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

# Scoring and quality

> How the score is built, how to bend it toward your business, and how to see the filter working.

## Scoring, and how to bend it toward your business

Every signal carries a score out of 100, built from seven components:

| Component        | Default weight | What it measures                                |
| ---------------- | -------------- | ----------------------------------------------- |
| Purchase intent  | 30             | Evidence they are ready to buy — not vocabulary |
| Fit              | 20             | How well they match who you sell to             |
| Urgency          | 15             | How soon this matters                           |
| Recency          | 10             | How fresh the post is                           |
| Commercial value | 10             | What the opportunity is plausibly worth         |
| Evidence quality | 10             | How much the source actually gave us to read    |
| Multi-signal     | 5              | Whether this company has come up before         |

Each listener has a **score bar** — the minimum a conversation must clear to be kept, 55 by default. Below the bar, a candidate is recorded as rejected with its reason rather than stored. Competitor and content rows skip the bar, since low-scoring intel is still intel.

On Pro you can change the score bar per listener and choose a vetted **emphasis preset**:

| Preset          | For                                                                 |
| --------------- | ------------------------------------------------------------------- |
| **Balanced**    | The default. Intent leads, fit is the second voice.                 |
| **Fit-led**     | A narrow market: a strong signal from the wrong company scores low. |
| **Urgency-led** | Work won by responding first — restoration, incident response.      |

Enterprise can set the seven weights directly. See [openpulse.cloud/pricing](https://openpulse.cloud/pricing) for which plan includes score tuning.

## Quality: seeing the filter's working

This is the part no comparable product shows you, and it is deliberately product surface rather than diagnostics.

* **Rejections are kept, with reasons.** Every dropped candidate records why: wrong page shape, off-topic, excluded by your own keyword, blocked domain, too old, duplicate, ranked out, below the score bar, or noise. Kept for 14 days. When a listener feels quiet, this tells you whether the searches returned nothing or the filters threw everything away.
* **Per-query and per-source yield.** Which of your searches earn their cost and which have never produced a kept signal. A query that produces candidates but no signals for three runs in a row is disabled automatically and reported in the run log.
* **Your thumbs move the bar.** Rated signals are fed back into that listener's next classification as worked examples, so the definition of *relevant* becomes yours rather than one a model guessed at on day one.
* **The excluded list** shows what was dropped, in the interface, next to what was kept.

The quality report is also available to an AI assistant as `get_quality_report` — see [MCP & agents](/mcp/tools).


## Related topics

- [Plans and what each includes](/guides/plans.md)
- [Getting results out](/guides/getting-results-out.md)
- [Tools](/mcp/tools.md)