# ReskPoints: AI Agent Logging with Sampling, Masking, and Multi-Export

> Source: <https://dev.to/resk/reskpoints-ai-agent-logging-with-sampling-masking-and-multi-export-5g88>
> Published: 2026-07-11 07:01:00+00:00

ReskPoints makes every agent action observable. Console, Datadog, Prometheus, OpenTelemetry — one install, all exporters.

**Links:**

A typical AI agent orchestrator makes dozens of tool calls per user request. Each call has request parameters a response latency and a success or failure state. When something goes wrong you need to replay what the agent was thinking and doing.

Standard Python logging gives you raw text. Datadog APM gives you traces but not the agent intent layer. You need a purpose-built logger that captures the agent loop not just the HTTP calls.

ReskPoints is a Python library that hooks into your agent loop and records every action with context. Here is the core API:

``` python
from reskpoints import AgentLogger

logger = AgentLogger(
    service="my-agent",
    sampling_rate=0.1,   # keep 10 percent of actions
    exporters=[
        "console",
        "datadog",
        "prometheus"
    ],
    masks=[
        "api_key",
        "user.email"
    ]
)

# Inside your agent loop
logger.log_action(
    action="tool_call",
    tool="search_docs",
    input={"query": user_input},
    output=result,
    duration_ms=340,
    token_count=1200
)
```

The library works with Python 3.13+ and has zero required dependencies beyond the exporters you use.

```
pip install reskpoints
```

Then add one `AgentLogger`

instance to your agent loop and wire your exporters. Full docs on GitHub.

[https://github.com/Resk-Security/ReskPoints](https://github.com/Resk-Security/ReskPoints)

What logging setup do you use for your AI agents?