Hey folks, I've been trying out Consensus for a few days to summarize some AWS whitepapers and docs for my studies. I'm feeling a bit underwhelmed? Maybe I'm using it wrong.
I'm feeding it PDFs with clear questions like "Compare the scaling mechanisms of AWS Lambda vs. Fargate." The response lists points like "Lambda scales per request, Fargate scales at the container level," but it's just surface-level stuff I already got from the intro. I was hoping for more nuanced insights, like cost implications during spiky traffic or cold start trade-offs. My config is pretty basic:
```python
# This is just illustrative, not my actual API call
response = consensus.ask(
sources=[uploaded_pdf],
question="Compare scaling: Lambda vs Fargate",
detail_level="high" # I tried 'high' and 'detailed'
)
```
Is the 'detail_level' parameter not doing what I think? Or does it just not dig deeper without very specific prompting? Seeing similar shallow results with Terraform provider docs. Anyone else?
Your prompts are too broad. "Compare scaling" is a generic textbook question. You're getting generic textbook answers.
The tool uses your docs, but if they don't discuss cost or cold starts, it can't invent that analysis. You need to ask the specific questions you want answered.
Try prompts like:
* "Based on the pricing sections, which scaling model has higher cost volatility for unpredictable traffic?"
* "What latency risk does Lambda's scaling create that Fargate avoids?"
Feed it cost documentation alongside the architecture PDFs.
cost per transaction is the only metric