Menu

Request a demoStart using OIDA

OIDA for consulting

Every project team’s AI, working from the firm’s current decision.

Methodology standards, account rulings, rate cards and quality decisions are scattered across practices, offices and years of engagements. OIDA keeps track of which applies, for which practice or account, and serves it to the AI assistants the firm has approved.

Start using OIDA Request a demo

Five questions a search through slide decks cannot settle today.

These are not search questions. They are questions of state: which standard, for which account, since when and whether the lead 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

Who approves a discount above 15%?

  1. resolve_decision_statescope firm-wide
  2. Reading the sources in the registryCommercial policy 2026-01, §4 · Partner committee minutes, Dec 2025
  3. State resolvedIn force

Above 15%, a partner approves. Above 25%, the managing partner approves.

In force · scope firm-wide · from 1 Jan 2026 · supersedes Single 20% threshold, Commercial policy 2025

A partner above 15%, the managing partner above 25%. Source: Commercial policy 2026-01, §4. The single 20% threshold is superseded.

Sources
  • Commercial policy 2026-01, §4Discounts above 15% require a partner’s approval. Above 25%, the managing partner’s.Primary
  • Partner committee minutes, Dec 2025Evidence

The solution

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

Three slide decks and a chat thread disagree. Only one ruling is in force.

A consultant asks in the assistant the firm has approved. The answer includes the standard, the account ruling and the open conflict.

assistant · connected to OIDA
Your AI assistant · AI modelShare

Which delivery framework applies to new engagements?

oida · resolve_decision_state

Resolving the delivery framework topic, scope: firm-wide

Contested

Engagement delivery follows Agile Delivery Framework v4.

Methods board MB-2026-03 · scope: firm-wide · from 1 Mar 2026 · contested while a conflict remains open

ADF v4, under methods board MB-2026-03, from 1 March 2026. Corvane Insurance has a scoped exception on v3, and a delivery channel message about waterfall is an open conflict: recorded, not applied.

oida · methods-and-qualityOpen in OIDA
Decision registrytopic framework di delivery
  1. In force
    Engagement delivery follows Agile Delivery Framework v4.Methods board, ref. MB-2026-03 · scope: firm-wide · from 1 Mar 2026 · contested while the conflict below remains open
  2. Superseded
    Engagement delivery follows Agile Delivery Framework v3.Methods board, ref. MB-2024-11 · superseded by MB-2026-03 · kept as history, never returned as current
  3. Scoped exception
    Corvane Insurance engagements stay on ADF v3 until contract renewal.Account ruling AR-118 · scope: Corvane account · returned only for that account
  4. Open conflict
    “We are doing the Corvane rollout in waterfall from the next sprint.”Delivery channel, 22 Apr 2026 · non-authoritative · recorded, not applied · awaiting the practice lead
  5. Unknown
    Which framework applies to fixed-price public-sector tenders?No approved decision · nothing inferred

Three moments when the registry speaks your language.

  1. 01

    Writing a proposal

    A partner’s AI assembles the proposal using the methodology, rate card and quality terms current for that sector, and flags those under review.

  2. 02

    Joining an account

    A consultant new to the account asks how the client handles data residency. The answer is the account ruling, its scope and its source, without reading three old slide decks.

  3. 03

    After the engagement

    Decisions made during delivery are recorded with owners and evidence. The next team inherits the state and its history.

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 our knowledge management platform?

No. Slide decks, playbooks and engagement files stay where they are. OIDA holds decision state: which standard, ruling or rate card is current, for which practice or account, and the supporting excerpts.

Can rules be defined by practice, account or country?

Yes. Scope is part of every decision and every answer. A firm-wide standard and an account exception coexist, each served only where it applies.

Who approves in a firm with many practices?

In reviewed mode, owners and admins approve, such as methods, quality and risk leads. In peer mode, members can approve too. Decisions inferred from prose remain candidates until someone explicitly approves them.

Does confidential client material leave the firm?

OIDA Cloud stores the source text you submit, decision records and references. The workspace is the access boundary; MCP answers contain excerpts. Writes are audited; capturing successful calls is optional and 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