# Run profile - Obss

Read results
Run profile
See whether the agent used each tool in the treatment, where its tool calls and time went, and what stood out in the run.
Check the
Run profile
to confirm the agent used the treatment before you trust its pass rate. It’s the right rail of every run tab, tops each
Traces
column in
Compare
, and is available from the CLI and the plugin.
Counts and times are exact or absent: Obss never estimates a missing count or time.
Treatment use
Treatment use
says whether the agent used each skill, MCP server, CLI, or SDK in the treatment. The
Runs
list uses the same states for the whole treatment, and a blank cell there means the run has no run profile (see
When the profile cannot answer
).
State
What it means
Used
The log shows the agent used it. The count is how many tool calls it served.
Not used
It was available for the whole run, and the agent never used it.
Not measured
The log can never show its use, for example an SDK called from the agent’s own code.
Can’t tell
The log can’t show it either way, for example a CLI run from a script, a log with no tool calls, or one call that named two tools.
Obss decides use from the agent’s log:
Tool
Counts as used when
Skill
The agent reads a file in the skill’s folder or calls its skill tool.
MCP server
The agent calls one of the server’s tools.
CLI
A shell command runs it directly, including inside a loop, an
if
block, or
bash -c
.
SDK, or a service the machine started
Not measured from the agent’s log
A CLI counts under its command name and every other name its package installs:
@brightdata/cli
, for example, installs
brightdata
and
bdata
. Obss reads those names from the package’s registry entry when the CLI pins an exact npm or Rust (crates.io) version, or installs with Go. A CLI run through another program (
npx
,
sudo
,
timeout
) or a script doesn’t count, so a CLI no command ran directly shows
Can’t tell
, not
Not used
.
When the log can place the first use, the row names that turn or step.
Not used
is a fact about this run, not a pass or fail result.
Tool calls
Tool calls
counts every tool call the agent made, split by what served it: a launched skill, MCP server, or CLI, or
Other tools
. A call that matches more than one of them counts toward none, and
Evidence warnings
says so.
What stood out
What stood out
lists patterns that meet fixed thresholds:
The same tool call repeated with the same input.
Input that grew by at least 10,000 tokens and by at least 10% in one turn.
A tool call that took at least 5 seconds and at least 5% of the agent’s working time.
A gap of at least 10 seconds between two turns, and at least 3 times the run’s median gap, unless a slow tool call above already explains the gap.
Each line links to its turn or step on
Traces
. An empty list means no pattern met a threshold, not that the run had no problems.
Time
Time
splits the run into its recorded phases:
Phase
What it covers
Machine setup
Building and starting the machine and its services
Agent setup
Installing and configuring the agent
Agent working
The agent’s turns and tool calls. When the agent reports tool call times, they show here as
Treatment tools
and
Other tools
. No agent reports model time separately, so it isn’t split out.
Saving output
Saving the agent’s changed files and outputs after it finished, and checking them for secrets. It doesn’t grade the run.
Other overhead
Elapsed time the phases above don’t cover, such as stopping the machine
A phase with no recorded time is hidden. When phases overlap, the profile says
The phase times overlap, so the total isn’t split.
When no phase has a time, it says
No phase times were recorded for this run.
Token totals and cost appear with the time, and an unreported cost stays blank, not $0.
When the profile cannot answer
While the run is going, the profile says
The profile appears when the run finishes.
If none was recorded, it says
No run profile was recorded for this run.
A partial profile shows the sections it can, and
Evidence warnings
names the limit:
No readable agent log was captured for this run.
This run has no record of what it launched, so its calls can’t be matched to what served them.
The agent’s log says what served each call, but leaves some calls out.
The agent’s log names a skill, MCP server, or CLI that this run didn’t launch.
Some calls match more than one launched skill, MCP server, or CLI, so they count toward none.
The agent’s log records no tool calls, so it can’t show whether the agent used what the run launched.
A warning means that part of the evidence is incomplete. It never adds a cause that the log doesn’t support. An unknown warning says
Run evidence needs review.
From the CLI and the plugin
Task
CLI
Plugin (MCP)
Read one run’s profile
obss runs profile
get_run_profile
List runs with their treatment use
obss runs list
list_runs
Next steps
Evals
Learn how Evals mark each run against its rubric.
Frictions
Find the problems that agents hit across runs.
Measure a tool's impact
Compare a tool with the baseline.
obss runs and results
Read a run’s profile with
obss runs profile
.
Run details
Share results
Powered by
This documentation is built and hosted on Mintlify, a developer documentation platform