab’s Public Security Questionnaire

I took GitLab’s published security questionnaire, hid its answers, and tested whether an automated workflow could answer the same questions from GitLab’s public handbook alone, with every answer quoting its source.

11 min read
ai-adoptionai-roiai-trial

Eight Questions to Ask Before Approving Any AI Spend

Before the budget moves, eight practical questions about an AI project’s process, outcomes, data and costs. A recommended checklist, not a validated predictor.

7 min read
ai-adoptionai-roismall-business-ai

Why AI Use Doesn’t Turn Into AI Value

McKinsey finds 88% of surveyed organisations use AI somewhere, but 39% report enterprise-level EBIT impact. Organisational barriers recur in the research; technical limits matter too.

8 min read
agentsmodel-evaluationai-governance

Which AI Model Should Check Your AI’s Work?

I sealed four AI models in a sandbox with no view of the answer key, then had each one review the same frozen code for planted defects. Two providers’ own safety filters stopped their model from finishing the job before it reached my score sheet.

10 min read
jevmodel-routingprivate-ai

How Jev Speeds Up My Production AI Review Workflow

Jev is a small decision model I call from code for four narrow jobs on my production AI workflow: picking a model, ranking reference pages, catching bad inputs and suggesting where a file belongs. A person decides every result.

7 min read
automation-engineerai-automationsmall-business-ai

What Is an Automation Engineer, and Do You Need One?

An automation engineer embeds inside a company to turn AI into a working part of a real process, not a demo.

7 min read
private-aiagentsmodel-routing

One Agent on My Phone, Five Tools Behind It

A one-day experiment on my laptop: one assistant on my phone takes the request, Jev sizes it, cheap models do the research, frontier models get the hard work, and every task ends with a written hand-off. What moves into my production workspace first is the discipline, not the router.

10 min read
ai-trialrecurring-taskhuman-review

How to Scope an AI Trial Before Buying Tools

Choose the work, define the data boundary and human checks, and write down when to continue or stop before committing to tools.

6 min read
internal-knowledge-assistantacceptance-checkshuman-review

Acceptance Checks for an Internal Knowledge Assistant

Write down what a usable answer must do, which sources it may use and when a person must take over. A fictional handbook shows how to specify the checks.

7 min read
llm-costtoken-pricingkimi-k3

Cheaper AI Tokens. A Bigger Bill.

Kimi K3 charges less per token than GPT-5.6 Sol. Yet one published benchmark reports a higher cost per task. I checked the prices, the token counts and what the comparison actually proves.

6 min read
ai-pilotai-roiprivate-ai

AI Pilot Cost: Measure Cost per Accepted Result

Define an accepted result, count failed attempts and human review, and compare the full cost of the work before committing to a build.

6 min read
model-routinglitellmself-hosted-ai

Automatic Model Routing: What to Test Before Using It

I assess automatic model routing by task quality, full cost, fallback behaviour and data permissions. A complexity estimate must not decide where data may go.

4 min read
agentsai-governancellm-operations

The LLM Writes Data. A Script Writes the Document.

I separate AI findings from document rendering so the source data, review decisions and output can be checked without regenerating the reasoning.

3 min read
agentsai-governancecompliance

Agent Finds, Human Checks: Using Gated Vendor Knowledge

I separate finding a reference from permission to retrieve or share it. Human access does not automatically authorise copying gated content into an AI system.

3 min read
cost-controlllm-operationsprompt-caching

Prompt Caching: Verify Configuration Against Actual Usage

I verify cache settings through accepted configuration and provider usage. A misspelled or unsupported option can look correct in a file and never take effect.

3 min read
agentsmodel-evaluationcost-control

How I Evaluate a Cheaper Model for a Second Opinion

A cheaper reviewer is useful only if it catches the errors that matter. Here is how I would test one without confusing agreement with correctness.

3 min read
agentsai-governancecompliance

When an AI Validator Invents a Rule

I check AI rule citations against an agreed source. A plausible identifier is not evidence, and a correct reference does not prove the conclusion.

3 min read
agentslibrechatoperations

Why an Agent Can Use Less Than Its Model’s Context Window

I check the effective context limit, framework configuration and actual requests before relying on a model’s advertised window for long tasks.

3 min read
sovereign-aiself-hosted-aivendor-risk

An AI Coding App Indexed 627,652 Files On My Laptop

OpenAI’s Codex desktop app registered my home directory as a workspace and kept scanning a project folder deleted three months earlier. The interesting part isn’t the bug. It’s that I could find it at all.

8 min read
architecture-reviewsecurityvendor-assessment

Named or Assumed: The First Question in Architecture Review

The weak point of most architecture dossiers is the sentence that says security is “handled by the platform.” Here’s the one distinction that separates auditable inheritance from a gap in disguise.

5 min read
cost-controlself-hosted-ailitellm

AI Router Health Checks: Count Cost and Detection Delay

I count scheduled API calls and compare their cost with the required failure-detection time before changing a model-router health-check interval.

3 min read
self-hosted-aitcoopenai

Buying an AI Server vs Paying for OpenAI API Tokens: A TCO Comparison

Is buying an AI server cheaper than paying for OpenAI API tokens? Compare hardware, subscriptions and API usage with setup, power, operator time and result quality included.

8 min read
self-hosted-aiinfrastructurevllm

3 Hidden Failure Modes of Self-Hosted LLMs Past 25 Users

KV cache fragmentation, the context-window I/O trap, and kernel scheduler thrashing, the three failure modes that crash self-hosted LLM stacks at scale, and how to fix them.

11 min read
ocrself-hosted-aicompliance

Use AI on Your Documents Without a Third Party

A local model alone does not keep documents in house. What has to run on your own systems, from OCR to backups, and how I check each step.

6 min read
vllmllamacppollama

vLLM vs llama.cpp vs Ollama at 25 Concurrent Users

Single-user local inference is a solved problem. Production LLM serving at 25 concurrent users is a different engineering domain, and the published benchmarks all agree on the shape of the failure.

7 min read
gdprcomplianceopenai

OpenAI DPA and GDPR Article 28: What to Check

A practical review of the contract, API retention, regional processing and the decisions your team still owns before sending personal data to an AI service.

7 min read

Talk it through with me. Request a free call