1# Zed AI Improvement
2
3## Agent Panel
4
5### Opt-In
6
7When you use the Agent Panel through any of these means:
8
9- [Zed's hosted models](./subscription.md)
10- [connecting a non-Zed AI service via API key](./llm-providers.md)
11- using an [external agent](./external-agents.md)
12
13Zed does not persistently store user content or use user content to evaluate and/or improve our AI features, unless it is explicitly shared with Zed. Each share is opt-in, and sharing once will not cause future content or data to be shared again.
14
15> Note that rating responses will send your data related to that response to Zed's servers.
16> **_If you don't want data persisted on Zed's servers, don't rate_**. We will not collect data for improving our Agentic offering without you explicitly rating responses.
17
18When using upstream services through Zed's hosted models, we require assurances from our service providers that your user content won't be used for training models.
19
20| Provider | No Training Guarantee | Zero-Data Retention (ZDR) |
21| --------- | ------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------- |
22| Anthropic | [Yes](https://www.anthropic.com/legal/commercial-terms) | [Yes](https://privacy.anthropic.com/en/articles/8956058-i-have-a-zero-data-retention-agreement-with-anthropic-what-products-does-it-apply-to) |
23| Google | [Yes](https://cloud.google.com/terms/service-terms) | [Yes](https://cloud.google.com/terms/service-terms), see Service Terms sections 17 and 19h |
24| OpenAI | [Yes](https://openai.com/enterprise-privacy/) | [Yes](https://platform.openai.com/docs/guides/your-data) |
25
26When you use your own API keys or external agents, **Zed does not have control over how your data is used by that service provider.**
27You should reference your agreement with each service provider to understand what terms and conditions apply.
28
29### Data we collect
30
31For prompts you have explicitly shared with us, Zed may store copies of those prompts and other data about the specific use of the Agent Panel.
32
33This data includes:
34
35- The prompt given to the Agent
36- Any commentary you include
37- Product telemetry about the agentic thread
38- Metadata about your Zed installation
39
40### Data Handling
41
42Collected data is stored in Snowflake, a private database where we track other metrics. We periodically review this data to improve our overall agentic approach and refine the product via our system prompt, tool use, etc. We ensure any included data is anonymized and contains no sensitive information (access tokens, user IDs, email addresses, etc).
43
44## Edit Predictions
45
46By default, when using Zed Edit Predictions, Zed does not persistently store user content or use user content for training of its models.
47
48### Opt-in
49
50Users who are working on open source licensed projects may optionally opt-in to providing model improvement feedback. This opt-in occurs on a per-project basis. If you work on multiple open source projects and wish to provide model improvement feedback you will have to opt-in for each individual project.
51
52When working on other projects where you haven't opted-in, Zed will not persistently store user content or use user content for training of its models.
53
54You can see exactly how Zed detects open source licenses in: [license_detection.rs](https://github.com/zed-industries/zed/blob/main/crates/zeta/src/license_detection.rs).
55
56### Exclusions
57
58Zed will intentionally exclude certain files from Predictive Edits entirely, even when you have opted-in to model improvement feedback.
59
60You can inspect this exclusion list by opening `zed: open default settings` from the command palette:
61
62```json [settings]
63{
64 "edit_predictions": {
65 // A list of globs representing files that edit predictions should be disabled for.
66 // There's a sensible default list of globs already included.
67 // Any addition to this list will be merged with the default list.
68 "disabled_globs": [
69 "**/.env*",
70 "**/*.pem",
71 "**/*.key",
72 "**/*.cert",
73 "**/*.crt",
74 "**/secrets.yml"
75 ]
76 }
77}
78```
79
80Users may explicitly exclude additional paths and/or file extensions by adding them to [`edit_predictions.disabled_globs`](https://zed.dev/docs/configuring-zed#edit-predictions) in their Zed settings.json:
81
82```json [settings]
83{
84 "edit_predictions": {
85 "disabled_globs": ["secret_dir/*", "**/*.log"]
86 }
87}
88```
89
90### Data we collect
91
92For open source projects where you have opted-in, Zed may store copies of requests and responses to the Zed AI Prediction service.
93
94This data includes:
95
96- the edit prediction
97- a portion of the buffer content around the cursor
98- a few recent edits
99- the current buffer outline
100- diagnostics (errors, warnings, etc) from language servers
101
102### Data Handling
103
104Collected data is stored in Snowflake, a private database where we track other metrics. We periodically review this data to select training samples for inclusion in our model training dataset. We ensure any included data is anonymized and contains no sensitive information (access tokens, user IDs, email addresses, etc). This training dataset is publicly available at [huggingface.co/datasets/zed-industries/zeta](https://huggingface.co/datasets/zed-industries/zeta).
105
106### Model Output
107
108We then use this training dataset to fine-tune [Qwen2.5-Coder-7B](https://huggingface.co/Qwen/Qwen2.5-Coder-7B) and make the resulting model available at [huggingface.co/zed-industries/zeta](https://huggingface.co/zed-industries/zeta).
109
110## Applicable terms
111
112Please see the [Zed Terms of Service](https://zed.dev/terms-of-service) for more.