XConf India 2026 Hyderabad
as the organisers put it
XConf is Thoughtworks' annual technology event created by technologists, for technologists who care deeply about software and its impact on the world.
| title | author | length |
|---|---|---|
| wrap up | 02m | |
Wrap up lists concrete outcomes from XConf India 2026: 580 technologists, 31 speakers, 15 expert sessions, focused on AI-first software delivery, agentic AI… | ||
| Top game changing technology trends shaping the IT industry | Bharani Subramaniam, Vanya Seth | 01h 01m |
Eight actionable trends focus on turning models into reliable systems: harness engineering++ (prompts, memory, skills, storage, orchestration, tool calls… | ||
| Build an AI knowledge fabric for your organisation | Sunit Parekh | 30m |
Claims an agent‑optimized semantic layer stops LLM hallucination and latency by constraining models with three concrete pillars: engineering defaults, industry… | ||
| AI First Legacy Migration | Muskaan Dhanda | 30m |
An agentic orchestration pipeline extracts language‑agnostic specs using CodeGraph, LLM agents, Ader and Glean, then deterministically regenerates apps with a… | ||
| Engineering the harness | Jaya Simha Reddy Nandyala, Prabina Pani | 31m |
Two teams—one with a 28‑repo brownfield platform and one greenfield agentic workflow—build a shared harness called an AIKit wrapper that centralizes skills… | ||
| But it worked in my PoC! | Divye Singh, Madhukar Bhandari | 26m |
Deploying agents to push updates across thousands of devices initially works in a five-agent PoC but fails in QA with 2 minute replies, 3M tokens per run and… | ||
| Deep research at scale | Rathlavath Sindhu, Ishaan Bhatnagar | 33m |
Blueprint for scaling an LLM pipeline to 15M+ documents with measurable results: use HPC-based retrieval plus hybrid search (BM25 + HNSW ANN), enrich documents… | ||
| TFM based Shared Intelligence Layer | Muralikrishnan Puthanveedu, Shrijayan Rajendran, Mitra Bhanu Rath | 31m |
Claim: replacing permutation‑invariant aggregates with sequence‑aware Transaction Foundation Models (TFMs) and a shared intelligence layer gives big… | ||
| Human in the loop is not enough | Uday Kumar S S, Navin Govindarasu, Piyush S | 42m |
Claim: human review breaks at scale (10k–100k outputs/day) so security must move from manual controls to continuous AI-assisted pentesting, automated… | ||
| One guardrail is not enough: Defense-in-depth against LLM jailbreaks | Nitin Gupta | 26m |
Production chatbots leak contracts and data; OWASP ranks prompt injection #1 and RAG/fine-tuning don’t remove it. The pipeline runs on AWS with a fine-tuned… | ||
| The AI Kill Chain | Nalinikanth Meesala | 33m |
Shows a concrete AI kill chain: a malicious PyPI library is planted, a resume white-on-white prompt injects instructions into an ATS, retrieval poisoning and… | ||
| nothing matches | ||