← All posts
Event

Docling at IBM TechXchange 2026

Meet the Docling team at IBM TechXchange

In two weeks the Docling team heads to Atlanta for IBM TechXchange 2026 (October 26–29). We're bringing seven sessions: four hands-on labs and three talks, with partners from AWS, NVIDIA, ABBYY and Confluent.

The labs are where you build something yourself: bring your laptop and leave with a working document pipeline. Between sessions, come find us. We're happy to talk about Docling, your use case, or how to get involved in the project.

Rooms and times below come from the session catalog. Check it for last-minute changes and to add sessions to your agenda. All times are EDT.

Schedule

Monday, October 26

Agentic RAG with OpenRAG on IBM watsonx.data & External Agents: From Docling Ingestion to MCP

12:15 PM – 1:45 PM · Hands-on lab (pre-conference day) · LAB-3834 · Lab 05, Labs & Certifications, Sandbox

Build an agentic RAG pipeline with OpenRAG on IBM watsonx.data. Docling parses the documents into an OpenSearch knowledge base, and agents query it over MCP from watsonx Orchestrate and the Hermes Agent framework. Run by the watsonx.data team.

Speakers: Thomas Schäck (IBM), Charna Parkey (IBM)

Tuesday, October 27

Enriching the Knowledge Layer for Enterprise Agents with IBM and NVIDIA

10:30 AM – 10:50 AM · Tech talk · TLK-4011 · Tech Talk 02 | 551, AI Applications, Sandbox

A case study on turning complex enterprise documents into agent-ready knowledge with Docling, DocLang and NVIDIA NeMo Retriever, keeping layout, metadata and provenance intact all the way to RAG and agents.

Speaker: Ryan Chesler (NVIDIA)

Build a RAG Pipeline and Document Agent with IBM Docling, Amazon Bedrock, and Amazon S3 Vectors

2:45 PM – 4:15 PM · Hands-on lab · LAB-2944 · Lab 06, Labs & Certifications, Sandbox

A citation-aware RAG pipeline on IBM and AWS. Docling parses the documents, and Amazon Bedrock and S3 Vectors handle embeddings, retrieval and generation. Then a Strands agent navigates the documents by their outline and uses the RAG pipeline as one of its tools.

Speaker: Michele Dolfi (IBM)

Wednesday, October 28

From Bucket to RAG: Event-Driven Docling for watsonx and Confluent

10:30 AM – 12:00 PM · Hands-on lab · LAB-2775 · Lab 06, Labs & Certifications, Sandbox

Drop a file into a bucket and watch it flow. Docling for IBM watsonx writes layout-aware chunks straight to Kafka, and Apache Flink on Confluent checks quality, removes duplicates, redacts PII, embeds with watsonx.ai and indexes into OpenSearch. No scheduler, no glue scripts.

Speakers: Michele Dolfi (IBM), Peter Staar (IBM)

Docling for IBM watsonx: Convert, Extract, and Build Your Own Document-Powered App

12:45 PM – 2:15 PM · Hands-on lab · LAB-1499 · Lab 03, Labs & Certifications, Sandbox

Convert documents in the Workbench, then call the same service from Python. After that, pick a track: a RAG notebook with Docling chunking, Docling in agentic frameworks, or an end-to-end app built with IBM Bob.

Speakers: Michele Dolfi (IBM), Peter Staar (IBM)

Docling for IBM watsonx: Building Agentic Document Workflows at Enterprise Speed

2:45 PM – 3:30 PM · Breakout · TEC-2232 · B202, Level 2, Building B

Context engineering for agents: why plain PDF-to-text loses the headings, tables and reading order that agents need, and how Docling for IBM watsonx delivers structured, agent-ready output as a managed service.

Speakers: Michele Dolfi (IBM), Eduardo Monich Fronza (AWS), Mikhail Shapirov (AWS)

The Missing Layer in Enterprise AI: Building Document AI Pipelines with DocLang

2:45 PM – 3:30 PM · Breakout · TEC-2541 · B208, Level 2, Building B

Why documents break AI pipelines, and how DocLang, the open AI-native document format created by ABBYY, IBM, NVIDIA and Red Hat, makes them reliable. With Docling and ABBYY FineReader Engine examples and benchmarks.

Speakers: Peter Staar (IBM), Max Vermeir (ABBYY)

Heads-up: TEC-2232 and TEC-2541 run at the same time, in neighbouring rooms in Building B.

Lab material

All the code used in the labs is available in IBM/txc2026-docling, so you can follow along even if you can't make it to Atlanta.

Resources

See you in Atlanta!