# Insights - Obss

Evals and Insights
Insights
See where agents got stuck in each run, what Insights read, and how those problems become your project’s frictions.
Where
Evals
check a run’s outcome,
Insights
check how the agent got there: failed calls, missing context, long detours, and wasted retries. Obss groups those problems into your project’s
frictions
so you know what to fix first.
Two models do this work. The
Insights model
reviews each run and reports the problems the agent hit. The
Experiment insights model
matches each problem to an existing friction or names a new one. It also writes the sentence in each
Brief
, the note under a difference on
Comparisons
. An experiment without Insights has no Brief.
Insights don’t read the changed files or change Evals verdicts. A run can have Evals, Insights, both, or neither.
Turn on Insights
1
Assign the models
Assign the
Insights model
and the
Experiment insights model
under
Organization settings →
Obss AI features
.
2
Choose Insights for an experiment
Turn on
Insights
when you
launch an experiment
, or choose
Run insights
on an experiment that already ran.
3
Read the frictions
Frictions
appear on the experiment’s
Frictions
tab, on
All frictions
, and on each run’s
Traces
at the steps they cite.
Choose a mode
If your organization has Agent mode for Insights, pick a mode when you launch, or in
Run insights
or
Rerun Insights
. Both modes use your
Insights model
and
Experiment insights model
, and report frictions in the same way.
Mode
How it reviews
Standard
Reviews each run in one pass with your Insights model. It’s the fastest and lowest-cost mode.
Agent
(private beta)
Obss’s insights agent reads the whole run and checks each friction against what the tools returned. It costs more and takes a few minutes per run.
In Agent mode, each difference on
Comparisons
also shows
what the runs did differently
.
What Insights read
Your
Insights model
reads the run’s recorded steps. If the run doesn’t fit the model’s context window, a note above the
Timeline
on
Traces
(and on each
Traces
column in
Compare
) says what was left out:
A numbered range of steps didn’t fit. The model gets a count of those steps by kind and tool instead.
A long step was shortened.
Some friction signals were shortened.
The trace is larger than the 32 MB limit for one run file, so the steps couldn’t be read.
No note means the model read everything. A friction covers only what the model read. In
Agent mode
, nothing is shortened, so a note shows only when the saved run is incomplete, for example when the trace was too large to save.
If the work still doesn’t fit after Obss shortens it, Insights fail for that run and the message names the model and the feature:
Insights
or
Experiment insights
. Choose a model with a larger context window under
Obss AI features
and run Insights again. A failed Insights read isn’t a friction.
Runs processed before Obss added these notes show none, so on an older run a missing note doesn’t prove a full read.
Which models ran
Each Insights attempt keeps the models it started with, even if you change a model later.
Where
What it shows
A run’s
Traces
tab, above the Timeline
The
Insights model
that wrote the review you see. While a rerun is pending, it still names the earlier review’s model.
Any tab of a run
The help icon next to
Frictions
names the
Insights model
of the frictions
The experiment’s
Frictions
tab and a friction’s page
The
Insights model
and
Experiment insights model
behind the frictions. If runs used different models, for example after a rerun with another model, each shows with its run count.
All frictions
shows no models because it spans experiments.
The info icon next to the experiment status
Latest evals and insights
: the models of the latest attempts
CLI and Plugin (MCP)
Each attempt’s models, and each friction list’s models with run counts
obss data query
and the plugin’s
Query Obss data
The model fields of the
insights
and
frictions
datasets (
insightsModelId
,
insightsModelName
,
experimentInsightsModelId
,
experimentInsightsModelName
), and the
insights
dataset’s
mode
. Use them to compare results by model or mode.
Pending frictions
When a run shows no frictions, Obss tells you whether it has none or Insights haven’t finished:
With no filters set, the experiment’s
Frictions
tab says
Warming up
while Insights can still add frictions.
Until grouping is done, a run’s frictions show only on its trace, and the friction list counts the runs with ungrouped frictions and the runs Insights haven’t reviewed.
Rerun Insights
replaces each run’s frictions with the new review. Frictions keep their IDs.
From the CLI and the plugin,
obss results analyze
counts the runs that Insights reviewed, the runs still pending, and the runs they didn’t review. An empty friction list is final when no run is pending.
obss frictions list
also reports runs that had Insights off.
Run Insights again
Rerun Insights to review the runs again, for example after you assign a different model. Evals verdicts don’t change. When Insights finish, Obss writes the experiment’s
Brief
again.
Dashboard
CLI
Plugin (MCP)
Open the experiment and choose
Rerun Insights
(or
Run insights
if Insights haven’t run yet). You can change the
Insights model
, the
Experiment insights model
, and the mode.
obss
insights
preview
exp_8f2c41d0
obss
insights
trigger
exp_8f2c41d0
obss insights trigger
lists every flag.
Ask your AI assistant to run Insights again. It calls
Start Insights for an experiment
(
trigger_insights
), and you approve each call.
From the CLI and the plugin
Task
CLI
Plugin (MCP)
Preview Insights before you run them
obss insights preview
preview_insights
Run Insights
obss insights trigger
trigger_insights
List Insights attempts
obss insights list
list_insights
Read Insights results
obss insights get
get_insights_results
List the frictions they found
obss frictions list
list_frictions
Read the Brief
obss experiments brief
get_experiment_brief
Next steps
Frictions
Rank the problems agents hit and decide what to fix.
Run details
Read the trace at the steps a friction cites.
obss evals and insights
Every command and flag.
Agent mode
Have Obss’s insights agent review each run in depth.
Agent mode
Frictions
Powered by
This documentation is built and hosted on Mintlify, a developer documentation platform