You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
To train Foyle to be your Honeycomb you follow these steps
77
77
78
-
1. Make sure you turned on learning by following the [guide](/learning/)
79
78
1. Create a markdown cell expressing the high level intent you want to accomplish
80
-
1. Ask Foyle to generate a completion
81
-
82
-
* The first time you do this Foyle will probably provide a widely inaccurate answer because it has no prior
83
-
knowledge of your infrastructure
84
-
* Edit one of the generated code cells to contain the Honeycomb query and `hccli` command
85
-
* Execute the cell to generate the URL
86
-
1. Each time you ask for a completion and edit and execute the cell you are providing feedback to Foyle
87
-
* Foyle uses the feedback to learn and improve the completions it generates
88
-
89
-
**Important** When providing feedback to Foyle its important to do so by editing a code cell that was generated
90
-
by Foyle. If you create a new code cell Foyle won't be able to learn from it. Only cells that were generated by Foyle
91
-
are linked to the original query.
79
+
1. Create a code cell which uses `hccli` to generate the query link
80
+
1. Execute the code cell
81
+
1. Foyle automatically learns how to predict every successfully executed code cell
92
82
93
83
If you need help boostrapping some initial Honeycomb JSON queries you can use [Honeycomb's Share](https://docs.honeycomb.io/investigate/collaborate/share-query/)
94
84
feature to generate the JSON from a query constructed in the UI.
0 commit comments