Skip to content

Commit f796398

Browse files
committed
linking to intro page now
1 parent bbeb50a commit f796398

File tree

1 file changed

+5
-53
lines changed

1 file changed

+5
-53
lines changed

docs/faqs.md

Lines changed: 5 additions & 53 deletions
Original file line numberDiff line numberDiff line change
@@ -21,59 +21,11 @@ The user base is geographically diverse with three main pockets: United States,
2121

2222
## How does SAP Research Agent work?
2323

24-
### Core Architecture
24+
Details [here](./research-agent/research-intro.mdx#how-does-sap-research-agent-work)
2525

26-
- **AI Backend**: SAP Research Agent uses over 40+ Large Language Models with specialized configuration for SAP research tasks. More details [here](https://getadriai.github.io/code-agent-docs/faqs#which-models-are-being-used)
27-
- **Vector Database**: The attached ERP system has been indexed into a ChromaDB vector database. It contains 18 million standard objects of ECC 6.0 EHP 7 and 27 million standard objects of S/4HANA 2023 like:
26+
## Which models are being used?
2827

29-
- Transaction codes, programs, classes
30-
- Tables, views, data elements
31-
- BAdIs, enhancements, function modules
32-
- Menu paths, documentation, and more
33-
34-
### Which models are being used?
35-
36-
SAP Research Agent uses a combination of:
37-
38-
- Internally fine-tuned models
39-
- Public frontier models
40-
41-
Depending on the subtask, an appropriate combination of models is chosen dynamically.
42-
43-
| Model Provider | No. of models used |
44-
| -------------- | ------------------ |
45-
| Adri AI | 4 |
46-
| Google | 9 |
47-
| Mistral | 6 |
48-
| Meta | 8 |
49-
| OpenAI | 7 |
50-
| Anthropic | 4 |
51-
| Cohere | 4 |
52-
| Total | 42 |
53-
54-
Note: Counts are as of November 2025
55-
56-
### Key Capabilities
57-
58-
1. **System Validation**
59-
60-
SAP Research Agent queries the attached SAP system by writing ChromaSQL queries. ChromaSQL is a SQL-inspired domain specific language created by Adri AI.
61-
62-
2. **Web Search**
63-
64-
SAP Research Agent also has the capability to search the internet for SAP solutions, best practices, and similar use cases.
65-
66-
3. **Document Processing**
67-
68-
SAP Research Agent can read the uploaded attachments and optionally index them for future reference.
69-
70-
### Typical Workflow
71-
72-
1. User asks a research question (text + optional attachments)
73-
2. Depending on the question, the SAP Research Agent may think of a solution from its own knowledge base or search the web for relevant resources.
74-
3. The solution is then validated against your SAP system's capabilities using the vector database.
75-
4. The agent creates detailed implementation plans with specific T-codes, ABAP objects, and configuration steps.
76-
5. The agent provides alternatives and visual diagrams when helpful.
28+
Details [here](./research-agent/research-intro.mdx#which-models-are-being-used)
7729

7830
## What are the usage limits?
7931

@@ -84,7 +36,7 @@ After signup, they get another 200,000 free tokens.
8436
Once you runout of these free tokens, you should upgrade to the Enterprise Plan.
8537

8638
:::note
87-
For Enterprise Plan, contact us at [darshita@getadri.ai](mailto:darshita@getadri.ai)
39+
For Enterprise Plan, contact us at [founders@getadri.ai](mailto:founders@getadri.ai)
8840
:::
8941

9042
## What is the difference between all the tiers?
@@ -95,5 +47,5 @@ For Enterprise Plan, contact us at [darshita@getadri.ai](mailto:darshita@getadri
9547
| Conversation History | Not saved | Saved | Saved |
9648

9749
:::note
98-
For Enterprise Plan, contact us at [darshita@getadri.ai](mailto:darshita@getadri.ai)
50+
For Enterprise Plan, contact us at [founders@getadri.ai](mailto:founders@getadri.ai)
9951
:::

0 commit comments

Comments
 (0)