All spotlights

Product spotlight · October 2026

See who uses AI and let your own tools post in Slack

The AI platform adds a searchable AI audit log, a Slack bot messaging API for your own tools, spend warning emails and Australian-only model lists on QuantGov.

Updated AI platform For government and enterprise

What changed in October 2026

The October 2026 changelog has the full details.

  • AI audit log

    A new AI audit log page in the AI menu lets organisation owners and admins search the organisation's AI audit records. The records show who used which model and tool. You can read records from the last 365 days, and every search, record view and download is itself recorded in the log.

  • Slack bot messaging API

    Your own tools can now read and post in Slack through a Quant Slack bot. A token with the ai:slack scope can read recent messages and threads in the channels you choose, post messages and upload images.

  • Spend warning emails

    When your organisation's AI spend reaches the warning threshold set in AI governance, everyone with AI governance permission receives an email, at most once a month. The email shows spend against the monthly budget and says whether requests are already blocked because the budget is reached.

  • Australian-resident models on QuantGov

    On QuantGov, the model pickers, the models API and AI governance list only models that run in Australia. An allowlist or blocklist cannot add others. When the AI API refuses a model outside your region, it returns model_not_available_in_region, and the dashboard asks you to select a different model.

  • Filter policies for single agents

    Built-in filter policies that are off by default now appear in the agent editor and on the Governance page, labelled as off organisation-wide. You can apply one to a single agent or add it to the mandatory list.

  • Stop a running workflow

    The workflow editor now has a Stop button on running and paused runs. If a run cannot be stopped, for example because it has already finished or runs inline, the editor says why.

By the numbers

of AI audit records to read
365 days
at most per audit log search
31 days
per minute per bot, at most
60 writes

Who it is for

  • Governance and audit

    Search who used which model and tool, download records as JSON Lines, and get an email at a spend warning threshold.

  • Teams that work in Slack

    Let your own tools read recent messages and post updates or images in chosen channels through a Quant Slack bot.

  • QuantGov organisations

    On QuantGov, model pickers and the models API list only models that run in Australia, so AI requests stay there.

How it works

In the AI audit log, you can filter a date range of up to 31 days by user, API token, model, record type, decision, tool, outcome or interface. You can open a single record and download the results as JSON Lines.

New v3 API endpoints also return the same records to tokens with the new ai:audit:read scope. Full-access tokens include this scope. If you have AI governance permission, you can also export a date range from the Export audit log card on the Governance page.

The Slack bot messaging API lets your own tools use a Slack bot that you already manage in Quant. In the Slack bot editor, turn on API access, choose the bot’s API channels from its allowed channels, and set a limit of 1 to 60 writes per minute. A token with the ai:slack scope can then list the bots it can use and read recent messages and threads in those channels. It can also post messages, and upload PNG, JPEG, GIF or WebP images of up to 4 MiB with an optional caption, title and alt text.

Each post includes a line that names the person who sent it. An optional Idempotency-Key header stops a retried request from posting twice. Full-access tokens do not include ai:slack, so create a token with that scope. The token’s owner needs a verified email address.

Streamed /oai/v1/chat/completions requests that set stream_options.include_usage now receive the usage chunk, and the reasoning_effort parameter now works. See the October 2026 changelog for every change.

Get started

  1. Open the AI audit log

    As an organisation owner or admin, open AI audit log and filter up to 31 days.

  2. Set a warning threshold

    In AI governance, set a spend warning threshold. Leave it empty for no email.

  3. Turn on Slack API access

    In the Slack bot editor, choose API channels and a limit of writes per minute.

  4. Create a scoped token

    Create an API token with the ai:slack scope. Its owner needs a verified email.

  5. Call the messaging API

    Send requests to /api/v3/organizations/{organisation}/ai/slack-bots.

Related: Explore AI platform · Documentation · October 2026 changelog

Ready to try it on Quant?

Use the AI platform on your own project, or talk to our team first.