Report Generator
The Report Generator AI Task quickly transforms uploaded raw data into professional reports, saving businesses time and ensuring accurate, polished presentations.
Additional Resources
Easily create professional reports with QAnswer’s Report Generator AI. Watch our few seconds tutorial to quickly turn your data into concise, ready-to-present reports!
You can access this AI task click on AI Tasks and Report Generator :
To generate a report, you can write it yourself and use the AI Assistant to generate specific sections. To use the AI Assistant, follow these steps:
Click on Insert, then select Add AI writer block to add an AI-generated section.
Enter your prompt in the text field to give the assistant writing instructions.
Click on Generate. The assistant will create a response, which you can read as it's being written.
You can leave the page and return, the generation will continue in the background.
If you're not satisfied with the result, you can modify the prompt by going back to the corresponding tab.
Finally, click on File to access options such as Create a New report, Load template, Save and rename the document, Download as template file, and Export as .docx file.
- New Report
- Insert
- AI Bloc
- Prompt
- Answer
- File
Task Settings
If you want to customize your Report Generetor Ai Assistant you can click on
You can customize the way your Ai assistant answers you by :
Filling the prompt settings : It will define its personality and you can follow the example provided in the default settings
Adjusting the LLM settings : you can choose the LLM that will power the answers, the answer length, its creativity level, the answer speed.
Adjusting the Retriver : you can choose the LLM reference level, add synonyms.
- Open Tasks Settings
- Prompt
- LLM
- Retriever
- On prompt settings, you can define the personality of your AI assistant by using variables like
{{bot_name}}or{{bot_answer_length}}. It allows you to personalize the answers you get from your AI assistant settings. - Press the / and you'll get the available variable list.
- For example brief comes from the
{{bot_answer_length}}variable you can set in the LLM settings of your AI Task.
In the LLM settings, you can adjust the parameters of the LLM that will power your AI assistant like:
- the LLM model unstructured
- the context window in tokens
- to show or hide last update date in sources
- the maximum answer length
- the creativity level (temperature)
- the answer speed
-
Context window (tokens): how much text (conversation + documents) the model can consider at once. If your input exceeds this, earlier content may be dropped.
-
Maximum response length: cap on tokens the model returns; prevents overly long outputs.
Practical tip: use low temperature for factual extraction, increase context window to include long documents, and set a max response length to control output size and cost.
In the retriever settings, you can adjust the parameters of the retriever that will be used to retrieve relevant documents for your AI assistant. It contains:
- the embedding model used (note this can only be changed at creation time of the AI Assistant)
- The number of references passed to the LLM
- the synonyms used to retrieve more relevant documents
Synonyms
In the synonyms settings, you can define groups of synonyms that will be used to retrieve more relevant documents.
Click on + Add synonym group to add a new group of synonyms.
Enter a word in the input field and press Enter or click the + button to add it to the list of synonyms.
You can only add a new group if there are no existing groups, or if the last one has at least one synonym and the input field is empty.
You can delete a group by clicking the
button.
- Synonyms
- First group
- Input filled
- List created
- Add Group
Document Chunking
How It Works
Document chunking controls how text is split before being embedded and indexed. It impacts retrieval quality and context windows. You have three main parameters:
Split by
Choose the unit used to cut the document:
- Words – Splits by a fixed number of words.
- Sentences – Splits by sentence boundaries.
- Pages – Splits based on original PDF/page breaks.
Split Length
Defines how big each chunk is, based on the selected unit.
- If split by Words: this = number of words per chunk.
- If split by Sentences: this = number of sentences per chunk.
- If split by Pages: this = number of pages per chunk (usually 1).
Split Overlap Defines how much of the previous chunk is carried into the next chunk to preserve context.
- Example: Split length = 100 words, Overlap = 20 → each new chunk repeats 20 words from the previous one.
Example Scenarios
| Split By | Length | Overlap | Result |
|---|---|---|---|
| Words | 100 | 0 | Independent 100-word chunks |
| Words | 100 | 20 | Each chunk shares 20 words with the next |
| Sentences | 5 | 1 | Each chunk contains 5 sentences, last sentence overlaps |
| Pages | 1 | 0 | One full page per chunk, no overlap |
How to Test It
Step 1 – Upload a Simple Test Document
Use a small manual text like:
This is sentence one.
This is sentence two.
This is sentence three.
Step 2 – Set Chunking Options
Test multiple configurations:
- Words (Split length = 3, Overlap = 1) – Expect sliding windows of 3 words.
- Sentences (Split length = 1) – Each sentence becomes a separate chunk.
- Pages – Upload a multi-page PDF and set split by Pages.
Step 3 – Check the Indexed Chunks
[Search Task] Ask a question and check:
the top extracts:
- Does it retrieve the expected chunk?
- Is each chunk contain a sentence?
or:
info button on the assistant message, check the prompt and then verify the #Documents part of the prompt
AI Block Versioning and Feedback
How It Works
In the AI Writer block, every time you Regenerate content or Ask a new question, you generate a new version of the response. These versions are stored and accessible via a version switcher.
- Instruction 1
- Instruction 2
- Version Switcher
You can now:
- Switch between versions to compare outputs.
- Provide thumbs up or thumbs down feedback.
- Add comments to explain your rating.
- Copy any version directly into your clipboard.
This feedback is for tracking the good/bad generations across versions and blocks.
Example Use Case
-
You prompt the AI:
"Summarize the key insights from the Q3 sales data in 100 words." -
The AI generates Version 1. You review it and find it too detailed.
-
You click Regenerate → get Version 2, which is more concise.
-
You:
- Click on Version 2.
- Add a comment: "More concise and focused on key metrics."
-
If you later want to revisit Version 1, you can use the version changer and go back to Version 1.
Key Benefits
| Feature | Benefit |
|---|---|
| Multiple Versions | Compare AI outputs side-by-side |
| Feedback System | Rate and comment on each version |
| Copy Content | Instantly insert the best version into your report |
| Version Switcher | Navigate between generations with ease |
AI Bloc Settings
You can access the AI Block settings by clicking on the
icon in the AI Writer block toolbar. It will open the right panel.- AI Block Settings
- Prompt
- LLM
- Retriever
- Sources
- On prompt settings, you can define the personality of your AI assistant by using variables like
{{bot_name}}or{{bot_answer_length}}. It allows you to personalize the answers you get from your AI assistant settings. - Press the / and you'll get the available variable list.
- For example brief comes from the
{{bot_answer_length}}variable you can set in the LLM settings of your AI Task.