Menu

Request a demoStart using OIDA

OIDA for manufacturing

Every engineer’s AI, working from the current revision.

Engineering changes, approved suppliers, process parameters and procedures vary between plants and product lines. OIDA keeps track of which revision is in force, where it applies and on what evidence, and serves it to the AI assistants your engineers already use.

Start using OIDA Request a demo

Five questions a PLM search cannot settle today.

These are not search questions. They are questions of state: which revision, for which line, since when and whether quality has decided. Here is how OIDA answers.

Illustrative examples. Choose a question and compare the answer and sources.

Get a demo

assistant · connected to OIDA

Which coating supplier is approved for the EU caliper lines?

  1. resolve_decision_statescope EU caliper lines
  2. Reading the sources in the registrySupplier quality approval QA-0932 · Supplier audit report, Oct 2025
  3. State resolvedIn force

Coatings for the EU caliper lines are purchased under supplier approval QA-0932.

In force · scope EU caliper lines · from 15 Nov 2025 · supersedes Supplier approval QA-0711

Supplier approval QA-0932, for the EU caliper lines, in force since 15 November 2025. Source: supplier quality approval QA-0932. QA-0711 is superseded.

Sources
  • Supplier quality approval QA-0932QA-0932 supersedes QA-0711 for all coating supplies to the EU caliper lines from 15 November 2025.Primary
  • Supplier audit report, Oct 2025Evidence

The solution

A shared memory that grows as your company grows, and builds your own intelligence, for full sovereignty over your data.

A drawing, a deviation and a shift note disagree. Only one revision is in force.

An engineer asks in the assistant the plant has approved. The answer includes the current change, the deviation and the open conflict.

assistant · connected to OIDA
Your AI assistant · AI modelShare

What torque applies to cover screws on line 3?

oida · resolve_decision_state

Resolving cover screw torque, scope: Turin plant, line 3

Contested

Cover screws on line 3 are tightened to 12 N·m.

ECO-2041 · scope: Turin plant, line 3 · from 3 Feb 2026 · contested while a conflict remains open

12 N·m under ECO-2041, from 3 February 2026. Pre-2024 fixtures remain at 10 N·m under deviation DV-118. A shift handover note reporting 11 N·m is an open conflict: recorded, not applied.

oida · eu-qualityOpen in OIDA
Decision registrytopic coppia viti carter
  1. In force
    Cover screws on line 3 are tightened to 12 N·m.ECO-2041 · scope: Turin plant, line 3 · from 3 Feb 2026 · contested while the conflict below remains open
  2. Superseded
    Cover screws on line 3 are tightened to 10 N·m.ECO-1877 · superseded by ECO-2041 · kept as history, never returned as current
  3. Scoped exception
    Covers on pre-2024 fixtures remain at 10 N·m.Deviation DV-118 · scope: pre-2024 fixtures · returned only for that scope
  4. Open conflict
    “Torque on line 3 is 11 from Monday.”Shift handover note, 9 Mar 2026 · non-authoritative · recorded, not applied · awaiting quality review
  5. Unknown
    What torque applies on the new line 5?No approved decision · nothing inferred

Three moments when the registry speaks your language.

  1. 01

    Engineering change

    An engineer asks which drawing revision is released for a plant. The answer is the current change, its effective date and the deviation valid for just one line.

  2. 02

    Quality and audit

    Auditors and their AI read the same approved procedure, with its evidence and chain of supersessions.

  3. 03

    Handover between shifts and plants

    A chat note does not change a parameter. It becomes an open conflict until quality reviews it, and history keeps both.

Lost time has a cost. Measure what changes for your team.

More than 6 in 10 times

when the document the AI retrieves holds a wrong figure, the AI repeats it as true: even when it knew the right answer

ClashEval, 2024–2025: six models compared on over 1,200 questions across six fields

50 hours a month

spent reconstructing decisions if ten people spend fifteen minutes a day

Making fewer mistakes, and managing your ontology and your company memory to build an AI of your own, means saving money.

Find the decision

Ask which rule applies today and read the source alongside the answer.

Your AI assistant

QuestionWhich database do we use for a new service?

Toolresolve_decision_state

OIDAone answer, with its source
In force

PostgreSQL is the approved database for new services.

ADR 024 · scope new-services · since 1 Feb 2026

  • ADR 024 · Choice of databaseNew services use PostgreSQL.primary

Architecture and sovereignty

Your decisions stay with you, even when you change AI.

Decisions stay in a registry separate from the AI model. In Cloud, data is in the database we run and each organisation has its own workspace. For enterprise integration we talk directly to your IT department and keep your data in your own infrastructure, with your own policy.

Your AI assistantscompatible, via MCP

Your peopleweb app

Who asksyour people and your tools

OIDAthe decision layer
  • explicit rules for decision state
  • traceable sources and evidence
  • recorded authority and scope

  • No copy of your documentsOIDA stores the source text you submit, decisions and evidence. MCP answers return excerpts and references.

  • No trainingOIDA trains no model on the data in the registry. The dataset stays yours: any use starts from a decision of yours.

Your databasewhere the decisions stay

Cloudone workspace per organisation, data kept separate, Frankfurt

Enterprise integrationyour infrastructure and your policy, agreed with your IT department

Your data stays where you decideOriginals stay in their systems; OIDA retains submitted sources.

The model is the tenant. The structure is yours.

Data sovereignty starts with where data is stored and who can access it: we define those boundaries together for the pilot. AI sovereignty starts with a memory separate from the model, queryable through MCP, the protocol that connects assistants to external tools. You can change compatible assistants while keeping the same registry.

95 %or more of respondents consider private and sovereign AI important. 29% concretely prioritise sovereign AI in the near term
NTT DATA, 2026 Global AI Report, nearly 5,000 senior decision-makers across 30+ markets

  • Boundaries. Where the registry lives and who may read it is your call, settled before the pilot starts.

  • Models. Authorised assistants query the same registry, kept separate from models.

  • Permissions. Access by workspace, actions by role. Applicability scope is not a reading permission.

  • Efficiency. Answers carry excerpts, state and references. Use the pilot to assess the context your agent needs.

Accelerated in Turin, with a scientific advisor from MIT.

OIDA is accelerated within Kakashi Venture Accelerator, an AI-native venture studio based in Turin, with senior scientific advisor Pierfrancesco Beneventano, researcher in machine learning theory at Massachusetts Institute of Technology. The method is described in a publication with public evaluation corpora.

We publish what we learn.

All publications

Works with the clients you already have.

Connect a compatible client and authorise workspace access. Your agent can query decisions, sources and states through MCP. Another authorised AI client can consult the same registry.

Connect your AI

  • ChatGPTin developer mode
  • Claudeweb, desktop and mobile
  • Claude Code
  • Cursor
  • CodexCLI and IDE extension
  • GitHub Copilotin VS Code
  • Any MCP client

Get started with a clear approach.

  1. 01

    Documentation

    How to connect a client, what an answer contains, who approves what and where data lives.

    Read the documentation
  2. 02

    Research

    The method behind OIDA and other publications, with public evaluation corpora.

    All publications
  3. 03

    Installation guide

    Setup steps and workspace address for each compatible client, inside the web app.

    Open the guide

Frequently asked questions.

How to start, who approves, who can read, and what works today.

Does OIDA replace the PLM or quality management system?

No. Drawings, change orders and procedures stay in the systems that own them. OIDA holds decision state: which revision, supplier or parameter is in force, for which plant or line, and the supporting excerpts.

Can rules be defined by plant, line or product?

Yes. Scope is part of every decision and every answer. A plant-wide parameter and a deviation for one fixture generation coexist, each served only where it applies.

Who approves changes?

In reviewed mode, owners and admins approve, such as quality and engineering leads. In peer mode, members can approve too. Decisions inferred from notes, chats and drafts always need explicit review.

Can it run inside our network?

OIDA Local runs the same core on a machine you control, for one operator. OIDA Cloud uses the workspace as the access boundary. It audits write operations; capturing arguments and results of successful calls requires owner consent.

Is OIDA an assistant or a chat?

OIDA is a decision registry your AI assistant can query. Keep working in your existing compatible client. You record the relevant sources: OIDA does not automatically listen to calls or conversations.

Who approves a decision?

By default, owners and admins approve. Member contributions stay proposed. An owner can enable peer governance, allowing members to approve decisions too. Inferences from prose stay proposed. Ontology changes always require separate approval by an owner or admin.

Does OIDA train models on our data?

OIDA Cloud stores decisions, evidence and history without training models. OIDA Intelligence is a separate pipeline, not connected to Cloud and off by default. Using it requires an owner-admitted dataset, recorded rules and evaluation before a candidate model is approved.

Which clients work today?

Claude Code, Cursor and Codex have completed a real end-to-end run. ChatGPT in developer mode, the Claude apps and GitHub Copilot in VS Code follow the vendor’s published setup path. Any client supporting Streamable HTTP and OAuth 2.1 can connect. Clients that send only a static header cannot.

Start with one decision. Check what your AI answers.

Choose a decision that changed recently: an offer, a procedure or a policy. Bring the earlier source and the approved one.

  1. 01

    Create your workspace

    Sign up with your email and organisation name. Confirm your email when requested and sign in to your workspace.

  2. 02

    Connect your assistant

    Follow the installation guide: copy OIDA’s address into a compatible assistant’s settings and authorise access.

  3. 03

    Record, approve, check

    Ask your assistant to propose a map of topics and scopes, then approve it. Record the decision with its source, approve it and ask what applies now.

Start using OIDA

Start using OIDA Request a demo