Enterprise AI in Production: Mumbai Call for Proposals
Share what it takes to run AI inside an enterprise: architectures, trade-offs, and lessons from production.
Accepting submissions till 18 Oct 2026, 11:50 PM
Not accepting submissions
What to include in your submission
- Title and one-line pitch: what will the audience learn?
- Abstract, 200–400 words: the problem, implementation, key decisions, and outcome.
- Architecture summary: components, data flows, models, and tools. A diagram is welcome.
- Production evidence: scale, time in production, measured results, and how you measured them. State where figures are approximate or anonymised.
- Failures and trade-offs: at least one thing that went wrong or that you would do differently.
- Three takeaways: specific things attendees can apply.
- Audience and prerequisites: who the session is for and what they should already know.
- Preferred format: 30-minute talk or 45-minute deep dive, including questions.
- Speaker details: name, role, organisation, short biography, contact details, and a professional profile. Prior talks or writing are optional.
- Disclosures and availability: commercial interests, confidentiality constraints, and your availability to speak in Mumbai on 31 October and take part in editorial preparation.
Draft slides or a short recorded walkthrough are optional.
Make a submission
Accepting submissions till 18 Oct 2026, 11:50 PM
Swetha A When Good Agents Disagreed Until We Built Shared UnderstandingAbstract Multi-agent systems are often built around orchestration: an orchestrator routes requests to specialist agents, coordinates their work, and brings their outputs together. But in production, we encountered a more fundamental problem: every agent could be doing its job correctly, while the system as a whole was still wrong. more
|
|
Swetha A Understanding Your Agents From Traces to TrustAbstract While building and operating LLM-powered systems in production, one lesson keeps repeating itself which is that the hardest failures are often invisible. Unlike traditional software, agentic systems can fail in countless ways while every dashboard remains green. An agent may misunderstand user intent, choose the wrong tool, retrieve stale information, drift from its objective, or silentl… more
|
Manas Chaturvedi From AI Agents to AI Platform: Lessons From Building an In-House Multi-Agent PlatformFrom AI Agents to AI Platform: Lessons From Building an In-House Multi-Agent Platform more
|
|
Ar
Akash raj Modernising legacy systems with AI: from the missing "why" to tests that prove nothing brokeUnderstanding legacy code with an LLM is only step one. This session walks through the full pipeline we run in production: ingest, build and validate a knowledge base with the client’s experts, generate BRDs and use cases, turn them into test cases, modernise with a coding agent, and re-run the same tests to prove behaviour has not changed. more
|
|
UA
Uzair Ali Engineering Trust in a Financial Agent: The Harness Behind the ChatEngineering Trust in a Financial Agent: The Harness Behind the Chat more
|
Mahita D The Hard Part Isn't Building an Agent. It's Changing One That's Already in Production.What happens when the underlying API that your agentic system relies on changes unexpectedly? This talk is a production case study of how I handled an upstream API change in two weeks for a system already running in production, without regressions. more
|
|
UK
Utkarsh Kanwat Keeping an Autonomous Coding Agent Reliable on Long Tasks: Lessons from ProductionKeeping an Autonomous Coding Agent Reliable on Long Tasks: Lessons from Production. What actually breaks when an AI agent runs long, multi-step tasks for enterprise teams, and the checks that raised our long-task success rate from 74% to 86%. more
|
|
HC
Harsh Chaudhari One Chat Box, Three Execution Paths: RAG, SQL and APIs in Enterprise AIHow to connect enterprise AI to documents, business data and existing software without sacrificing correctness, control or reliability. more
|