Join our community to explore agentic AI, data science & cloud tech through tutorials, challenges & expert insights. Build skills, learn & grow with us.
Global
- Tweets 84,509
- Following 34,468
- Followers 121,794
- Likes 9,296
Starting next week, builders of every background will be putting IBM Bob to work as they design and deploy real solutions.
Are you ready to build with them?
Check out the challenge themes and get started: ibm.co/6015ETxgx
3
5
22
4,657
Choosing the right local LLM tool can be tough.
@cedricclyburn shares his take with a tier list to make the decision a little easier.
How would you rank them? Let us know below.
3
1
15
16,743
Turn one BRD into a multi-agent solution with five AI agents, Python tools, and a knowledge base.
Follow Ahmed Azraq and Allen Chan as they use the Launch Bob feature in watsonx Orchestrate to build, test, evaluate, and deploy the solution: ibm.co/6015ETZQf
1
1
9
1,675
Same coding agent. Completely different outcomes.
Context can be the difference between a rough response and production-ready software.
@TechCowgirlBri explains why: ibm.co/6013ETVBh
2
2
14
1,620
Consider this your printed reminder:
💻 IBM TechXchange 2026
🗓️ October 26–29
📍 Atlanta, GA
See you there. 👀
7
5
25
3,742
Coding agents can turn a vague idea into working software fast.
But what happens when no one has defined what “correct” means?
Markus Eisele explores how much specification agentic development actually needs: ibm.co/6016ErSVi
5
17
2,470
Build the practical skills to solve problems across real codebases.
Practice coding, debugging and application maintenance with IBM Bob through free, interactive #IBMSkillsBuild labs.
Start building: ibm.co/6018EriXy
3
19
2,472
Give @IBM Bob a structured markdown file and clear instructions, and it can follow a repeatable workflow tailored to your needs.
In this tutorial, @alexsotob shows how to create your first skill, refine it over time and adapt it to your own use cases: ibm.co/6017ErH0R
2
7
19
3,233
IBM Dev Day: Bob in Action kicks off next week.
Free virtual event + a hackathon with $2,000 and tickets to TechXchange up for grabs.
Secure your spot ➡️ ibm.co/6016ERQGp
1
8
2,008
One click. 🖱️
That’s all it takes to start building AI agents in watsonx Orchestrate using Bob.
Watch Ahmed Azraq go from BRD to five specialized agents in this tutorial.
2
7
19
3,287
CPU vs. GPU: Which handles large-scale analytics better?
Watch @gethackteam and William Hill put GPU-accelerated Presto to work on a 179-million-row dataset, then learn how to configure the environment yourself: ibm.co/6015ER5QW
2
21
2,552
Agentic Cinema: The Blockbuster Hackathon is open. 🎬
Join us to build AI-driven solutions with IBM Bob designed to help streamline enterprise workflows and enhance decision-making.
Register and start building.
→ ibm.co/6019ERJAH
1
2
14
1,888
Native QSYS connectivity, built-in @IBM i skills and agentic workflows, all within your VS Code-family workspace.
Premium Package for i brings IBM Bob directly to your IBM i system. No export loops. No friction.
Explore what’s possible: ibm.co/6019Eu4K9
3
6
26
3,566
4️⃣ Autonomy requires proof. Bob runs the generated tests, flags security risks, and highlights clean-up items.
Once everything passes, Bob commits the changes and opens a pull request. You do the final review and ship.
1
3
295
3️⃣ Implementation is where AI autonomy peaks.
Bob builds a to-do list, writes code, and writes tests (like Playwright).
You set the risk level: run in "yolo mode" with auto-approvals, or require manual sign-off for every file write.
1
1
61
2️⃣ Make sure your specs create guardrails, but don't go into so much detail that you're just writing code in natural language.
Use the "grill me" skill in Bob to get targeted questions that help you clarify design decisions, catch model size issues, and finalize a solid spec.
1
1
126
1️⃣ Cut out the guesswork. Have Bob pull feature requests directly from GitHub issues via MCP and drop them into a clean requirements file.
From there, Bob drafts an implementation plan.
You review, refine, and set clear expectations before a single line of code is written.
1
1
223
Don't just hope you didn't miss an important infrastructure change buried in hundreds of lines of output.
Learn how to review your Terraform plan with Terraform MCP and LLMs in this tutorial from Ash Minhas: ibm.co/6011EOinZ
2
1
1,107
Messy PDFs don't have to stay messy.
Use IBM Bob + Docling for IBM watsonx to extract structured data from documents and build a purchase order processing app with spec-driven development.
Start building → developer.ibm.com/tutorials/…
6
1,315
AI agents are easy to demo. Production is a different problem.
Enter CUGA. 🦉
An open-source agent harness that lets you focus on building instead of plumbing: ibm.co/6011EO64S
5
6
33
8,567
Give AI agents access to the tools they need to take action.⚡️
@alexsotob shows how Java, Quarkus, and MCP can be used to extend IBM Bob with custom tools and integrations.
🎥: ibm.co/6045E3mrJ
3
1
10
959
Your models and agents can only reason over what they can understand.
Docling for IBM watsonx transforms PDFs, images, and more into structured, AI-ready data while preserving the context many extraction approaches lose.
Start for free → ibm.biz/~d3cefNA0k
1
3
10
1,132
Build AI agents and MCP tools in watsonx Orchestrate using IBM Bob. 🏗️
In this walkthrough, Ahmed Azraq shows how to build an MCP server with Bob, from designing to implementation.
🎥: ibm.co/6012E3z5m
6
5
47
7,804
Building with Terraform or Vault? 🏗️
Join @HashiCorp experts for live exam prep sessions designed to help you assess your knowledge, brush up on key concepts, and prepare for certification.
Sign up today → ibm.co/6045EMUo5
1
5
1,137
New to IBM Bob? This quickstart helps you get started with:
🧰 Environment setup
📂 Codebase exploration
🛠️ Feature development
🔄 Testing changes
2
5
9
1,635
Another IDE? There are already too many of those.
Nicholas Renotte gives an honest review of IBM Bob and what it actually feels like to build with it.👇
1
13
1,861
Writing the playbook is only part of the work. The real overhead is:
⚙️ handlers
👥 roles
📄 templates
🔄 conventions
📚 docs
@alexsotob shows how Bob can generate and organize that scaffolding automatically: ibm.biz/~t0WMP3FIA
1
7
903
Turn YouTube videos, podcasts, and conference talks into searchable knowledge.
@SonicDMG shows how to use Docling + OpenRAG to:
🎤 extract transcripts + timestamps
⚙️ build an AI-ready RAG pipeline
🔎 search exact moments from long-form videos
1
1
6
846
As context windows continue to grow, where does RAG still fit into modern AI workflows?
@MartinRTP explores how RAG and long-context models compare when building AI apps and agents, and why grounding, latency, and accuracy still matter in practice: ibm.biz/~kicuIECgi
7
729
So… why is everyone suddenly talking about Bob?
@if54uran shows how IBM Bob works alongside you across the full SDLC, from writing and reviewing to modernizing and deploying your code. ↓
2
8
25
4,286
Four days of hands‑on building with IBM experts.
Ready to dive in?
Register and start building → ibm.co/6017EKnhF
2
2
515
A lot of knowledge is locked in video, audio, and documents that agents can’t use.
Docling turns it into Markdown/JSON in <40 lines of code, built for RAG.
@TejasKumar_ shows how ↓
1
1
8
1,787
Chief Architect, Gabe Goodhart built a local AI coding assistant with Granite 4, Ollama, VS Code, and Continue.
He walks through the full workflow — including the architecture and how to run it locally: ibm.biz/BdpqfH
1
1
4
965
Interested in quantum computing?
With over 13 million downloads, Qiskit is the world's most popular open-source quantum computing stack for building and researching quantum algorithms. Dive deeper into Qiskit and our quantum ecosystem here: ibm.co/6010EHDuY
2
4
5
867
There’s a lot of noise around AI IDEs.
@if54uran walks through how IBM Bob works with real-world Java codebases, analyzing dependencies and supporting modernization at scale. ⬇️
1
2
9
1,161
Enterprise Java isn’t about typing faster. It’s about understanding the system first.
@myfear shares a technical perspective on how IBM Bob supports planning and controlled change in real Java codebases:ibm.co/601887E3q
8
3
10
1,857
ClickOps doesn’t scale.
How Python SDKs let teams build data pipelines as code—versioned, automated, and ready for AI agents.
0:00 Why click-ops break
0:27 Pipelines as code
1:36 Programmatic workflows
3:55 AI agents in production
6:05 Observability
piped.video/R43Q0nIXa1Q
4
699
Stanford’s Transparency Index just dropped: ibm.co/6019BlOqv
Granite didn’t just rank #1, it set the highest score ever.
3
12
1,678
Run an AI model on your phone, completely offline. 🤯
IBM’s Granite Nano models make it possible, find out how with Emma from the Granite team.👇
1
8
1,628
Introducing Granite 4.0 Nano, compact and open-source models built for AI at the edge.
Available in 350M and 1B, for building AI on laptops and mobile devices: ibm.co/6013Bzpt7
5
11
39
3,690
Part wonderland, part innovation hub.
The future was on full display at #IBMTechXchange. From Ferrari activations to a quantum chandelier, here's a peek into the ultimate tech playground.
2
7
1,144
Take a closer look at what buildpacks are, why they're advantageous, and how you can use them for your cloud-native Java applications: ibm.co/3FYSJuG
ALT Image contains: cargo ship
6
11
35
8,371
Congrats to the @CallforCode Round 4 winners and their #AI solutions powered by @IBMwatsonx. Learn about the top #developer teams including solutions from @Persistentsys and @MorganStanley tackling food waste: ibm.co/49IKTmT
#innovation #GenerativeAI
ALT Image contains: fruits and vegetables.
1
14
33
7,351
In this new tutorial, learn how to set up OpenSSL and how to configure it to use quantum-safe encryption algorithms. Explore more: ibm.co/40zKv5Y
#cUrL #quantum #OpenSSL
ALT Image contains: safe vault
16
32
5,244
Most #developers want to focus on the code and solving problems, but much of their team is busy in handling other tasks and documentation. This is where Backstage will become an important tool in their toolbox. To learn more, watch the video: ibm.co/3Myf9qi
ALT Image contains: Brad Bazemore
4
8
33
4,869
Thinking about deploying and scaling #AI? Consider #PyTorch an #OSS framework for scaling AI, here Suraj from Meta and Raghu, from IBM Research share more insights: ibm.co/3MjBfN8
ALT Image contains: from left Raghu Ganti and Suraj Subramanian
9
35
6,118