<?xml version="1.0" encoding="utf-8" standalone="yes"?><?xml-stylesheet type="text/xsl" href="/rss.xsl"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Blog on ApplauseLab</title><link>https://applauselab.ai/blog/</link><description>Case studies, field notes, and AI-native workflows from systems operating under real constraints.</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Mon, 03 Aug 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://applauselab.ai/blog/index.xml" rel="self" type="application/rss+xml"/><item><title>Hamal: An Agentic Harness for Local Repository Work</title><link>https://applauselab.ai/blog/hamal-agentic-harness/</link><pubDate>Mon, 03 Aug 2026 00:00:00 +0000</pubDate><guid>https://applauselab.ai/blog/hamal-agentic-harness/</guid><description>&lt;p&gt;Most coding agents look straightforward while they are still a prompt box. The difficult part starts when a model asks to read a file, write code, run a command, pause for input, or continue later without losing what happened.&lt;/p&gt;
&lt;p&gt;Hamal is our attempt to make that difficult part explicit.&lt;/p&gt;
&lt;p&gt;It is an experimental, Effect-native local coding agent organized as an npm workspace. Effect is the typed runtime and composition foundation beneath the workspace, not a wrapper added at the edge.&lt;/p&gt;
&lt;p&gt;The product navigation calls Hamal an &lt;strong&gt;agentic harness&lt;/strong&gt;. That means a bounded model and tool-execution loop around local repository work, not an autonomous magic box.&lt;/p&gt;
&lt;p&gt;&lt;strong&gt;TL;DR:&lt;/strong&gt; Hamal keeps project selection, provider and model choice, tools, permissions, durable run state, context management, and capability UI inside one local harness. It supports an interactive terminal UI and a plain headless mode. It is currently an experimental private preview, its APIs can change, no open-source license has been selected, and it is not ready for redistribution.&lt;/p&gt;</description></item><item><title>Introducing xHeal V2: One App for Your Health, Powered by ApplauseLab</title><link>https://applauselab.ai/blog/introducing-xheal-v2/</link><pubDate>Sun, 12 Jul 2026 18:00:00 +0300</pubDate><guid>https://applauselab.ai/blog/introducing-xheal-v2/</guid><description>&lt;p&gt;Your health data should not be scattered across apps, PDFs, wearables, and notes.&lt;/p&gt;
&lt;p&gt;&lt;a href="https://xheal.ai/"&gt;xHeal V2&lt;/a&gt; brings health records, lab results, Apple Health data, workouts, nutrition, mindfulness, and daily health metrics into one secure app. It helps people organize their information, understand wellness patterns, and build healthier habits with AI-powered insights grounded in the information they choose to add.&lt;/p&gt;
&lt;p&gt;V2 is more than a visual update. It is the clearest expression yet of what we are building at ApplauseLab: a connected product powered by our reusable &lt;strong&gt;Infrastructure Layer&lt;/strong&gt; and &lt;strong&gt;Intelligence Layer&lt;/strong&gt;.&lt;/p&gt;
&lt;p&gt;xHeal is the flagship venture and primary product of our venture studio. It is where those layers are being tested, refined, and proven in a real product people can download and use today.&lt;/p&gt;</description></item><item><title>From Digithon to Digitalk: Bulgaria's Tech Ecosystem Has Never Felt More Alive</title><link>https://applauselab.ai/blog/from-digithon-to-digitalk/</link><pubDate>Sun, 12 Jul 2026 17:30:00 +0300</pubDate><guid>https://applauselab.ai/blog/from-digithon-to-digitalk/</guid><description>&lt;p&gt;What were you building at 17 or 18 years old?&lt;/p&gt;
&lt;p&gt;At &lt;a href="https://www.digitalkconference.com/"&gt;Digitalk Conference&lt;/a&gt; in Sofia, I watched three teams of founders aged 17-19 present products live in front of a jury and the full conference audience.&lt;/p&gt;
&lt;p&gt;They were the three teams that had earned the top places at Digithon two days earlier. Now their ideas had moved from a fast-paced hackathon into one of Southeast Europe&amp;rsquo;s leading technology and business events.&lt;/p&gt;
&lt;p&gt;The products were impressive. The bigger story was the ecosystem forming around the people who built them.&lt;/p&gt;</description></item><item><title>Leading by Example: Mentoring the Next Generation at Digithon</title><link>https://applauselab.ai/blog/leading-by-example-at-digithon/</link><pubDate>Sun, 12 Jul 2026 00:00:00 +0000</pubDate><guid>https://applauselab.ai/blog/leading-by-example-at-digithon/</guid><description>&lt;p&gt;Four students. One ambitious idea. Just a couple of hours to turn it into a working MVP.&lt;/p&gt;
&lt;p&gt;On June 7, I joined &lt;a href="https://www.digithon.tech/"&gt;Digithon&lt;/a&gt; in Sofia as a mentor to a team of four students from TUES. They were in 10th and 11th grade, aged 16-17, but they approached the challenge with the energy and ambition of a team preparing to launch a real product.&lt;/p&gt;
&lt;p&gt;By the end of the day, they had built an AI-assisted revenue management system designed for large grocery chains in the United States.&lt;/p&gt;
&lt;p&gt;That result was impressive. The people behind it were even more impressive.&lt;/p&gt;</description></item><item><title>Bachkator: Terraform for Your Agent Loops</title><link>https://applauselab.ai/blog/bachkator-terraform-for-agent-loops/</link><pubDate>Wed, 10 Jun 2026 00:00:00 +0300</pubDate><guid>https://applauselab.ai/blog/bachkator-terraform-for-agent-loops/</guid><description>&lt;p&gt;Its name comes from Bulgarian: &lt;strong&gt;бачкатор&lt;/strong&gt; (pronounced &lt;em&gt;BAHCH-kah-tor&lt;/em&gt;) means &amp;ldquo;the hard worker,&amp;rdquo; the one who gets the job done.&lt;/p&gt;
&lt;p&gt;We have been using the tool internally for about a month, and it has been useful enough that we decided to clean it up and share it.&lt;/p&gt;</description></item><item><title>Temporal Workflows, Now One Raycast Command Away</title><link>https://applauselab.ai/blog/temporal-workflows-one-raycast-command-away/</link><pubDate>Sun, 07 Jun 2026 00:00:00 +0000</pubDate><guid>https://applauselab.ai/blog/temporal-workflows-one-raycast-command-away/</guid><description>&lt;p&gt;We use Temporal every day at Applause Lab. It is how we build reliable, long-running systems without turning every retry, timeout, and recovery path into application glue.&lt;/p&gt;
&lt;p&gt;But when you live in Temporal daily, the small operational loops start to add up. You jump between the Temporal UI, the CLI, local namespaces, staging, production, workflow histories, schedules, and a browser tab you probably already lost under five others.&lt;/p&gt;
&lt;p&gt;Raycast is already where we open tools, run commands, and move through our work. So we brought Temporal into that flow.&lt;/p&gt;</description></item><item><title>Yap: A Lightweight, Open-Source Dictation Tool</title><link>https://applauselab.ai/blog/building-yap-in-public/</link><pubDate>Mon, 01 Jun 2026 00:00:00 +0000</pubDate><guid>https://applauselab.ai/blog/building-yap-in-public/</guid><description>&lt;p&gt;We built Yap because we wanted a dictation tool that felt like a utility, not a platform.&lt;/p&gt;
&lt;p&gt;Lightweight. Minimal. Open source. Easy to run. Easy to understand. Easy to change if your workflow needs something different.&lt;/p&gt;
&lt;p&gt;The basic loop is simple: press a hotkey, speak, transcribe, and paste the result into whatever app already has focus. No new writing surface. No heavy workspace. No assumption that everyone wants the same workflow.&lt;/p&gt;</description></item><item><title>Introducing Atelier and the ServiceNow Architect AgentPack</title><link>https://applauselab.ai/blog/introducing-atelier-servicenow-architect-agentpack/</link><pubDate>Mon, 12 May 2025 00:00:00 +0000</pubDate><guid>https://applauselab.ai/blog/introducing-atelier-servicenow-architect-agentpack/</guid><description>&lt;p&gt;The workflows that run a company are not neat little tasks. They live across email, documents, delivery notes, project history, approvals, and the judgement of the people doing the work.&lt;/p&gt;
&lt;p&gt;That is what we built Atelier for: hyperautomation for the work that actually moves the business.&lt;/p&gt;
&lt;p&gt;Atelier ingests operational data, encodes an AgentPack against how a business actually decides, and runs it alongside the team. HR, delivery, operations, marketing, engineering, the workflows that carry the company can become runnable systems instead of scattered process knowledge.&lt;/p&gt;</description></item></channel></rss>