User Experience/Design
While it looks good, there are a number of issues that scream that this isn’t an enterprise-grade platform. We need to make a number of edits to the platform to offer users with a more consistent user experience.
[Cellstrat] The “thinking” process should be default closed. If you don’t know what I mean by that, ask questions to clarify. While it was nice to have it open, the consistent issue of opening and closing and re-trying make it look like the platform is broken most of the time. Closing with make is seem like it’s taking longer, but at least it won’t look broken. [Cellstrat] The thinking process needs to have a clear visual clue to communicate that something is going on in the back end. I’ve provided examples of the text shimmer. If you don’t think you have the required information to proceed, ask. See OpenAI’s shimmer process for o3-mini [Cellstrat] The initial comments I received about the platform included a concern about the ‘loading’. To the user, this seems that every new question includes a load step. To the user it seem repetitive since this might have been the 5th task. “Why does anything need to load again? Didn’t it load last time”. Please suggest language that is more in line with the backend process that doesn’t make it seem like the app is broken. [Cellstrat] Do not continue to share with the users when there is an issue and you need to take another approach. Again, this looks like this is an error to the user. Every other platform keeps these reworks more private. Please think like a user. Retrys should not have their own “thinking” section. [Cellstrat] The initial welcome messages are not left aligned with the other text and operate at a much slower pace. This is supposed to be exactly like the agent response so the typewriter speed should approximate the response speed and the text should be aligned. [Cellstrat] The right panel need to follow the requested design. [Cellstrat] The right panel should include the data file(s) used for the data set. [Cellstrat] Please provide a rough style-guide outline so that we know what everything should be ahead of time and if we create new section, we have a common style guide for instructions. [Cellstrat] If you have any questions about the users flow, follow what you see in sana.ai.\ [Cellstrat] Fix the broken process for whenever the users asks for an Edit. It current throws an error and crashed the app.
Reviews
Sandbox access to the review API, pulling in all key review details for discovery and analysis. You already have access to the the account using the same credentials, here is the API call:
https://reputationmanager.io/api/getReviews
{
"from": 0,
"size": 1000,
"profileId": "9be8687429dc971a4b4ba222943391bc",
"filters": {"dateRange": { "from": "2024-11-21","to": "2025-04-20" } },
"readMask": "storeCode,title,masterAddress,locationKey,entityTags,createTime,locationId,detectedLanguage,source,timeZone,isReviewFromPubSub,reviewer,starRating,comment,commentWordCount,sentimentAnalysis,websiteUrl,lastUpdateTime"
}
Milestones
[Cellstrat] Access the profile review data set for the last 180 days up to the last 1000 reviews. A combined filter will cover the need across different types of clients. [Cellstrat] Home page navigation button triggers the correct file download and presents the already providing greeting conversation to initiate. [LC] Create sets of Tasks for Reviews Analysis that provide insights and reporting not available from the platform. [Cellstrat] Review the task prompts to identify language suggestions to improve user experience. [Cellstrat] Provide LC with instructions on how to provide a systemic markdown so that the review analysis outputs look polished. [LC] Different card background style for Tasks from different Data sets.
Review Tasks:
Title: Monthly Analysis
You are an AI analyst tasked with generating a comprehensive monthly report based on customer reviews, including star ratings and textual comments. Please perform the following analyses:
Executive Summary: Provide an overview of the overall customer sentiment and satisfaction trends observed during the past month. Include a brief comparison with the previous month’s data to highlight any significant changes or trends. Positive Highlights: Identify and summarize the key aspects or features that customers praised. Include representative comment excerpts to illustrate these positive points. Negative Highlights: Identify and summarize the main issues or concerns raised by customers. Include representative comment excerpts to illustrate these negative points. Actionable Suggestions: Based on the negative feedback, suggest specific, actionable improvements to address customer concerns. Ensure that these suggestions are directly informed by the feedback received. Ensure that your analysis is structured, concise, and based solely on the provided data. Present the findings in a clear and organized manner.
Title: Comparative Analysis
“Compare the customer reviews from the most recent completed with the previous month. Highlight any significant changes in ratings, sentiment, emerging themes, or shifts in customer concerns. Provide insights into potential causes for these changes.”
Title: Actionable Insights
“Based on the analysis of customer reviews from the prior month, list the top five areas for improvement. For each area, provide a brief explanation supported by customer quotes and suggest potential actions to address these issues.”
Title: Multilingual Sentiment Overview
Objective: Analyze customer reviews, categorized by the detectedLanguage variable, to extract language-specific insights and identify cross-linguistic differences.
Instructions:
Language-Specific Summaries: For each unique language detected: Overall sentiment distribution (positive, neutral, negative). Identify predominant topics or aspects mentioned. Provide representative comment excerpts that highlight these themes. Note any culturally specific phrases or idioms that may influence sentiment interpretation. Cross-Language Comparison: Compare the findings across all detected languages to: Highlight differences in customer concerns or praises. Identify any discrepancies in sentiment trends. Discuss potential cultural factors influencing these differences. Based on the analysis, recommend strategies to address language-specific feedback. Suggest improvements to enhance customer experience across diverse linguistic groups.
Title: Customer Reviews by Source
Objective: Analyze customer reviews categorized by the source variable (e.g., Google, Yelp, Trustpilot) to identify and compare feedback themes across different platforms.
Instructions:
Source-Specific Summaries: Overall sentiment distribution (positive, neutral, negative). Identify predominant topics or aspects mentioned. Provide representative comment excerpts that highlight these themes. Note any distinctive features of the reviews from this source (e.g., length, detail, tone). Compare the findings across all review sources to: Highlight differences in customer concerns or praises. Identify any discrepancies in sentiment trends. Discuss potential reasons for these differences, considering the nature of each platform. Based on the analysis, recommend strategies to address source-specific feedback. Suggest improvements to enhance customer experience across all platforms.
Title: Weekly Summary
You are an AI assistant analyzing customer feedback from Google Business Profile reviews. Your task is to generate a concise and insightful weekly summary report based on the reviews received over the past 7 days. The dataset includes star ratings, review comments, and timestamps.
Please structure the report into the following sections:
Total number of new reviews Average star rating for the week Comparison to the previous week (e.g., +0.2 stars, -5 reviews) Identify 2–3 recurring positive themes mentioned in the reviews Include 1–2 sample quotes that highlight each theme Top Areas for Improvement Identify 2–3 recurring concerns or negative feedback themes Include 1–2 sample quotes per issue to provide context Notable Review Highlights Mention any especially impactful or detailed reviews, whether positive or critical Summarize any opportunities for improvement or suggestions based on the reviews Propose possible actions to address negative trends or amplify positive ones
Use clear language and bullet points where helpful. Keep the tone professional, yet conversational. Assume the reader is a multi-location business manager who needs quick, actionable insights.
Confirmation & Email
Please find below the type of conversation flow we are hoping for direct edits. Each thread should be saved and trigger an email to support@localclarity.com.
Blank Sample
Sample conversation that starts without initial questions.
🧑 Human:
I need to update the business hours for several of our locations.
🤖 Agent:
Of course! I can help with that. Could you please confirm if you’d like to update the hours for all your locations or only a select few?
🧑 Human:
Just the ones in Texas and Florida, please.
🤖 Agent:
Got it. You’d like to update the business hours for your Texas and Florida locations. Can you please share the new hours you’d like applied?
🧑 Human:
Yes, all of them should now be open from 9 AM to 8 PM, Monday through Saturday, and closed on Sundays.
🤖 Agent:
Understood. To confirm:
New Hours: Monday–Saturday: 9:00 AM – 8:00 PM
Closed: Sunday
Locations: All in Texas and Florida
Would you like me to proceed with scheduling these updates?
