Speaker

Harish Kotra

Harish Kotra

Developer Relations, Hackathons Specialist & A No-Code Educator

డెవలపర్ రిలేషన్స్, హ్యాకథాన్ స్పెషలిస్ట్ & నో-కోడ్ ఎడ్యుకేటర్

डेवलपर रिलेशंस, हैकाथॉन विशेषज्ञ और नो-कोड शिक्षक

Hyderābād, India

Actions

I have spent 13 years in developer relations and community, most recently as Community Lead at AngelHack, running 200+ hackathons across India, Maldives, Sri Lanka, Bangladesh, and Dubai. Today I help teams launch and scale their own AI agents, and I have shipped one working AI build every day for over 300 days at DailyBuild.xyz.

I was DevX Lead at an AI infrastructure startup, at Quirq (xo.builders) where teams launch autonomous agents on private infrastructure in seconds. Previously as a Developer Advocate at Gaia 🌱 (https://gaianet.ai), I focused on onboarding developers and enterprises to create, launch and scale their own AI agents.

Since January 2026 I have shipped one working AI build every day, now past 300 consecutive days at DailyBuild.xyz. That is where most of my recent agent, CLI and local-first work lives.

Before this I was Community Lead at AngelHack for over 11 years, a global company dedicated to developer relations and building diverse communities of change makers and innovators worldwide. I am also a passionate advocate for no-code technology and believe in empowering individuals to bring their own ideas to life without coding. I have helped run some of the best hackathons and developer competitions globally, hosting and running over 200 hackathons for developers and students across India, Maldives, Sri Lanka, Bangladesh, Pakistan, Dubai and more countries.

In my spare time I help entrepreneurs build and automate anything without coding and create YouTube content on no-code. I have worked with Microsoft, Discover, IBM, AWS, Mastercard, Jina.ai, DataStax, Consensys, Algorand, Celo, Zepeto and Polkadot on their developer acquisition and developer relations.

గత 13 సంవత్సరాలుగా నేను డెవలపర్ రిలేషన్స్ మరియు కమ్యూనిటీ రంగంలో పని చేస్తున్నాను. చివరిగా AngelHackలో Community Leadగా ఉన్నాను, అక్కడ భారతదేశం, మాల్దీవులు, శ్రీలంక, బంగ్లాదేశ్ మరియు దుబాయ్లో 200కి పైగా హ్యాకథాన్లు నిర్వహించాను. ఈరోజు నేను జట్లు తమ సొంత AI ఏజెంట్లను ప్రారంభించడంలో, స్కేల్ చేసుకోవడంలో సహాయం చేస్తున్నాను. అలాగే DailyBuild.xyzలో 300కి పైగా రోజుల పాటు ప్రతిరోజూ ఒక పనిచేసే AI బిల్డ్ను షిప్ చేశాను.

నేను ఒక AI ఇన్ఫ్రాస్ట్రక్చర్ స్టార్టప్లో, Quirq (xo.builders)లో DevX Leadగా ఉన్నాను. ఇక్కడ జట్లు తమ ఆటోనామస్ ఏజెంట్లను క్షణాల్లో ప్రైవేట్ ఇన్ఫ్రాస్ట్రక్చర్పై లాంచ్ చేయవచ్చు. అంతకుముందు Gaia (gaianet.ai)లో Developer Advocateగా, డెవలపర్లు మరియు ఎంటర్ప్రైజెస్ తమ AI ఏజెంట్లను సృష్టించి, లాంచ్ చేసి, స్కేల్ చేసుకోవడంలో సహాయపడటంపై దృష్టి పెట్టాను.

జనవరి 2026 నుంచి నేను ప్రతిరోజూ ఒక పనిచేసే AI బిల్డ్ను షిప్ చేస్తున్నాను. ఇప్పుడు DailyBuild.xyzలో 300 కంటే ఎక్కువ వరుస రోజులు పూర్తయ్యాయి. నా ఇటీవలి ఏజెంట్, CLI మరియు లోకల్-ఫస్ట్ పని చాలావరకు అక్కడే ఉంది.

అంతకుముందు నేను AngelHackలో 11 సంవత్సరాలకు పైగా Community Leadగా ఉన్నాను. ఇది డెవలపర్ రిలేషన్స్కు అంకితమైన, ప్రపంచవ్యాప్తంగా విభిన్న సమాజాలను నిర్మించే గ్లోబల్ కంపెనీ. నేను నో-కోడ్ టెక్నాలజీకి బలమైన ప్రతిపాదకుడిని, కోడింగ్ లేకుండా తమ ఆలోచనలను జీవితంలోకి తీసుకురావడానికి ప్రజలను సన్నద్ధం చేయాలని నమ్ముతాను. భారతదేశం, మాల్దీవులు, శ్రీలంక, బంగ్లాదేశ్, పాకిస్తాన్, దుబాయ్ మరియు మరెన్నో దేశాల్లో డెవలపర్లు మరియు విద్యార్థుల కోసం 200కి పైగా హ్యాకథాన్లు నిర్వహించి, ప్రపంచంలోని ఉత్తమ హ్యాకథాన్లు మరియు డెవలపర్ పోటీలను నిర్వహించడంలో సహాయం చేశాను.

ఖాళీ సమయంలో, ఎంటర్ప్రెన్యూ�������్లు ��ోడింగ్ లేకుండా ఏదైనా నిర్మించడంలో, ఆటోమేట్ చేయడంలో సహాయం చేస్తాను, నో-కోడ్పై YouTube కంటెంట్ చేస్తాను. Microsoft, Discover, IBM, AWS, Mastercard, Jina.ai, DataStax, Consensys, Algorand, Celo, Zepeto మరియు Polkadotలతో వాటి డెవలపర్ అక్విజిషన్ మరియు డెవలపర్ రిలేషన్స్ విషయంలో కలిసి పని చేశాను.

मैंने पिछले 13 साल डेवलपर रिलेशंस और कम्युनिटी में बिताए हैं। सबसे हाल में मैं AngelHack में Community Lead था, जहाँ मैंने भारत, मालदीव, श्रीलंका, बांग्लादेश और दुबई में 200 से ज़्यादा हैकाथॉन चलाए। आज मैं टीमों को उनके अपने AI एजेंट लॉन्च करने और स्केल करने में मदद करता हूँ, और DailyBuild.xyz पर 300 से ज़्यादा दिन से हर दिन एक चलने वाला AI बिल्ड शिप कर रहा हूँ।

मैं एक AI इंफ्रास्ट्रक्चर स्टार्टअप, Quirq (xo.builders) में DevX Lead था, जहाँ टीमें कुछ ही सेकंड में प्राइवेट इंफ्रास्ट्रक्चर पर अपने ऑटोनॉमस एजेंट लॉन्च कर सकती हैं। इससे पहले Gaia (gaianet.ai) में Developer Advocate के रूप में मेरा फोकस डेवलपर्स और एंटरप्राइज़ेस को उनके AI एजेंट बनाने, लॉन्च करने और स्केल करने में मदद करना था।

जनवरी 2026 से मैं हर दिन एक चलने वाला AI बिल्ड शिप कर रहा हूँ, और DailyBuild.xyz पर अब 300 से ज़्यादा लगातार दिन पूरे हो चुके हैं। मेरा हाल का ज़्यादातर एजेंट, CLI और लोकल-फर्स्ट काम वहीं है।

इससे पहले मैं 11 साल से ज़्यादा AngelHack में Community Lead रहा, एक ग्लोबल कंपनी जो डेवलपर रिलेशंस के लिए समर्पित है और दुनिया भर में बदलाव लाने वाले लोगों के विविध समुदाय बनाती है। मैं नो-कोड टेक्नोलॉजी का प्रबल समर्थक हूँ और मानता हूँ कि लोगों को बिना कोडिंग के अपने आइडिया ज़िंदा करने का हुनर मिलना चाहिए। मैंने दुनिया के कुछ बेहतरीन हैकाथॉन और डेवलपर प्रतियोगिताओं को चलाने में मदद की है, और भारत, मालदीव, श्रीलंका, बांग्लादेश, पाकिस्तान, दुबई और अन्य देशों में डेवलपर्स और छात्रों के लिए 200 से ज़्यादा हैकाथॉन होस्ट किए हैं।

खाली समय में मैं उद्यमियों को बिना कोडिंग के कुछ भी बनाने और ऑटोमेट करने में मदद करता हूँ, और नो-कोड पर YouTube कंटेंट बनाता हूँ। मैंने Microsoft, Discover, IBM, AWS, Mastercard, Jina.ai, DataStax, Consensys, Algorand, Celo, Zepeto और Polkadot के साथ उनके डेवलपर एक्विज़िशन और डेवलपर रिलेशंस पर काम किया है।

Badges

Area of Expertise

  • Business & Management
  • Government, Social Sector & Education
  • Information & Communications Technology

Topics

  • No-Code Tools
  • AI
  • AI Agents
  • Generative AI
  • LLMs
  • Generative AI Use Cases
  • AI & ML Solutions
  • AI for Startups
  • AI for Social Good
  • AI Builder
  • AI / Copilot
  • AI & Machine Learning
  • Decentralized AI

Dead Reckoning for gRPC Streams: Resumable AI Inference

Server-streaming gRPC is the natural fit for LLM token delivery, until the stream drops. Today, a mid-stream failure means retrying from token zero: wasteful, expensive, and broken for users. HTTP solved this with Range headers in 1999. gRPC has no equivalent for streams.

This talk introduces a resumable streaming protocol built on top of standard gRPC. Using a session cursor, a lightweight server-side token journal, and periodic ACKs, dropped streams resume from the last confirmed token, not from scratch. We'll cover why this is a checkpointing problem (not a retry problem), how to size the journal TTL, and where LLM non-determinism makes naive resumption unsafe. Live demo: a gRPC-streamed LLM generation gets killed mid-sentence and resumes seamlessly on reconnect.

Build an Agent You Can Trust: Hands-On Harness, Traces and Evals

A hands-on session where you build a small AI agent and then make it trustworthy. Bring a laptop; we ship code, not slides. We start with a minimal agent loop against an OpenAI-compatible model.

Then we add the parts that separate a demo from something you would run in production: a structured, replayable trace of every step; a small eval suite with five real cases; and a guardrail that fails loudly instead of silently. The best part is the failure. We deliberately break the agent with a prompt injection and watch the trace tell us exactly where it went wrong. Then we fix it and prove the fix with the evals.

You leave with a working repo you can extend after DevFest, and a repeatable loop for evaluating any agent you build.

Running MCP Fully Local: Private, Offline-Capable Agents with Ollama and Open Models

Over the last few months I've built and shipped 100+ agents in public, many wired into MCP servers running against local models through Ollama, LM Studio, and decentralized open-source inference. A draw.io MCP server driven by Llama 3.2, an Excalidraw MCP integration, a Bright Data MCP briefing agent, all running end-to-end without a single token leaving the host.

This talk is a working engineer's tour of that stack. We'll walk through a minimal local MCP setup (server + client + Ollama) and then dig into the real-world failure modes: tool-selection collapse on 7B models, JSON-schema compliance gaps, capability-negotiation mismatches, and the surprisingly large quality delta between structured-output fine-tunes and general chat models. I'll share the prompt shapes, tool-description patterns, and schema-validation tricks that reliably push small open models from "demo-grade" to "I'd ship this internally."

Attendees will leave with a reference architecture for private MCP, a shortlist of open models that actually handle tool calls well today, and a set of design patterns for MCP servers that degrade gracefully when the client LLM has 8B parameters instead of a trillion.

Clone Yourself with Local LLMs

Master the Retrieval-Augmented Generation (RAG) pipeline for personal data using open-source models, local vector stores, and lightweight tools to achieve “style cloning” without costly fine-tuning.

In this 45-minute hands-on session, you’ll build a self-sovereign AI agent that writes like you - powered by a privacy-first, open-source framework.

We start with Data Sovereignty: learn how to legally export your data (e.g., X/Twitter or LinkedIn archives) and convert JSON or CSV files into a clean “voice corpus.”

Next, explore Voice Vectorization via RAG - embedding your content into a private vector store so your AI “remembers” your style and topics without retraining.

Finally, Deploy the LLM (e.g., Gemma 3) locally and apply prompt engineering to generate authentic, on-topic content: tweets, posts, or emails, in your own voice.

Leave with portable code to run the agent entirely offline: $0 API costs, full privacy, and total control of your digital persona.

100 Agents in 100 Days: Patterns and Anti-Patterns for MCP-Based Multi-Agent Systems

Multi-agent systems on MCP are where most of the interesting architectural questions live: routing, state, retries, coordination, and what happens when any one of N tool calls misbehaves. Most talks on the topic are theoretical. This one is not.

Since early 2026 I've published one new AI agent every day at dailybuild.xyz. Many of them are multi-agent: price-war simulations, research pipelines, a local agent orchestration studio, a recursive research loop, human-in-the-loop travel planners, and a "swarm CFO" with policy-gated spend. Dozens of them plug into MCP servers.

In this session I'll pull out the ten orchestration patterns I now use by default when MCP is in the mix, and the ten I've thrown out. Topics include: why single-agent-with-many-tools usually beats a team of agents until it suddenly doesn't; how to design a router that survives tool-name collisions across multiple MCP servers; state strategies that don't rot; retry and compensation patterns for idempotent vs non-idempotent tools;

Every pattern in the talk is tied to a specific public build with working code, so attendees can go verify, fork, or challenge anything I claim.

OpenSearch with Gaia: Building Next-Gen AI-Driven Search and Analytics Workflows

This session explores how Gaia’s decentralized AI platform integrates with OpenSearch to create scalable, privacy-preserving solutions for semantic search, generative AI applications, and real-time analytics.

In this session, I intend to demonstrate a use case where Gaia’s federated learning models enhance OpenSearch’s vector database capabilities, enabling dynamic personalization and efficient retrieval-augmented generation (RAG) workflows.

Gaia’s AI Framework: How Gaia’s decentralized architecture complements OpenSearch’s ecosystem, particularly in scenarios requiring data privacy and distributed model training (e.g., healthcare or financial analytics).

Demo a RAG Pipeline: Build a real-world demo/example using Gaia’s language models to generate embeddings stored in OpenSearch’s binary vector indexes (new in v2.19), coupled with OpenSearch Flow for automated pipeline configuration.

Community Impact: A look at how this integration supports OpenSearch’s goal of becoming the preferred backend for generative AI while adhering to open governance principles.

gRPConf India 2026 Sessionize Event Upcoming

November 2026 Bengaluru, India

MCP Dev Summit Mumbai 2026 Sessionize Event

June 2026 Mumbai, India

MCP Dev Summit Bengaluru 2026 Sessionize Event

June 2026 Bengaluru, India

AI Community Conference - AICO Seoul Sessionize Event

November 2025

OpenSearchCon India 2025 Sessionize Event

June 2025 Bengaluru, India

Harish Kotra

Developer Relations, Hackathons Specialist & A No-Code Educator

Hyderābād, India

Actions

Please note that Sessionize is not responsible for the accuracy or validity of the data provided by speakers. If you suspect this profile to be fake or spam, please let us know.

Jump to top