Analytics & Reporting

The Unbound dashboard provides analytics at several levels — from organization-wide summaries down to a single task trace, plus a full inventory of the AI tools running across your fleet. Analytics answers what your agents did. AI Tools Discovery answers what your developers have installed. Most teams use both.

​

Analytics

Dashboard: gateway.getunbound.ai/analytics

​

Overview

Organization-wide spend and activity at a glance — cost and token consumption over time, how spend and prompts split across models, and how many agent actions were allowed, warned or blocked. The three headline figures each carry a comparison against the period before them. Start here before drilling into any one team or developer.

​

Tasks

Every agent task, classified by the kind of work it was doing, with cost and token consumption attached. Spend is broken out by work type — feature development, bug fixes, testing, refactoring — and by repository. Tasks are listed newest first, and a task still waiting for its summary and work type is listed too, showing its first prompt instead.

​

Agentic Use

What your agents did, split into three views:

• Terminal Run — the shell commands agents executed, with a risk level on each.
• MCP Actions — the MCP servers and tools agents called, with risk categorization and per-user and per-server breakdowns. Open a server and you get its own view: how many calls, their average risk score, how many were high risk, how many developers made them, which tools were used, and the trend over the window. A Tool Calls / Audit Logs switch there turns the classified view into the raw call history — every MCP call with its tool name, the developer who made it, and when, expandable for the exact arguments sent and the output returned. Large values are shortened in two ways, and the page tells you which applies. A call whose arguments or output were too large to keep whole carries a note with the original size, and what you see is a preview. Anything over 4,000 characters is trimmed on screen with a Show full link. Audit Logs may not be enabled for your organization; where it is, it reads to Admins and Analytics Viewers.
• Skills — which Agent Skills were actually run, by whom, and through which agent. See Skills below.

Each action is attributed to a user and session, and carries the policy that matched it and what that policy did. This is the fastest way to see where a Tool Policy would have the most impact: watch the traffic, then write the rule. Terminal Run, MCP Actions, unsanctioned MCP usage and the MCP server list can each be exported.

​

Data

Every time a Security Policy guardrail fires — sensitive data like PII or a secret detected in a prompt, and whether it was audited or blocked — it lands here. Two views:

• Summary — Top Tools with Guardrail Actions: which AI tools are triggering the most guardrail activity, as a table of tool, guardrail, action, and hit count. Start here to see where sensitive data is concentrated.
• Logs — the individual events behind those counts, each with its timestamp, tool, user, the guardrails that fired, and the action taken. Filter by tool type, guardrail, or action, and open any event for the full detail.

Click a row in Summary to drop straight into Logs pre-filtered to that tool, guardrail, and action. Go back to Summary and that drill-down clears itself, while any filters you set by hand stay put. Security Policies decide what to catch; this tab shows what they caught.

​

Usage

Beta. Two views of how your organization is using AI, at Analytics → Usage. Adoption reports take-up: weekly and monthly active users, a Claude Code Users · WAU figure, an Adoption Funnel from seats through to weekly habit, Weekly Active Users by agent, and Adoption by Team. Choose a window of 4, 8 or 12 weeks; every chart compares against a 50% adoption target. The team breakdown is built from the Okta directory sync. Account Usage reports which vendor accounts your developers are signing in with. Account Access refusals are not here — they live on the policy’s own page, under Policies → Usage. Adoption is licensed per organization. Account Usage is available to every Admin and Analytics Viewer.

​

Users

Per-developer activity, oriented around how agentic each developer’s workflow is: how long their agents run unattended, median run length, clean-completion rate, how many tasks they worked on, tokens, cost, and how many distinct models they used. Across the top: active users, tokens used, how many developers have reached a steady clean-completion rate, and your single heaviest consumer. Open a developer to see which models they actually leaned on and what share of their spend each one took. Use it to see which developers are getting real leverage from agents, and which are still babysitting every step. Clean-completion rate and median run length stay blank until a developer has enough agent runs in the window for the number to mean something — a quiet week reads as blank, not as zero. Every figure column sorts: Total Tokens descending for your heaviest users, ascending for your lightest.

​

Task Logs

Dashboard: gateway.getunbound.ai/logs Every agent session, logged with full prompt-level detail — messages sent and received, models used, token counts, tool calls made, and policy decisions. Filter by user, model, tool type, or date range, then click any task to trace the whole conversation end to end.

​

AI Tools Discovery

Dashboard: gateway.getunbound.ai/ai-tools-discovery Analytics shows you the agents routed through Unbound. Discovery shows you everything installed across your fleet — including the tools nobody told you about. It’s powered by unbound discover.

​

Summary

The fleet at a glance: how many AI tools are in use, how they’re distributed across your org, and which users carry the most risk. From here you can sanction the agents you approve of — everything else is surfaced as unsanctioned, which is how you find Shadow AI.

​

Inventory

The full catalogue of what Discovery found, in four views:

​

Users (Discovery)

Discovery from the people side — what each developer has installed, rather than what’s deployed across the fleet. Open any user for a per-user risk view: their tools, their risk factors, and what’s driving their score.

​

Permissions

What your agents are permitted to do on each machine, with recommendations on the permissions worth denying.

​

Skills

Dashboard: gateway.getunbound.ai/analytics/agentic-use?tab=skills — a sub-tab of Analytics → Agentic Use, not a page of its own. Which Agent Skills your developers are actually running — how often, by whom, and through which agent. AI Tools Discovery tells you which skills are installed across your fleet; this tells you which ones get used. Headline numbers up top — total invocations, distinct skills used, and how many developers used them over the period — then a daily invocation trend, your most-invoked skills, and a breakdown of which agent (Claude Code, Cursor, and the rest) each skill was called from. Filter the whole view by skill, tool, user, or time range. The All Skills table lists every skill with its invocation count, unique users, the tools that ran it, its categories, a risk level, and when it was last used. Open any skill to see its usage over time, its top users, and the rendered SKILL.md content itself — including each distinct version when several copies of a skill share one name across your fleet.

​

Custom Reports

Dashboard: gateway.getunbound.ai/custom-reports Query your Unbound data in natural language, or with a structured builder. Example queries:

• “Which users ran the most delete commands this week?”
• “What models did my team use most in April?”
• “Show me all policy matches grouped by command family”

Queries can be saved, shared with your team, and assembled into Dashboards — reusable boards of the reports your team checks regularly.

​

Cost reporting

For cost-focused reporting, see Cost Policies and Analytics — Overview.