<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/">
  <channel>
    <title>Stencilled</title>
    <link>http://www.stencilled.me/</link>
    <description>Recent content on Stencilled</description>
    <image>
      <title>Stencilled</title>
      <url>http://www.stencilled.me/%3Clink%20or%20path%20of%20image%20for%20opengraph,%20twitter-cards%3E</url>
      <link>http://www.stencilled.me/%3Clink%20or%20path%20of%20image%20for%20opengraph,%20twitter-cards%3E</link>
    </image>
    <generator>Hugo -- 0.125.7</generator>
    <language>en</language>
    <lastBuildDate>Mon, 01 Sep 2025 00:00:00 +0000</lastBuildDate>
    <atom:link href="http://www.stencilled.me/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Verifiable Agents, Not Demos: A Problem-First Approach</title>
      <link>http://www.stencilled.me/posts/2025-09-01-verifiable-agents/</link>
      <pubDate>Mon, 01 Sep 2025 00:00:00 +0000</pubDate>
      <guid>http://www.stencilled.me/posts/2025-09-01-verifiable-agents/</guid>
      <description>Course notes from &amp;#39;Building Agentic AI Applications with a Problem-First Approach&amp;#39; - moving beyond clever demos toward measurable, reliable agent systems with practical playbooks for problem-first framing, early evaluations, guardrails as product requirements, and iteration with data.</description>
    </item>
    <item>
      <title>No More Data Gatekeepers: How We&#39;re Making Analytics Accessible to Everyone</title>
      <link>http://www.stencilled.me/posts/2025-08-01-ami-dashboard/</link>
      <pubDate>Fri, 01 Aug 2025 00:00:00 +0000</pubDate>
      <guid>http://www.stencilled.me/posts/2025-08-01-ami-dashboard/</guid>
      <description>Introducing AMI - Adaptive Media Intelligence, a platform that democratizes data access through conversational analytics, interactive dashboards, and AI-powered insights.</description>
    </item>
    <item>
      <title>QuickMMM: Making Media Mix Modeling Simple for Marketers</title>
      <link>http://www.stencilled.me/posts/2025-06-10-quickmmm/</link>
      <pubDate>Sun, 15 Jun 2025 00:00:00 +0000</pubDate>
      <guid>http://www.stencilled.me/posts/2025-06-10-quickmmm/</guid>
      <description>A fast, marketer-friendly tool for media mix modeling — get actionable insights in hours, not months.</description>
    </item>
    <item>
      <title>Is Your Website Built for LLMs? Why Analytics Needs to Rethink the Funnel</title>
      <link>http://www.stencilled.me/posts/2025-06-09-llm-funnel/</link>
      <pubDate>Mon, 09 Jun 2025 00:00:00 +0000</pubDate>
      <guid>http://www.stencilled.me/posts/2025-06-09-llm-funnel/</guid>
      <description>In a world where large language models are the first point of contact, your website needs to speak to them as much as it does to your users. Here&amp;#39;s how analytics teams can help rewire the funnel.</description>
    </item>
    <item>
      <title>Benchmarks vs. Baselines: When &#39;Above Average&#39; Isn&#39;t Good Enough</title>
      <link>http://www.stencilled.me/posts/2025-06-02-benchmarks-baselines/</link>
      <pubDate>Mon, 02 Jun 2025 00:00:00 +0000</pubDate>
      <guid>http://www.stencilled.me/posts/2025-06-02-benchmarks-baselines/</guid>
      <description>Why relying on external benchmarks in media analytics can be misleading, and how building your own baselines leads to smarter, more context-aware decision making.</description>
    </item>
    <item>
      <title>Stop Asking for Data You&#39;ll Never Use</title>
      <link>http://www.stencilled.me/posts/2025-05-06-stop-asking-data/</link>
      <pubDate>Tue, 06 May 2025 00:00:00 +0000</pubDate>
      <guid>http://www.stencilled.me/posts/2025-05-06-stop-asking-data/</guid>
      <description>The real problem isn&amp;#39;t the dashboard. It&amp;#39;s how we treat data as a checklist, not a conversation. Learn how to make analytics work harder for the right questions.</description>
    </item>
    <item>
      <title>Why Every Media Team Needs a Measurement Playbook (Not Just a Dashboard)</title>
      <link>http://www.stencilled.me/posts/2024-05-08-measurement-playbook/</link>
      <pubDate>Tue, 06 May 2025 00:00:00 +0000</pubDate>
      <guid>http://www.stencilled.me/posts/2024-05-08-measurement-playbook/</guid>
      <description>Demystifying media analytics tools like MMM and incrementality testing, and how to leverage them to move from tactical execution to strategic mastery.</description>
    </item>
    <item>
      <title>Why Every Media Team Needs an Analytics Agent</title>
      <link>http://www.stencilled.me/posts/2025-04-05-analytics-agents/</link>
      <pubDate>Sat, 19 Apr 2025 00:00:00 +0000</pubDate>
      <guid>http://www.stencilled.me/posts/2025-04-05-analytics-agents/</guid>
      <description>From dashboards to decisions — AI is now the analyst. Explore how analytics agents are transforming media teams by providing instant insights and automated analysis.</description>
    </item>
    <item>
      <title>The Death of Manual Data Analysis? Why AI Won&#39;t Replace You (Yet)</title>
      <link>http://www.stencilled.me/posts/2025-02-26-ai-wont-replace-analysts/</link>
      <pubDate>Sat, 05 Apr 2025 00:00:00 +0000</pubDate>
      <guid>http://www.stencilled.me/posts/2025-02-26-ai-wont-replace-analysts/</guid>
      <description>Exploring why AI tools enhance but don&amp;#39;t replace human data analysts, and how to leverage AI for better analytics.</description>
    </item>
    <item>
      <title>Resume</title>
      <link>http://www.stencilled.me/page/resume/</link>
      <pubDate>Fri, 04 Apr 2025 00:00:00 +0000</pubDate>
      <guid>http://www.stencilled.me/page/resume/</guid>
      <description>SENTHIL THYAGARAJAN (504) 908 0008 | senthil.thyagarajan@gmail.com Portfolio: http://www.stencilled.me https://www.linkedin.com/in/senthilthyagarajan/
PROFESSIONAL EXPERIENCE Analytics Director, Mekanism, New York, NY June 2023 –Present
Built real-time reporting dashboards with Supermetrics &amp;amp; BigQuery, integrating cross-channel data to improve decision-making. Developed a RAG tool that cut insight generation time by 30%, streamlining reporting and enhancing data-driven decision-making. Condensed 100+ slides into a one-page executive report, simplifying media insights for C-suite stakeholders. Embedded a data-driven culture, mentoring teams on analytics tools and integrating data into agency strategy.</description>
    </item>
    <item>
      <title>Resume</title>
      <link>http://www.stencilled.me/resume/</link>
      <pubDate>Fri, 04 Apr 2025 00:00:00 +0000</pubDate>
      <guid>http://www.stencilled.me/resume/</guid>
      <description>SENTHIL THYAGARAJAN PROFESSIONAL EXPERIENCE Analytics Director, Mekanism, New York, NY June 2023 –Present
Built real-time reporting dashboards with Supermetrics &amp;amp; BigQuery, integrating cross-channel data to improve decision-making. Developed a RAG tool that cut insight generation time by 30%, streamlining reporting and enhancing data-driven decision-making. Condensed 100+ slides into a one-page executive report, simplifying media insights for C-suite stakeholders. Embedded a data-driven culture, mentoring teams on analytics tools and integrating data into agency strategy.</description>
    </item>
    <item>
      <title>Empowering Media Campaigns with Dynamic Analytics</title>
      <link>http://www.stencilled.me/posts/empowering-media-campaigns/</link>
      <pubDate>Thu, 04 Apr 2024 00:00:00 +0000</pubDate>
      <guid>http://www.stencilled.me/posts/empowering-media-campaigns/</guid>
      <description>How to create effective interactive dashboards for media campaigns</description>
    </item>
    <item>
      <title>Building a Strong Data Infrastructure</title>
      <link>http://www.stencilled.me/posts/building-a-strong-data-infrastructure/</link>
      <pubDate>Thu, 21 Mar 2024 00:00:00 +0000</pubDate>
      <guid>http://www.stencilled.me/posts/building-a-strong-data-infrastructure/</guid>
      <description>Learn why establishing a robust data infrastructure is crucial for digital marketing and media campaigns, and how tools like ETL and data warehousing solutions can streamline your analytics process.</description>
    </item>
    <item>
      <title>Get over that data fatigue</title>
      <link>http://www.stencilled.me/posts/2020-08-15-datafatigue/</link>
      <pubDate>Sat, 15 Aug 2020 00:00:00 +0000</pubDate>
      <guid>http://www.stencilled.me/posts/2020-08-15-datafatigue/</guid>
      <description>Tips and tricks to overcome data fatigue using R and Google Sheets</description>
    </item>
    <item>
      <title>Whats Cooking ??</title>
      <link>http://www.stencilled.me/posts/2020-03-29-whatscooking/</link>
      <pubDate>Sun, 29 Mar 2020 00:00:00 +0000</pubDate>
      <guid>http://www.stencilled.me/posts/2020-03-29-whatscooking/</guid>
      <description>This R shiny app is for all the home chefs out there looking to try different recipes, especially now that we are all social distancing and looking at ways to keep us sane! (Yes, cooking is a form of meditation wherein the end, you have something to eat :D). From a database of 28000 + recipes, just enter the ingredients you wish to filter on and the type of cuisine and you will see all the recipes with your specified ingredients from your favorite cuisine!</description>
    </item>
    <item>
      <title>Styling DataTables</title>
      <link>http://www.stencilled.me/posts/2019-04-20-stylingdt/</link>
      <pubDate>Sat, 20 Apr 2019 00:00:00 +0000</pubDate>
      <guid>http://www.stencilled.me/posts/2019-04-20-stylingdt/</guid>
      <description>Most of the shiny apps have tables as the primary component. Now lets say you want to prettify your app and style the tables. All you need understand how tables are built using HTML. This is how the default datatable looks like in the app.
In order to build the html table I have used a function table_frame which can be used as a container in DT::renderdatatable. This function basically uses htmltools.</description>
    </item>
    <item>
      <title>Edit datatables in R shiny app</title>
      <link>http://www.stencilled.me/posts/2019-04-18-editable/</link>
      <pubDate>Thu, 18 Apr 2019 00:00:00 +0000</pubDate>
      <guid>http://www.stencilled.me/posts/2019-04-18-editable/</guid>
      <description>Tables are very much the standard way of representing data in dashboard along with visualizations. Wouldnt it be more useful if you could edit the values in the tables to trigger some calculations and update the values on the fly . These can be used for adjusting allocations or budgets in a project.
Libraries The libraries which we will be using are shiny for the app itself, dplyr and DT for displaying and editing the tables.</description>
    </item>
    <item>
      <title>Download and Email reports in R Shiny app</title>
      <link>http://www.stencilled.me/posts/2019-04-14-downloadshiny/</link>
      <pubDate>Sun, 14 Apr 2019 00:00:00 +0000</pubDate>
      <guid>http://www.stencilled.me/posts/2019-04-14-downloadshiny/</guid>
      <description>Most of the dashboards / R shiny app are viewed by the people who want to view the underyling data without doing much analysis. While they view the KPI&amp;rsquo;s , the charts and the tables it would be also an important for them to take the results out of the app for meetings and presenations. One of way doing it is the traditionally downloading the reports. But to make it one step easier they could also be given an option to email these reports.</description>
    </item>
    <item>
      <title></title>
      <link>http://www.stencilled.me/page/reading/</link>
      <pubDate>Tue, 25 Sep 2018 00:00:00 +0000</pubDate>
      <guid>http://www.stencilled.me/page/reading/</guid>
      <description> Injustice : God Among Us Year one - Tom Taylor 5/5 </description>
    </item>
    <item>
      <title>Colleges vs Breweries - What tops in your State ?</title>
      <link>http://www.stencilled.me/posts/2018-09-26-college-brewery/</link>
      <pubDate>Mon, 24 Sep 2018 00:00:00 +0000</pubDate>
      <guid>http://www.stencilled.me/posts/2018-09-26-college-brewery/</guid>
      <description>In this post we see how the no. of breweries stack up against no. of colleges across USA. Here I am using d3js and a grid bar chartwhere each grid represents 5 breweries/colleges.I collected the data for Brewery from Beer Advocate and for colleges from wikipedia
&lt;!DOCTYPE html&gt; More Breweries than Colleges Breweries vs Colleges in US = 5 Top 10 States Bottom 10 States College Brewery &amp;lt;script src=&amp;quot;https://cdnjs.cloudflare.com/ajax/libs/d3/4.4.4/d3.min.js&amp;quot;&amp;gt;&amp;lt;/script&amp;gt; &amp;lt;script src=&amp;quot;https://cdnjs.</description>
    </item>
    <item>
      <title>Google Trends using gtrends and R shiny</title>
      <link>http://www.stencilled.me/posts/2018-09-24-gtrends/</link>
      <pubDate>Mon, 24 Sep 2018 00:00:00 +0000</pubDate>
      <guid>http://www.stencilled.me/posts/2018-09-24-gtrends/</guid>
      <description>Recently while I was searching for trend data I came across Google Trends. So in the post I am using gtrends, a r package to understand the trends and display it using a R shiny app using the shinymaterial package. The shinymaterial package tends to move away from the traditional shiny dashboard layouts and design. You can use this shiny app from here.</description>
    </item>
    <item>
      <title>Visualizing your favourite song?</title>
      <link>http://www.stencilled.me/posts/2018-10-02-song-wave/</link>
      <pubDate>Mon, 24 Sep 2018 00:00:00 +0000</pubDate>
      <guid>http://www.stencilled.me/posts/2018-10-02-song-wave/</guid>
      <description>Recently I was searching for some gifts when I stumbled across Sound Viz and Cumberland Coast . These were your favorite songs which were visualized and printed. So that&amp;rsquo;s when I started looking into on how could you visualize them. So I wanted to try the same and that’s when I came across the r packages tuneR and seewave. Now I knew that I wanted to visualize the song but then I also wanted to see how different are the visualizations for the same song in an original version and the acoustic version.</description>
    </item>
    <item>
      <title>MTA Subway Ridership</title>
      <link>http://www.stencilled.me/posts/2018-08-16-mta-subway-ridership/</link>
      <pubDate>Thu, 16 Aug 2018 00:00:00 +0000</pubDate>
      <guid>http://www.stencilled.me/posts/2018-08-16-mta-subway-ridership/</guid>
      <description> </description>
    </item>
    <item>
      <title>Visualizing Airbnb listings.</title>
      <link>http://www.stencilled.me/posts/2017-10-25-airbnb-listing/</link>
      <pubDate>Wed, 25 Oct 2017 00:00:00 +0000</pubDate>
      <guid>http://www.stencilled.me/posts/2017-10-25-airbnb-listing/</guid>
      <description>In this day and age of so many sharing services like Uber and Lyft , pricey hotels are being replaced by Airbnb. Students, working people and travelers wouldn&amp;rsquo;t always want to pay a high price for staying a couple of nights at the Marriott and would rather stay at a place where that has the basic amenities needed for them at a reasonable price. In this project I am trying to understand the listings put on Airbnb on how the price varies by neighborhood ,house type and various other factors.</description>
    </item>
    <item>
      <title>Taps near you</title>
      <link>http://www.stencilled.me/posts/2017-09-18-taps-near-you/</link>
      <pubDate>Mon, 18 Sep 2017 00:00:00 +0000</pubDate>
      <guid>http://www.stencilled.me/posts/2017-09-18-taps-near-you/</guid>
      <description>While working on a couple of projects involving beer data I did land up at breweries association. They have a data set on all the breweries across the US. This raw html table was scrapped ,cleaned and geocoded using R. You can find the R Scripts which I used for this project here.
Once the data was ready this was put to use by being displayed on a web mapping application built on js and bootstrap.</description>
    </item>
    <item>
      <title>States to Shapes</title>
      <link>http://www.stencilled.me/posts/2017-05-10-states-to-shapes/</link>
      <pubDate>Wed, 10 May 2017 00:00:00 +0000</pubDate>
      <guid>http://www.stencilled.me/posts/2017-05-10-states-to-shapes/</guid>
      <description>&lt;p&gt;I started working on this visualation after coming across  &lt;a href=&#34;https://bl.ocks.org/mbostock/3081153&#34;&gt;Mike Bostock&amp;rsquo;s shape tweening bl.ock&lt;/a&gt; ,
which was done for one state. The source for this data is
Insurance Institute for Highway Service(IIHS). The size of the square is based on the motor vehicle deaths per 100,000 people(2015).&lt;/p&gt;</description>
    </item>
    <item>
      <title>Breweries or Wineries ??</title>
      <link>http://www.stencilled.me/posts/2017-04-29-whats-your-states-poison/</link>
      <pubDate>Sat, 29 Apr 2017 00:00:00 +0000</pubDate>
      <guid>http://www.stencilled.me/posts/2017-04-29-whats-your-states-poison/</guid>
      <description>&lt;style&gt;

.myIframe {
position: relative;
padding-bottom: 65.25%;
padding-top: 30px;
height: 0;
overflow: auto;
-webkit-overflow-scrolling:touch; //&lt;&lt;--- THIS IS THE KEY
border: solid black 1px;
}
.myIframe iframe {
position: absolute;
top: 0;
left: 0;
width: 100%;
height: 100%;
}
&lt;/style&gt;
&lt;p&gt;When you think about Texas, the first thing that would come in mind is barbecue which of course  pairs well with a good beer. In this post I have mapped each state in the
US ranked based on the breweries or wineries present. I got the data from the Brewers Association and the American Winery Guide. With data visualization being so
important in representing the dataset I have used hexbins shapefile from   &lt;a href=&#34;https://github.com/donmeltz/US-States---Hexbins&#34;&gt;Don Meltz&amp;rsquo;s repo&lt;/a&gt;.&lt;/p&gt;</description>
    </item>
    <item>
      <title>Maps and gifs</title>
      <link>http://www.stencilled.me/posts/2017-03-20-map-gif-r/</link>
      <pubDate>Mon, 20 Mar 2017 00:00:00 +0000</pubDate>
      <guid>http://www.stencilled.me/posts/2017-03-20-map-gif-r/</guid>
      <description>As I have been using R for a while, one of the things I wanted to do was a time series map. Most of the time series maps I see have sliders to change the years. While looking at how to make time series maps I happened to lear how to make a GIF with a set of images.
So I thought, how about making an election based map over the past elections.</description>
    </item>
    <item>
      <title>Top Beers in 2016.</title>
      <link>http://www.stencilled.me/posts/2017-02-22-topbeers2016/</link>
      <pubDate>Wed, 22 Feb 2017 00:00:00 +0000</pubDate>
      <guid>http://www.stencilled.me/posts/2017-02-22-topbeers2016/</guid>
      <description>&lt;style&gt;

.myIframe {
position: relative;
padding-bottom: 65.25%;
padding-top: 30px;
height: 0;
overflow: auto;
-webkit-overflow-scrolling:touch; //&lt;&lt;--- THIS IS THE KEY
border: solid black 1px;
}
.myIframe iframe {
position: absolute;
top: 0;
left: 0;
width: 100%;
height: 100%;
}
&lt;/style&gt;
&lt;p&gt;After completing my previous post on food I wanted to work on something which I have started to explore recently,craft beer.
A friend of mine introduced me to a beer club membership prior to which I never knew anything beyond the Corona&amp;rsquo;s .
Then began the collection and here it is, what  have so far.&lt;/p&gt;</description>
    </item>
    <item>
      <title>Where do people eat in Austin ??</title>
      <link>http://www.stencilled.me/posts/2017-02-15-foursquare/</link>
      <pubDate>Wed, 15 Feb 2017 00:00:00 +0000</pubDate>
      <guid>http://www.stencilled.me/posts/2017-02-15-foursquare/</guid>
      <description>&lt;p&gt;Recently I visited Austin and many of my friends had mentioned about the variety in food options here.
So my wife and I decided to search for places to eat on the foursquare app. As a standard search filter
with high rating we ended up at pretty good places and foursquare did alert us to checkins whenever we
reached a place. Post the trip I wanted to see how many people do checkins using this app and how the checkins are
correlated with the ratings.&lt;/p&gt;</description>
    </item>
    <item>
      <title>NFL Season 2016-17</title>
      <link>http://www.stencilled.me/posts/2017-01-29-nfl/</link>
      <pubDate>Sun, 29 Jan 2017 00:00:00 +0000</pubDate>
      <guid>http://www.stencilled.me/posts/2017-01-29-nfl/</guid>
      <description>&lt;p&gt;Hello World !!! This is my first project using d3js. Being a GIS professional, visualization is always a part of job.
I always wanted to learn different ways for visualizing data.Let it be a simple plot using R or a choropleth map using Arcmap .&lt;/p&gt;
&lt;p&gt;In this project I am trying to display how the NFL season 2016-17 went about. Ofcourse was surprised to see the Cowboys doing so well.
May be we got our own Tom Brady.I started working with the data grabbed from the NFL site for how the season went by each seasson.
Below is the location for the each team.&lt;/p&gt;</description>
    </item>
    <item>
      <title></title>
      <link>http://www.stencilled.me/firstpost/</link>
      <pubDate>Fri, 11 Jul 2014 10:54:24 +0200</pubDate>
      <guid>http://www.stencilled.me/firstpost/</guid>
      <description></description>
    </item>
    <item>
      <title></title>
      <link>http://www.stencilled.me/page/about/</link>
      <pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate>
      <guid>http://www.stencilled.me/page/about/</guid>
      <description>Hello, I’m Senthil Thyagarajan. My journey began with a school stencil, sparking a passion for mapping that evolved into a career in data analytics. As the Analytics Director at Mekanism and the founder of Stencilled, I specialize in transforming complex data into clear, visual narratives that drive informed decision-making. I integrate the latest AI trends into real-time reporting and strategic insights, ensuring every project is both innovative and impactful.
Outside of work, I’m a dedicated LEGO builder—currently immersed in Formula 1 sets—and an enthusiastic home cook who loves experimenting with new recipes.</description>
    </item>
    <item>
      <title></title>
      <link>http://www.stencilled.me/page/blogroll/</link>
      <pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate>
      <guid>http://www.stencilled.me/page/blogroll/</guid>
      <description>R-Bloggers</description>
    </item>
    <item>
      <title>Content Calendar 2025: Web Development in Ad Analytics</title>
      <link>http://www.stencilled.me/calendar/</link>
      <pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate>
      <guid>http://www.stencilled.me/calendar/</guid>
      <description>Technical content strategy for ad analytics roles</description>
    </item>
  </channel>
</rss>
