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
description: Benchmark Ask Fern's accuracy against your documentation.
4
+
---
5
+
6
+
<Markdownsrc="/snippets/wip-callout.mdx" />
7
+
8
+
Fern evaluates how accurately Ask Fern answers questions on your documentation site compared to competitor AI search solutions.
9
+
10
+
Fern first generates evaluation questions from your documentation files, then runs those questions through both Ask Fern and competitor systems.
11
+
Finally, Fern evaluates each answer against the original documentation for accuracy. You receive detailed performance metrics and comparative analysis.
12
+
13
+
## Availability
14
+
15
+
Evals are currently provided as custom analysis delivered directly by the Fern team.
description: Fern identifies documentation gaps and improvement opportunities from your user queries.
4
+
---
5
+
6
+
<Markdownsrc="/snippets/wip-callout.mdx" />
7
+
8
+
Fern analyzes Ask Fern query patterns to surface actionable recommendations for improving your documentation. After collecting sufficient query data over a month, Fern processes this through specialized models that analyze query-response pairs to identify documentation gaps, extract common themes, and generate specific suggestions for enhancing your docs.
9
+
10
+
## Availability
11
+
12
+
Insights are currently provided as a monthly report delivered directly by the Fern team.
Copy file name to clipboardExpand all lines: fern/products/ask-fern/pages/getting-started/what-is-ask-fern.mdx
+45-10Lines changed: 45 additions & 10 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -1,19 +1,21 @@
1
1
---
2
-
title: AI Search Overview
2
+
title: What is Ask Fern?
3
3
subtitle: Let your customers find answers in your documentation instantly.
4
4
---
5
5
6
+
<Note>Ask Fern is available on the [Pro plan](https://buildwithfern.com/pricing#Docs) of Fern Docs. Billing is by usage.</Note>
7
+
6
8
## Overview
7
9
8
10
<Framecaption="AI Search is accessed via the search bar, alongside keyword search.">
9
11
<imgsrc="../assets/search-modal.png"alt="Accessing AI Search" />
10
12
</Frame>
11
13
12
-
Fern AI Search indexes your documentation and provides an interface for your users to ask questions and get answers. We've found that it helps our customers:
14
+
Ask Fern is Fern's AI Search feature that indexes your documentation and provides an interface for your users to ask questions and get answers. It helps our customers
13
15
14
-
-**Decrease the time to find needed information**- Help users quickly locate crucial documentation without navigating through a maze of tabs and endpoints.
15
-
-**Integrate your product faster**- Accelerate implementation with ready-to-use code samples that demonstrate practical applications.
16
-
-**Surface where your docs have gaps**- Identify documentation weaknesses through user feedback and search patterns.
16
+
-**Decrease the time to find needed information**– Help users quickly locate crucial documentation without navigating through a maze of tabs and endpoints.
17
+
-**Integrate your product faster**– Accelerate implementation with ready-to-use code samples that demonstrate practical applications.
18
+
-**Surface where your docs have gaps**– Identify documentation weaknesses through user feedback and search patterns.
17
19
18
20
<Framecaption="Users can ask questions and get support in an intuitive chat interface.">
19
21
<imgsrc="../assets/ask-ai-modal.png"alt="Preview of AI Search" />
@@ -27,7 +29,7 @@ Fern AI Search indexes your documentation and provides an interface for your use
27
29
icon="regular book-open"
28
30
href="/learn/ai-search/custom-prompting"
29
31
>
30
-
Tailor AI Search results to your users' needs.
32
+
Tailor Ask Fern results to your users' needs.
31
33
</Card>
32
34
33
35
<Card
@@ -43,19 +45,52 @@ Fern AI Search indexes your documentation and provides an interface for your use
Offer flexibility to have users 'Ask AI' or search your docs directly with Algolia.
48
+
Offer flexibility to have users "Ask AI" or search your docs directly with Algolia.
47
49
</Card>
48
50
49
51
<Card
50
52
title="All-in-one platform"
51
53
icon="regular fa-layer-group"
52
54
href="/learn/docs/getting-started/overview"
53
55
>
54
-
Create seamless UX by offering a 'one-stop-shop' for all docs questions.
56
+
Create seamless UX by offering a one-stop-shop for all docs questions.
55
57
</Card>
56
58
57
59
</CardGroup>
58
60
59
-
## Pricing
61
+
## How it works
62
+
63
+
Ask Fern is a **Retrieval Augmented Generation (RAG)** system built on top of your documentation site that transforms your documentation into an intelligent, searchable knowledge base. The main parts of the Ask Fern system are:
64
+
65
+
***Content indexing** – Fern automatically processes your documentation pages,
66
+
breaking them into semantic chunks and converting each chunk into a vector
67
+
using sentence embedding models. They're stored in a database that serves as
68
+
Ask Fern's search index.
69
+
***Query processing** – When users ask questions, Ask Fern vectorizes their
70
+
query and searches the database to find the most relevant documentation
71
+
chunks.
72
+
***Response generation** – Ask Fern uses the retrieved chunks as context to
73
+
generate accurate answers with [citations](/ask-fern/features/citations) for the user. If the initial context isn't sufficient, it performs an additional keyword search.
74
+
75
+
### Life of a query
76
+
77
+
Each Ask Fern user query follows these steps:
60
78
61
-
Ask Fern is available on the [Pro plan](https://buildwithfern.com/pricing#Docs) of Fern Docs. Billing is by usage.
79
+
```mermaid
80
+
sequenceDiagram
81
+
autonumber
82
+
participant U as User
83
+
participant C as /chat Endpoint
84
+
participant V as Documentation Database
85
+
participant A as Ask Fern
86
+
87
+
U->>C: Submit question via Ask Fern searchbox
88
+
C->>C: Convert query to vector
89
+
C->>V: Search for relevant chunks
90
+
V->>C: Return matching documents
91
+
C->>A: Send query + context
92
+
A->>V: Perform additional keyword search if needed
0 commit comments