This section documents, honestly and verifiably, everything ingestia.io does with "intelligence" — from purely mathematical (deterministic) calculations to the features that send data to an Anthropic large language model (LLM).
A single principle organizes every page:
The product's AI refuses and warns — it does not pretend. When there is no evidence, it says there is none. When the data is a sample, it warns you. When it cites a number, that number has to be in the data it received. Nothing here claims cause and effect that the data does not prove.
The most important thing: deterministic ≠ LLM#
The product has two families of "intelligence", and they are very different in privacy, cost and guarantees. Do not confuse them.
| Family | What it is | Sends data to an LLM? | Token cost | How it is proven |
|---|---|---|---|---|
| Deterministic | Pure calculations (statistics, regression, threshold comparison) running on our server | No. Never. | Zero | Reference tests with identical results on every run; reproducible results |
| With LLM | Sends context to an Anthropic model and uses the response | Yes (subject to the kill switch) | Yes (metered and capped) | Deterministic verification over the LLM output (citations, ids, filters) |
Anomalies, forecasts and alerts are DETERMINISTIC — there is no LLM in them, no data leaves the product, and the result is reproducible bit for bit. An LLM never decides whether something is an anomaly, never projects a series, and never fires an alert.
Text-to-SQL, Q&A, insights, report narrative and assisted generation use an LLM — and that is why they go through the egress, budget and refusal controls described here.
Capability index#
Use an LLM (Anthropic)
- Text-to-SQL (natural language query)
- Dashboard Q&A (questions with verifiable citations)
- Dashboard insights ("explain this dashboard")
- Report narrative (the "AI Analyst")
- Aiô — the AI that helps on any screen
- Assisted generation (measure / visual / dashboard)
Deterministic — no LLM, no egress
Cross-cutting
Required template for capability pages#
Every capability page follows the same template: the Engine line at the top and 9 fields. The Engine says whether the capability runs only on our server (deterministic) or sends data to an LLM.
The 9 fields
- What it does — in one sentence, the value to the user.
- Deterministic or LLM? — the engine, and which model/version when there is an LLM.
- Data sent and egress — exactly what leaves the product (and what never leaves).
- Privacy and retention — PII, RLS, where the record is kept, and for how long.
- Tokens, cost and budget — reservation→settlement and monthly cap (or "not applicable").
- How to turn it on, who can use it and how to turn it off.
- Refusals — when and how the capability declines to answer instead of making something up.
- Limitations and absence of causality — what it does NOT do; no unproven cause.
- How to validate — concrete steps to check each claim above.