Ask what was decided. See the sentence it came from.

Meetings, Slack, GitHub and Jira flow into one memory for each project. Everyone on the project asks the same chat, and every answer carries the quote and the source behind it.

  • Your own Anthropic key, no markup
  • Runs on your server or ours, in the EU
  • A source on every answer

A copy of the product answering a question, shown as text: the question, the answer, the three sources it cites, and one of those sources opened to the sentence the answer came from.

From the demo project this page is built on.

Also works in
  • Claude
  • Claude Code
  • Cursor
  • VS Code

01 Learns from

Everything your project already says, kept

Connect a source once. What was said there becomes memory anyone on the project can ask about, each entry holding the sentence it came from.

What it reads

  • Slack: Channels where the team talks it through
  • GitHub: Pull requests, issues and reviews
  • Google Meet: Meetings, transcribed for you
  • Jira: Tickets and what changed on them
  • Meeting recordings: Calls recorded right in the app
  • Documents: Specs, briefs and contracts
  • Your own apps: Anything your own tools send

What it keeps

  • Decisions: with the sentence it came from
  • Who thinks what: who argued for what, and when
  • Action items: who owes what, and by when
  • Open questions: what nobody has answered yet
  • Risks: what could go wrong, raised early

02 Who asks

One memory, a different question from everyone

The people on a project need different things from it. Each of them asks in plain words and gets an answer built only from what they are allowed to see.

  • CEOLeadership only

    “Are we still on track for the 15 October launch?”

    Answer cites:Leadership sync · 3 Sept

  • Project managerTeam only

    “What did we promise the client about guest checkout?”

    Answer cites:Client call · 9 Sept

  • DesignerTeam only

    “Why was sign-up cut down to a single step?”

    Answer cites:#design · Slack

  • DeveloperTeam only

    “Which payment tests have to pass before code freeze?”

    Answer cites:PR #212 · GitHub

  • QATeam only

    “What changed in checkout since the last test run?”

    Answer cites:QA-41 · Jira

  • ClientClient can see

    “When will guest checkout be live?”

    Answer cites:Sprint planning · 12 Sept

03 How it answers

The same question. A different answer for the client, the developer and the CEO. All of them true.

Studio is building a checkout for its client Acme. Guest checkout moved to phase 2, not everyone agreed, and the client is in the same chat as the team.

Acme Checkout

It moved to phase 2 at sprint planning on 12 September. Building it for launch is about six more developer days, and it takes the payment tests from 24 to 48 cases before code freeze.

Sara disagreed on the day, on conversion grounds. The 15 October date cannot move, because Acme's campaign starts on 20 October.

Sprint planning12 SeptPR #212GitHubQA-41Jira

Elena's answer is not the model being careful. Her search cannot reach those rows at all: who sees what is a Postgres policy, checked before anything is sent to the model.

04 How it works

From a meeting to an answer you can check

What goes in, what memory keeps, how you ask, and what is still owed.

A question typed into the chat, and the answer arriving with the decision behind it.

05 Under the hood

Built to be trusted with a project’s memory

The parts nobody sees in a demo, and the first things a company asks about.

  • RLS

    Who sees what is enforced by the database

    Postgres row-level security checks every query, so a client never reaches a team-only row, not even by mistake.

  • EU

    Hosted in the EU

    It runs on your server or ours in Europe, and your content goes only to Anthropic, on your own key.

  • EN · RO

    English and Romanian

    The whole app is in both languages, and anyone can ask in the one they think in.

  • Your schedule

    Old content deletes itself

    Each company chooses how long things are kept. A nightly job removes the rest, without anyone remembering to.

  • Activity log

    Every sensitive change is logged

    Keys, people, roles, sources, sharing and retention changes are recorded with who made them and when.

  • Encrypted

    Keys and tokens stay sealed

    Anthropic keys and connector tokens are encrypted at rest, never logged and never sent to the browser.

06 Where to use it

Ask it from the tools you already use

Open InteliLang in the browser, or ask the same project memory from Claude, Claude Code, Cursor or VS Code without switching windows.

  • InteliLang on the web

    The whole app: the chat, memory, the board and files, for everyone on the project, including your client.

    Who pays for the AI: Your company's Anthropic key, at Anthropic's price

  • Claude

    Add InteliLang as a connector in Claude on the web, desktop or phone, then ask about a project in the middle of any conversation.

    Who pays for the AI: Your own Claude plan

  • Claude Code

    Connect it with one command and a personal key. Check what was decided before you write the code for it.

    Who pays for the AI: The account you use Claude Code with

  • Cursor and VS Code

    Paste a few lines into the editor's MCP settings, and its assistant can read the project's decisions next to your code.

    Who pays for the AI: The editor's own AI

Every way in sees only what you can see on that project. A personal key can be revoked in one click, and the app it connected stops right away.

07 Numbers

Numbers we hold ourselves to

No customer counts and no made-up benchmarks. Just how the product is built to spend your money.

Markup on AI. You pay Anthropic's price, on your own key.
0%
Off reading large imports and backfills, through Anthropic's batch pricing.
50%
For a question the project has already answered.
$0
Levels of who can see what: the client, the team and leadership.
3

08 Who it's for

Made for small and mid-sized teams

Studios, agencies and product teams that work in projects, often with the client in the same conversation. It is not trying to be a search engine for a company of ten thousand.

  • Set up in an afternoon

    Create a company, paste your Anthropic key, connect a Slack channel or upload a meeting. No sales call and no rollout project.

  • You pay for hosting, not for AI

    The AI runs on your own key, billed by Anthropic with no markup. Questions the project has already answered cost nothing.

  • Your client can join

    Invite the client as a guest. They ask the same chat and get true answers, built only from what they are allowed to see.

  • Your data stays in the EU

    Runs on your server or ours, in the EU. Old content is deleted on the schedule you choose.

Put one project in and ask it something you already know the answer to.

Connect a Slack channel, a repository or one recorded meeting, then ask it something you already know the answer to. The answer should come back with the quote you were thinking of, and the source next to it.

May we count visits to improve InteliLang? We would keep a small cookie for it. Nothing you type is ever sent. Privacy