PARRITAI
PARRIT / JOURNAL · REV 01 · 2026

This journal is written on the job.

What held and what broke, on AI systems inside companies. Dated and on the record.

  1. Journal / Entry

    Before you move a model in-house, measure the wait it will cost

    Sovereignty arguments get decided in the first second in front of a cursor. Running a model on hardware you own rarely fails on quality. It fails on the wait, because a rented endpoint spreads its cost across thousands of simultaneous strangers while your machine serves the handful of people who arrive at nine on Monday.

  2. Journal / Entry

    Before you let a model click, ask what it can undo

    Computer use ends the argument that software without an API cannot be automated. It leaves a harder problem behind: a logged-in browser session carries a whole person's permissions, and none of them are scoped.

  3. Journal / Entry

    What does multi-provider redundancy actually protect you from?

    On Thursday 3 September, ChatGPT, Claude and Grok degraded inside the same morning, and four days later nobody outside those companies can say whether the three failures were connected. Not being able to tell is the finding. If you cannot name the layer you share, you have bought two vendors and one failure domain.

  4. Journal / Entry

    What is a company operating system?

    A company operating system reads what happens across a business, frames the decisions that need a human, and executes the actions in the company's own tools. It is built for one company and belongs to it, code and data included.

  5. Journal / Entry

    What we mean when we call ourselves a manufacture

    Parrit.ai is a French manufacture founded by Paul Larmaraud: company operating systems built to order, one client at a time, owned by the client at delivery.

  6. Journal / Entry

    When you roll back a bad deploy, what else disappears with it?

    A rollback restores a known-good state, and everything that shipped since then goes with it. We lost a published article that way this week. The fix is in the shape of the deploy unit, not in the rollback.

  7. Journal / Entry

    Is a cheaper model good enough for everyday production work?

    For most production tasks, yes. We route the bulk of our own workload to inexpensive open-weight models and treat frontier models as an escalation path, not a default.

  8. Journal / Entry

    Agents that fabricate facts: what a 1,355-row cleanup taught us

    The real risk of production AI is not a chatbot hallucinating in front of a user. It is a process silently writing plausible, false records into a database everything else trusts.

  9. Journal / Entry

    Starting an AI Act compliance register without a compliance team

    The August 2, 2026 milestone is behind us. For a company that automates methodically, the compliance register is not a new project. It is an export of records the system should already be producing.

  10. Journal / Entry

    Letting a system publish without human review

    Machine gates can carry the responsibility of publishing. The condition is that the gates know how to say no, and that the human moves upstream.

  11. Journal / Entry

    AI agent security in the enterprise: the rules we apply

    Deploying an AI agent means giving it access to your data. The 8 security rules we apply to every deployment, and the questions to ask any provider.

  12. Journal / Entry

    GLM-5.2: dependence on American AI is already no longer inevitable

    A Chinese lab publishes an open model that comes close to Claude Opus 4.8 and beats GPT-5.5, six times cheaper, with no geographic restriction. Analysis, numbers, and how to use it.

  13. Journal / Entry

    One card, one action

    In an internal cockpit, approving a card must not only change a status. It must execute the promised action.

  14. Journal / Entry

    The draft that knows when to stay silent

    A useful editorial system does not force a daily post. It knows when the raw material does not deserve an article.

  15. Journal / Entry

    The right place to write

    Before automating publication, choose a stable write target. Otherwise the engine becomes a maintenance risk.

  16. Journal / Entry

    How to automate legal monitoring with an agent

    Delegate the monitoring of legal texts to a system without losing control.

  17. Journal / Entry

    MCP (Model Context Protocol): what is it and what is it for?

    An open protocol for connecting tools and data sources to agents in a consistent way.

  18. Journal / Entry

    Is Claude Code useful for a non-technical executive?

    Its value is measured in problems solved, not lines of code written.

  19. Journal / Entry

    How to secure an enterprise LLM for GDPR

    A practical review of data controls for using language models in a company.

  20. Journal / Entry

    How to deploy an LLM in your company

    A practical method for integrating a language model and obtaining useful results quickly.

  21. Journal / Entry

    Agent vs RPA: which one for which process?

    The question is not which technology is better, but which tool fits the work.

  22. Journal / Entry

    Claude Code or ChatGPT: which should a company choose?

    The useful question is which tool fits the work and the data involved.

  23. Journal / Entry

    How to integrate an agent into your operation

    Agent integration reorganizes work. Start with the process, not the technology.

  24. Journal / Entry

    What is an AI agent in a company?

    An operational definition without jargon, from a partner that deploys them every week.

  25. Journal / Entry

    Measuring SAP adoption with AI: putting an end to useless training

    Vendors train, no one uses it. An AI evaluation tool measures real SAP proficiency and drives change management.

  26. Journal / Entry

    Automated CRM for SMEs and tradespeople: no more forgotten follow-ups

    A CRM that follows up with your customers automatically, detects slow seasons and sends the right messages at the right time.

  27. Journal / Entry

    WhatsApp Business agent: automating customer relations without losing the human touch

    WhatsApp is your customers’ favorite channel. An AI agent can respond, qualify and follow up : all while keeping your tone.

  28. Journal / Entry

    Automated legal intelligence for lawyers: never miss a legal development again

    How AI monitors case law, appeals courts and legal doctrine to deliver a personalized briefing every Monday morning.

  29. Journal / Entry

    Automated invoicing with AI: zero entry, zero forgotten invoices

    Your invoices are generated, sent and reconciled automatically. Your bookkeeping runs itself.

  30. Journal / Entry

    AI prospecting: spotting your next customers through weak signals

    Podcasts, LinkedIn posts, B2B events : AI identifies the decision-makers who need you before they know it themselves.

Journal / Subscription

Every entry goes out by e-mail the day it appears.

One address is enough. Unsubscribe in one click.