Ask in plain words
Type the question the way you would ask an analyst, including nicknames, ratios and relative dates.
A clearer view
of your business.
Good decisions begin with a good question. Ask yours in plain language, explore the answer, and keep the view that matters. Your business data, thoughtfully understood.
Private by designYour rows stay out of model prompts.
Open to inspectionSee the query behind every answer.
A question, exploredInteractive demo
Top 3 categories by revenue in Q3 2025
Guard and budget
Prompt Guard 2 classifies the text as a normal question
Length, characters and your per-minute question budget checked
Only approved catalog labels are attached to the request
How AIDA works
From a question to a point of view.
Start with the words your team uses. AIDA connects them to definitions you approve, checks the query, and gives you an answer you can explore.
A shared understanding
It maps each phrase to an approved measure, grouping, value or time period, or asks you to choose when a name is ambiguous.
A carefully checked query
Grounding, coverage, approved values and capability limits are verified before anything runs.
An answer you can explore
Read-only SQL runs inside AIDA. Charts, tables, SQL and lineage show exactly how the answer was produced.
Security by design
Confidence, with a paper trail.
Pick a layer to see a real attack it is tested against. Each scenario is covered by an automated test in the AIDA backend suite.
Accounts and sessions
Passwords are hashed with scrypt. Sessions live in HttpOnly, SameSite=Strict cookies, are stored only as hashes, rotate at sign-in and expire when idle.
Attack scenario
Twelve password guesses against one account in a minuteThe account locks for 15 minutes after 5 failures, and the error never reveals whether the email exists.
Privacy you can inspect
Your data deserves discretion.
AIDA shares your question and an approved business vocabulary with the model. Database rows, query results and connection credentials stay inside AIDA. Explore exactly what is shared below.
Your question text
Approved measure and grouping labels
Plain-language definitions you approved
Owner-approved filter values
The dataset’s date range and as-of date
What each source can and cannot answer
Capabilities
Follow the question. Find the useful detail.
Name resolution that asks
An LLM maps everyday words to your approved definitions. When a name is ambiguous or unknown, AIDA asks you to choose instead of guessing.
Calculations in code
Ratios, differences, share_of_total, running_total and percent_change are computed after aggregation, never estimated by the model.
Time that makes sense
Calendar periods, “last month”, trailing windows and explicit ranges resolve against the dataset’s as-of date. Forecasts are refused, not invented.
Joins you approved
Relational sources follow approved relationships for related records, archived history and above-average comparisons, with lineage for every table touched.
Interactive results
Switch between bar, line, area, donut and scatter charts. Search, filter, sort and page through tables, then export exactly what you filtered.
Dashboards without re-asking
Saved analyses store the validated plan, so refreshing a dashboard runs SQL directly with zero model calls.
Benchmarks
The detail behind the answers.
Real questions through the real pipeline, scored against independently written SQL. These figures are read directly from the recorded benchmark runs.
48.1% → 70.4%correct on the 27 questions every compared run answered: gpt-oss-120b · Previous pipeline → Qwen3.8 27B · AIDA 4 · prompt 1 · repair 0
3 → 0wrong or unsafe answers on those same questions
112/112answers with a correct plan that also returned the correct rows, across 5 runs
10/10requests correctly refused or clarified by Qwen3.8 27B · AIDA 4 · prompt 1 · repair 0
These questions are a regression set, not a blind test. See every run, chart and question →
Onboarding
Make room for your next question.
1
Create your account
Sign up and make a home for the questions your team asks.
2
Tell us about your team
Company, role and the areas you care about shape your starting point.
3
Choose your data
Start with a sample, connect a database, or upload a reporting snapshot.
4
Ask and verify
Review what is shared with the model, then ask. Every answer shows its plan, SQL and lineage.