Auxot
Tutorials Docs Pricing Login

View your audit logs

Open the Audit Logs page to see every job that's run, every conversation that's happened, and every system event — in one searchable, live-updating view.

Plus: three pasted Admin-Agent briefings — investigating anomalies across Jobs/Threads/Events, tightening compliance paragraphs before leadership forwards them, and finding which agent quietly used most of last month's token budget.

Audience Admins
Time ~3 min
Prerequisites An Auxot account on any tier. You've been using Auxot long enough to have something to look at — at least one chat conversation, one agent job, or one system event in the past few days.
You'll end up with A clear sense of what each Audit Logs tab is for, which filters narrow the noise, and sample Admin-Agent prompts to use when scrolling through rows by hand isn't getting you anywhere.

When a tutorial shows italic text in quotation marks, it usually mirrors a label or helper string inside Auxot. Product copy changes between releases — if something reads differently in your workspace, trust what you see on screen.

Callouts with a Worth knowing gold accent are meant as must-read context before you move on. Blockquotes that open with Tip are lighter, optional depth.

Why this matters

Auxot logs everything that happens: every chat, every job, every agent action, every login, and every configuration change. Audit Logs is the page that lets you see all of it.

Most days you work in Chat; Audit Logs is the page you open when you need to look back: who routed what tokens where, whether a person started a chat or a webhook or cron job did, and whether a customer’s account of events matches what’s in the records.

The page has three tabs because three different kinds of activity matter: Jobs (the background work your AI is doing), Threads (the conversations happening with your agents), and Events (system-level things like configuration changes and scheduled triggers). Each tab has filters so you can narrow the noise. Live mode keeps the page refreshing as things happen.

Today, learn what’s in each tab. When something looks off, you know exactly where to look.

Audit Logs gathers every job, every conversation, and every system event into one searchable view. Filter by status, time range, source, severity, or agent. Toggle Live mode to watch activity in real time. Click any row to see the full detail underneath.

Quick start

  1. Sign in: open Auxot in your browser and log in.
  2. Open Audit Logs: click Audit Logs in the left menu.
  3. Pick a tab: Jobs (background work), Threads (conversations), or Events (system activity). Start with Threads if you want to see what your agents have been answering lately.
  4. Apply a filter: narrow by time range, status, source, or severity, depending on the tab.
  5. Click any row: see the full detail of that job, thread, or event underneath.

Done? You’ve taken your first look at the Audit Logs page. The rest is knowing which tab to open when something specific comes up.

The agent can do that?

Endless scrolling under incident pressure isn’t a useful default. Use the same approach as Take Auxot’s pulse in 10 seconds: paste the symptom into Admin Agent chat first; skim what comes back; then open specific rows yourself if the situation calls for detailed evidence.

1. Triage weirdness inside a time window

Chat → Admin Agent:

Something feels off in our Auxot account in the last [hour / day / week] — slower replies, weird answers, an integration acting up, anything. Look at recent events, recent jobs, and any errors. Tell me what's worth investigating, what's probably nothing, and what I should check first.

Why it’s non-obvious: Filters work better once you have a hypothesis. Paste the symptom into Chat first; the Admin Agent summarizes what’s visible because you asked, not on his own. You still need to open specific rows yourself if the result has to hold up in a formal review.

2. Run a compliance check

Same chat, follow-up:

For compliance, I need a summary of what [user name or team name] has done in Auxot over the past [time range]. List their thread count, the agents they used most, any failed jobs, any sensitive actions (role changes, credential changes, and agent edits), and anything that looks unusual. Be specific.

Why it’s non-obvious: Compliance reviewers want a narrative; the database returns raw rows. Paste your ask and the scope into Chat; the reply stitches threads, jobs, and events into paragraphs worth forwarding. Your sign-off still matters before HR distributes anything externally.

3. Find the agent quietly eating tokens

Which of my agents used the most tokens last [week / month]? Break it down by agent, what kind of work the tokens went to, and whether any of them are using more than I'd expect for their job. If any look out of line, recommend specific things to investigate or change.

Why it’s non-obvious: You don’t need a spreadsheet. Token usage often grows inside ordinary agents that loop over large context files. Paste the prompt block above; the summary will group Jobs by agent because you surfaced the question. Follow up on the agents the summary flags. See Give your agent its job description for context trimming if the numbers still look off.

Go deeper

Retention and export

Retention: Audit logs in Auxot’s database don’t currently expire: old records stay queryable indefinitely. (The live activity feed on System Health is separate; that’s a 20-minute sliding window in Redis.)

Export: Audit Logs doesn’t currently have a built-in CSV/JSON export from the UI. If you need to pull records for an external tool (a SIEM, a compliance platform, or a quarterly report spreadsheet), you’d use Auxot’s API directly, with a Team API Key (Create a shared Team API Key). The Admin Agent’s list_events tool also returns structured data that you can copy out of chat for one-off needs.

Troubleshooting
  • The page is blank: “No jobs found” / “No threads found” / “No events found”. Likely a filter is hiding everything. Check: is your time range too narrow? Are you on the right tab? Is your account too new to have any history yet?
  • Live mode isn’t refreshing. The 5-second refresh runs from your browser tab. If your tab is in the background, browsers throttle it: bring the tab forward and refresh once.
  • A job shows “Failed” but you don’t know why. Click the row. The detail view shows the error message. Common causes: provider over quota, credential expired, the agent’s tool returned an error, or the model timed out.
  • A thread is missing. Confirm the thread is on a team you have access to. If it should be in your scope but isn’t appearing, the source might not be flagged correctly: check the source filter.
  • You see jobs but no provider information. The provider was deleted after the job ran. Auxot keeps the job record but the provider link goes stale.
Variations & edge cases
  • Free tier has the same Audit Logs page as paid tiers: no feature gating here. Activity volume is naturally lower (one user, one team), so filters matter less.
  • Cancelling a running job marks it as cancelled but doesn’t undo work that’s already happened (e.g., a tool call that already executed). Use cancel to stop ongoing work; for true rollback, you’d need agent-level logic.
  • The “Recently completed” data on the Jobs tab is fast-moving. Don’t bookmark a specific row to come back to later; use the time-range filter and search instead.
  • Cron-triggered threads show up under the Threads tab with source = cron. Useful for monitoring whether your scheduled agent runs are actually firing.
  • Webhook-triggered threads show up with source = webhook. The thread name will reference the intake or workflow that received the call.
  • Token usage in Jobs is per-job (input → output). Multiply mentally for weekly totals, or reuse the pasted prompt from power move 3 when chatting with the Admin Agent is faster than working it out by hand.

Walkthrough

Step 1: Sign in

Open Auxot in your browser and sign in.

Step 2: Open Audit Logs

Click Audit Logs in the left menu. The page opens with the helper text that frames it well: “Review background jobs, threads, and system activity in one place.”

You’ll see three tabs across the top (Jobs, Threads, and Events) and a Live toggle in the top right. We’ll cover each tab next.

Step 3: The three tabs (what’s in each)

a. Jobs

Every time an agent runs work (answers a chat, executes a tool, processes a task), Auxot creates a job that runs in the background. The Jobs tab shows every one of them.

Each row shows:

  • Status: queued, running, complete, failed, cancelled, or retrying.
  • Agent name: which agent the job was for.
  • Model and provider: which AI model handled it (Claude, GPT-4, your local GPU, etc.) and via which connected provider.
  • Job type: what kind of work it was.
  • Token usage: input tokens → output tokens (useful for spotting cost surprises).
  • Evaluator status: whether Auxot’s quality check liked the result.
  • Timestamp: when the job ran.

You can also cancel a running or queued job by clicking the cancel icon on its row. Useful when you realize a runaway loop is spinning.

b. Threads

A thread is a conversation: anything from a chat-window conversation to a Slack message that triggered an agent to a webhook that started a task. The Threads tab shows them all, regardless of source.

Each row shows:

  • Source: where the thread came from: app (the chat window), Slack, Discord, email, webhook, cron, or other integration.
  • Type: chat (interactive) or cron (scheduled).
  • Agent name: which agent handled the conversation.
  • Message count: how many back-and-forth turns there were.
  • Snippet: first 30 characters of the latest message (so you can roughly tell what it was about).
  • Timestamp: when the latest activity happened.

This is where you go when you need to see what an agent has been answering lately, or trace a specific conversation that came up in a customer report.

c. Events

Events are the system-level happenings: agent evaluations, cron triggers firing, configuration changes, and errors. Each event has:

  • Event type: a short identifier like cron.fired or agent.evaluation.
  • Severity: info, warning, or error.
  • Description: what happened, in plain English.
  • Agent ID (optional): if the event was tied to a specific agent.
  • Timestamp: when it happened.

Events are how you spot configuration-level oddities: a cron that’s not firing, a credential that just got revoked, or an integration that lost its connection.

Each tab has its own filters. Common patterns:

  • Time range (Jobs, Threads): All Time, Last Hour, Today, Last 7 Days, or Last 30 Days. Last 7 Days is the most useful default for most questions.
  • Status (Jobs only): All Status, Complete, Failed, Running, Queued, or Cancelled. Pick Failed to spot trouble fast.
  • Source (Threads only): all sources or one specific source: useful when you want to see only your Slack-triggered conversations, for example.
  • Severity (Events only): All Severity, Info, Warning, or Error. Pick Warning or Error to skip the noise.
  • Search: text search by ID or model name (Jobs), or by event type (Events). Debounced: wait a moment after typing.

Tip: When you’re investigating something specific (an incident, a cost spike, or a customer report), filter aggressively. The page is designed to drown you in data unless you tell it what you’re looking for.

Step 5: Click any row for detail

Every row in every tab is clickable. Clicking opens a detail view with the full record: for a job, the prompt and response; for a thread, the conversation transcript; for an event, the full metadata.

This is where most investigations actually happen. The list view is for finding the right row; the detail view is for understanding what happened.

Step 6: Live mode for real-time monitoring

Toggle Live in the top right when you want the page to refresh every 5 seconds automatically. Helper text: “While Live is on, the list refreshes every 5 seconds so you do not need Refresh.”

Use Live mode when:

  • You’re watching something happen right now (e.g., kicking off a workflow and wanting to see jobs appear).
  • You’re monitoring during a deploy or change and want to spot errors as they show up.
  • You’re debugging an unreliable integration and want immediate feedback.

Don’t leave Live on all day: it costs nothing on Auxot’s end, but the constant updates can be distracting when you’re trying to focus on a specific row.

What’s next

Reference

Browse all tutorials