Menu

Request a demoStart using OIDA

OIDA for retail

Every store, every assistant, the same current rule.

Return policies, promotional rules, checkout procedures, planograms and store-cluster exceptions change constantly and reach stores in different versions. OIDA keeps track of which applies today, for which brand or format, and serves it to whoever asks, at head office or in store.

Start using OIDA Request a demo

Five questions an intranet search cannot settle today.

A current rule, an exception, an outdated version, a conflict and a missing decision. Five illustrative examples: choose a question and check its state and sources.

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

Get a demo

assistant · connected to OIDA

What is the return window for online orders bought on sale?

  1. resolve_decision_statescope all brands, online and in store
  2. Reading the sources in the registryReturns policy v6, §2 · Store network announcement, Jul 2026
  3. State resolvedIn force

Returns are accepted within 30 days of purchase, including sale items.

In force · scope all brands, online and in store · from 1 Jul 2026 · supersedes 14-day window for sale items, Returns policy v5

30 days, including sale items. Source: Returns policy v6, July 2026. Version 5’s 14-day window for sale items is superseded.

Sources
  • Returns policy v6, §2The return window is 30 days from purchase, including items bought on sale.Primary
  • Store network announcement, Jul 2026Evidence

The solution

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

Every store has its own version of the returns policy. OIDA identifies the one in force.

A store manager asks in the assistant the brand has approved. The answer includes the current rule, the format exception and the open conflict.

assistant · connected to OIDA
Your AI assistant · AI modelShare

Do we accept a return without a receipt?

oida · resolve_decision_state

Resolving the returns topic, scope: all brands

Contested

Returns without a receipt are accepted within 30 days for store credit.

Returns policy v6, §3 · scope: all brands · from 1 Jul 2026 · contested while a conflict remains open

Yes, within 30 days for store credit, Returns policy v6, §3, from 1 July 2026. Not in outlets: a scoped exception in the same v6. An area manager’s message about 14 days is an open conflict: recorded, not applied.

oida · store-networkOpen in OIDA
Decision registrytopic resi
  1. In force
    Returns without a receipt are accepted within 30 days for store credit.Returns policy v6, §3 · scope: all brands · from 1 Jul 2026 · contested while the conflict below remains open
  2. Superseded
    Returns without a receipt are not accepted.Returns policy v5, §3 · superseded by v6 · kept as history, never returned as current
  3. Scoped exception
    Outlets do not accept returns without a receipt.Returns policy v6, §5 · scope: outlet format · returned only for that format
  4. Open conflict
    “From Monday, returns are limited to 14 days.”Area manager message, 5 Sep 2026 · non-authoritative · recorded, not applied · awaiting review
  5. Unknown
    Returns policy for the marketplace channel?No approved decision · nothing inferred

Three moments when the registry speaks your language.

  1. 01

    Opening a new store

    The team opening the store asks the assistant which checkout procedures and return rules apply to that format. The answer is the current version, with scope and source, without searching through years of circulars.

  2. 02

    A new season

    Promotional rules and planograms change together. People preparing store network communications start from current decisions and see those still under review.

  3. 03

    A brand audit

    Reviewers auditing a brand and their AI read the same approved policy, with format exceptions and its chain of versions.

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 it replace our procedure system or intranet?

No. Procedures, circulars and manuals stay where they are. OIDA holds decision state: which policy or rule is in force, for which brand, format or store, and the supporting excerpts.

Can rules be defined by brand, format or store?

Yes. Scope is part of every decision and every answer. A network-wide policy and a format exception coexist, each served only where it applies.

Who approves in a network with franchises?

In reviewed mode, owners and admins approve, such as retail and operations leads. In peer mode, members can approve too. Decisions inferred from prose require explicit review. A franchisee exception is a scoped decision, recorded like the others.

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