Use n8n to track Steam player feedback
Aswin Behera built a competitor-intelligence agent while working on his indie game, serverBound.
dev.to
Suggested prompt
Suggested prompt written by Agents In Use, not the source author. Replace bracketed inputs and review tool permissions first.
Track [comparable Steam games]. Retrieve player counts and reviews, then summarize praise, complaints and current interest in [Notion]. Preserve release dates and source data, and flag questionable model interpretations.
Reach people exploring AI agents
See placements →Evidence at a glance
Sourced account- Source author
- Aswin Behera
- Original account
- Read the source ↗
- Published
- Source link checked
- Reported result
- Behera reports daily competitor insights on Notion pages, after correcting model release-date errors and integration problems.
- Human involvement
- Behera corrected release-date context and integration issues.
A linked account supports attribution. It does not mean we independently reproduced its result.
Report an issue with this case
Open correction emailOpens your email app with the case link included. Nothing is sent automatically.
How the agent did it
- Collect comparable Steam releases.
- Analyze player feedback and metadata.
- Create a Notion page per game.
Aswin Behera built a competitor-intelligence agent while working on his indie game, serverBound. He wanted to understand why comparable Steam releases attracted attention and what players praised or disliked without repeatedly reading reviews by hand. The workflow gathered popular releases and enriched them with player counts and review data.
An AI analysis step summarized likely discussion topics, emerging complaints and reasons a game resonated. Each competitor received a Notion page containing an application identifier, release date, player count, review score, popularity rank and the analysis. Behera showed an example page and linked the Notion workspace.
The build exposed practical limits. Some sources blocked requests, Notion's text-block size required splitting large outputs, and differently shaped Steam responses needed careful merging. Gemini sometimes treated release dates as future events, so Behera added context processing. He reports receiving daily competitive insights after these changes. The result is a maintained research workspace with documented data and model problems, rather than a guarantee that every interpretation of player sentiment is accurate.
Prompt
Suggested prompt (written by Agents In Use, not the author's)
Source: dev.to · Aswin Behera
Frequently asked questions
Where did each game analysis go?
A separate Notion competitor page.
How did the builder handle incorrect dates?
Behera added context processing after Gemini sometimes assumed release dates were still in the future.
What Notion constraint mattered?
Large output needed multiple text blocks.
More details
About this account
The AI analyzes review signals and competitor context.
Firsthand account opened and read. Results are attributed to the author. Prompt is our suggested adaptation, not an original quotation.
Credit: Aswin Behera
Source published
Added to Agents In Use
Source checked
Tools and topics
n8n AI Agent · Bright Data · Steam APIs · Gemini · Notion
Steam reviews · Competitor research · Notion
Editorial completeness: 100/100. Measures documented fields, not agent performance or verified outcomes.