Skip to content

Teach Ronja your business

The first answer Ronja gives you is the worst one you’ll ever get.

Not because it’s wrong — but because on day one she knows your data without knowing your business. She can see a revenue column; she can’t yet know that your fiscal year starts in April, that “active revenue” excludes one-time fees, or that the old orders table is kept only for auditors. Every company runs on knowledge like this, and most of it lives in people’s heads.

What separates Ronja from a generic AI tool is that this knowledge has a home. Corrections don’t evaporate at the end of a chat — they land in named, readable, governed places, and they apply to every future conversation, for everyone. Teach her once; she stays taught.

Ronja learns through three surfaces, each with a distinct job (the full model is in How Ronja learns):

  1. Notes live inside a feature, next to the data they describe. They come in two kinds: skills teach Ronja a procedure, knowledge notes record facts about that feature’s data.
  2. Organization Knowledge is the company-wide layer — rules, terminology, and context that apply everywhere, curated by admins, with the core applied in every conversation automatically.
  3. The data dictionary — the column and table descriptions on your tables — sharpens how Ronja reads the data itself. See Maintain the data dictionary.

Here’s how each one compounds.

You’ve just spent twenty minutes walking Ronja through how your team builds the weekly revenue report: which tables, which exclusions, which format. Don’t let that walk-through die with the session. Say:

“Save how we build the weekly revenue report as a skill.”

Ronja writes it up as a note of kind skill, attached to the feature, and opens it in a side panel so you can read exactly what she recorded. Two details make skills quietly powerful:

  • Each note carries a description written as a retrieval hint — “when should a future Ronja load this?” So the next time anyone works with this feature and asks for the weekly report, she finds the skill and reads it before starting work.
  • You refine a note the way you refine anything with Ronja: highlight a sentence in the panel, click Add to chat, and tell her what to change.

Skills and knowledge notes are listed in their feature’s hub, in their own Skills and Knowledge lanes — visible, browsable, and owned by the team, not buried in a model.

Pin down your definitions — knowledge notes

Section titled “Pin down your definitions — knowledge notes”

“Active revenue is net of refunds and excludes one-time fees — it comes from the subscriptions table, not orders.”

That sentence, spoken once in a chat, becomes a knowledge note: the metric’s real calculation, which tables and columns it uses, and the caveats, recorded beside the data it describes. From then on, “show me active revenue” means your active revenue — the same definition for the analyst who wrote it and the account manager who never will.

Set the rules of the house — organization Knowledge

Section titled “Set the rules of the house — organization Knowledge”

Some knowledge is bigger than any one feature: reporting currency, fiscal calendar, what words mean at your company. That belongs on the Knowledge page — an organization-wide knowledge base that Ronja largely builds up herself as she works with your data, and that admins curate.

Curation follows one deliberate principle: tell, don’t edit. There is no edit button on organization Knowledge — and that’s the feature, not the gap. An admin clicks Curate in chat, which opens a conversation with the Organization Knowledge panel alongside, and simply says what’s wrong:

“Our fiscal year actually starts in April, not January.”

Ronja rewrites the knowledge herself — you’ll see the panel pulse updating… as she works — and a single correction can update several related entries at once, keeping the whole knowledge base coherent instead of patching one page. Highlight any sentence in the panel and Add to chat to point her at the exact text that’s wrong.

The Organization Knowledge panel open beside a chat while Ronja updates a knowledge entry Tell, don’t edit: describe the correction in chat, and Ronja rewrites the knowledge herself.

The payoff is the compounding step: the core of organization Knowledge is injected into every conversation automatically. Fix the fiscal year once, and every conversation anyone has from that moment on groups quarters correctly — and the next workflow Ronja writes inherits the same rule. Curation is admin-only; the knowledge itself acts on every conversation. See Curate Knowledge.

There’s a single exception to “tell, don’t edit”: your personal memory, on your account page’s Memory tab — up to 2,000 characters about you, directly editable. Your role, your preferences, how you like results presented. It personalizes your answers without touching anyone else’s.

The fact Where it goes
“Always report money in SEK” Organization Knowledge — applies everywhere, for everyone
“Active revenue = net of refunds, excluding one-time fees” A knowledge note in the feature that owns the data
“How we build the weekly revenue report” A skill note — a procedure Ronja can follow
“I prefer tables over charts” Personal memory — yours alone

For notes, don’t overthink the routing — say it in chat and Ronja files it in the feature. Organization Knowledge is curated by admins, and personal memory you edit yourself on your account page. The table is for checking her work.

All of this is governed like everything else in Ronja — shared notes go through drafts and admin review, versions are kept, and every entry is readable by the people it affects. Which means the knowledge is trustworthy, not just present.

Spend an hour in week one correcting Ronja, and week two starts from a smarter baseline. Definitions stop being re-litigated. New teammates inherit the company’s context on day one, because the agent they ask already knows it. That’s the quiet difference between a tool that answers questions and a coworker who’s been paying attention.