> ## Documentation Index
> Fetch the complete documentation index at: https://langwatch.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# No-spy mode (drop conversational content)

> The privacy posture for organizations that must not store employee conversational content, one Organization rule in the data privacy policy that drops input, output, and system instructions at ingestion while keeping cost and usage metadata.

Many enterprises operate under policies that prohibit storing
conversational content from employee LLM interactions, even briefly.
**No-spy mode** is the privacy posture for those organizations: one
Organization-scope rule in the
[data privacy policy](/docs/ai-governance/data-privacy) that sets
**Input**, **Output**, and **System instructions** to **Drop**. The
content is stripped in the ingestion pipeline, before it ever lands
in storage.

<Info>**Pairs with:** [Data privacy policy](/docs/ai-governance/data-privacy) (the full reference for scopes, dispositions, audiences, and redaction), [Compliance architecture](/docs/ai-governance/compliance-architecture) (the observability substrate this posture operates against), and [Self-hosting compliance](/docs/self-hosting/compliance) (where this fits in the SOC 2, ISO 27001, HIPAA mapping).</Info>

## Setting it up

At **Settings > Privacy**, add an **Organization** rule and set the
content categories to Drop:

| Category            | Disposition                                |
| ------------------- | ------------------------------------------ |
| Input               | Drop                                       |
| Output              | Drop                                       |
| System instructions | Drop                                       |
| Tool calls          | Capture, or Drop for the strictest posture |

Dropping tool calls as well removes tool arguments and tool results.
That is the strictest posture, and it may break debugging flows that
need to inspect what tools received and returned.

Writing an Organization rule requires the organization manage
permission, so only org-level administrators can change this posture.

## What's stored, what's dropped

Dropped categories never reach storage. Observability metadata always
survives:

* model name and provider
* input and output token counts
* cost attribution
* latency, timings, and span structure
* status and error attributes
* identity attributes (which person, which organization)

So you can still answer "how much did this engineer's Claude Code
sessions spend this month?" and "did the gateway hit a 5xx?", without
anyone being able to read what was asked or what the model answered.

## Scoping the posture

A drop rule applies to **every ingestion path** for the projects in
its scope: AI gateway traffic, the OpenTelemetry endpoint, the REST
collector, ingestion keys, and coding-agent logs (for example Claude
Code request bodies).

The rule's scope decides which projects those are:

* **Narrowed to personal projects only**: every employee's personal
  CLI workspace drops its content, while application projects keep
  capturing for debugging. This is the common shape for "no employee
  chat surveillance" policies, it covers the coding assistants
  without touching product observability.
* **Organization-wide**: every project in the organization drops the
  chosen categories, application traces included.

<Note>If the requirement is "only a small audience may read it"
rather than "it must not exist", set the categories to **Restrict**
with a narrow [audience](/docs/ai-governance/data-privacy#audiences)
instead. Restriction keeps the content for the chosen reviewers and
applies retroactively to traces already stored.</Note>

## Drop is forward-looking only

Drop acts at ingestion, so it applies to traces that arrive after the
rule exists. Already-stored spans are not scrubbed. To remove
historical content, pair the rule with your retention setup so old
data cycles out while new ingest lands stripped (see
[Compliance architecture](/docs/ai-governance/compliance-architecture)).

## Trust boundary

The strip runs in the ingestion pipeline **before** the storage
write, so the searchable trace store never carries conversational
content for dropped categories. The gateway process still handles
each request in memory in order to proxy it to the provider. For
policies that require content never to transit LangWatch at all,
point those tools at the provider directly (BYOK endpoints) and skip
the gateway.

## Cross-org isolation

Privacy rules belong to a single organization. Two organizations on
the same self-hosted deployment hold independent policies: a drop
rule at `acme` has no effect on `globex`.

## Where to next

* [Data privacy policy](/docs/ai-governance/data-privacy): cascade
  resolution, audiences, PII levels, secrets redaction, and the
  defaults.
* [Compliance architecture](/docs/ai-governance/compliance-architecture):
  what dropping content means for your SOC 2, ISO 27001, HIPAA, EU AI
  Act posture.
* [Self-hosting compliance](/docs/self-hosting/compliance): compliance
  coverage for self-hosted deployments.