All our work

AI engineering · Climate data, nonpartisan fact tank · Australia

OnlyFactsOnlyFacts

Two agents on one data layer, and not a single number from memory.

OnlyFacts publishes the Australian climate data that newsrooms quote by name. We built the agent that answers their readers in plain English, grounded in a live query every time, and cited like everything else on the site.

At a glance

Engagement
2025 to ongoing
Status
Live in production
What we built
Two agents on a dedicated data layer
Licence context
Data published under CC BY 4.0, free to republish with attribution

What changed

What changed

Before

Readers hunted nine data sections, then emailed the team.

Now

A reader gets the figure they came for in one question.

And the answer carries its source, so it is safe to republish.

Data tools, one per view
190
Less data per report
75%
Weeks to a working pilot
< 3
Agents on one data layer
2

The ask

A reporter is filing on deadline. She needs one number: electric vehicle registrations in a single Sydney postcode, against the rest of New South Wales. It is published, but reaching it means working out which of nine data sections holds it, reading a ranked list thousands of rows long, then opening more pages for the state and the prior year.

Most give up and email the team. Hours of a small team’s week went on answering questions the database could already answer. And OnlyFacts publishes under CC BY 4.0, so a wrong number does not sit on the site waiting to be corrected. It travels.

What we built

A data layer, not a chatbot

So we did not point a general model at the site. We built a dedicated data layer of 190 tools, one per published view, each bound to that view’s chart type. The agent cannot ask what the site cannot answer. Every sum goes through a calculator call, the open web is switched off, and every figure is shown with the query that produced it.

  • Essential Agent

    Live on onlyfacts.io. Answers at national, state, LGA and postcode level, grounded in the database.

  • Deep Research agent

    Takes a multi step question and returns one synthesised report, at 75% less data per run than the naive approach.

  • Guardrails, not vibes

    No open web, no uploads, no code execution. Asked for a projection it cannot support, it declines in plain words.

The method

How it answers one real question

Taken word for word from the live agent: “What is Australia’s emissions trend with state and sector breakdowns?”

  1. 01

    Answerability check. It confirms every dimension exists before any tool runs. If one were missing, it stops and offers three questions it can answer.

  2. 02

    Query the data. Two separate tool calls, national then by state. It may not bundle two questions into one query.

  3. 03

    Calculator, not head. The gap to the 2030 target, 43 minus 24.7 equals 18.3, is worked out with a calculator call rather than in its head.

  4. 04

    Answer, cited. A named actor in every sentence, neutral verbs, and a footnote on every figure, sourced to the DCCEEW inventory.

Built to last

Why it keeps working

Nothing ships until it clears four checks.

  1. 01

    The risk

    Most AI projects quietly get worse. The model updates, the wording drifts, and nobody notices until a reader does.

  2. 02

    The guard

    Does the number match the database? Is that the right chart for this data? Is the citation there? Has a banned word crept back in?

  3. 03

    What it allows

    OnlyFacts can switch to a newer, cheaper model the week it launches. We run the suite and show the answers did not change.

Beyond this client

The job transfers

The same problem turns up well beyond this one client. These are the teams it fits.

Anyone held to their numbers

  • Research desks
  • Regulators
  • Investment committees

Anyone who publishes data

  • Compliance teams
  • Clinical registries
  • Statistical agencies

What the client says

AvestaLabs has been an indispensable partner for OnlyFacts. Their development of AI agents on our proprietary datasets combined deep technical expertise with innovative problem-solving and sound strategic advice. They have become a collaborative and trusted extension of our team.
Juliette O’Brien OAMCEO and Co-Founder, OnlyFacts.io

Next case study

All our work

Exam services provider · Product development

15 million answerbooks digitised, 100% recorded uptime

Read case study

Facing something similar?