Sam
Get started
SAM FROM OPS / SIGNALS

What Sam notices.
And the evidence for each.

Sam reads the two reports your code sends around each AI call: measurements only, never the content. These nine signals work from a feature’s first report. Every finding shows what Sam saw, and every limit can be changed or switched off per feature.

See the signals
FROM THE FIRST CALL

Across every call.
No history needed.

These read the measurements in each report, so they work from the moment a feature is connected.

  1. 01

    Model inventory

    Which models each feature calls, how often, and how that changes over time.

    Every call
  2. 02

    Deprecation exposure

    A feature still calling a model whose provider has announced a retirement date.

    Every call
  3. 03

    A run that stalled

    A call that starts and never reports back: no reply, no error, nothing that would trip an alert.

    After 10 min
  4. 04

    Retrying into an error

    The same error coming back again and again in one run, with nothing handling it.

    4 retries
  5. 05

    Growing context

    The context a run sends its model growing several times over, so each call does more work than the last.

    4× growth
WITHIN THE CURRENT RUN

One run at a time.
Watched while it happens.

These look at the run in progress. The limit on each card is the default; you can set your own for any feature.

  1. 06

    A loop

    The same call, with the same fingerprint, made again and again in one run.

    5 repeats
  2. 07

    Repeated tool calls

    The same tool called with the same arguments, over and over.

    8 calls
  3. 08

    Fan-out

    One run starting more and more child runs.

    12 children
  4. 09

    Too many steps

    A run going past the number of steps you expect from that feature.

    40 steps
YOUR CALL

Set the limits per feature.

A research agent is meant to take many steps. An extraction pipeline isn’t. Raise a limit, lower it or switch a check off for the features where it doesn’t fit, rather than living with the noise.

Evidence, and your verdict.

Each finding shows the counts, the limit and the run it came from. If one is wrong, mark it, and Sam records it alongside the finding.

Halting when you’re ready.

New teams start with Sam observing. Switch halting on and a finding also returns a halt to your agent on its next call. Your code decides what to do with it.

SEE IT ON YOUR OWN AGENTS

Connect one feature.
See what Sam notices.

Two reports around each call. Your first findings arrive while you watch.

Start a free trial