Join our community to explore agentic AI, data science & cloud tech through tutorials, challenges & expert insights. Build skills, learn & grow with us.
Global
Joined September 2008
- Tweets84.5K
- Following34.4K
- Followers122K
- Likes9.3K
How much does the agent harness matter when the model stays the same?
We tested three harnesses on the same tasks. Here’s what changed, and a demo you can try yourself.
On 90 AppWorld tasks with GLM-5.3-flash, completion ranged from 30% to 81% across CUGA, Hermes, and Deep Agents.
See how each harness was configured, then try changing what an agent can pay using a runtime policy in CUGA’s Policy Playground.
→ huggingface.co/blog/ibm-rese…
3
324
IBM Developer retweeted
Recorded at #IBMTechXchange 2026 in Atlanta, hear @KateHolterhoff chat with @myfear, AI Developer Strategist at @IBM, about the keynote announcements around Bob 2.0, including Bob Desktop, Bob Bazaar, and Bob DevSecOps. Full conversation on the MonkCast redmonk.com/videos/markus-ei…
IBM Developer retweeted
Welcome back to Tech Term of the Week! 🥳
This week's term → agentic workflows - /əˈdʒɛn.tɪk ˈwɝːk.floʊz/
Definition → AI-driven processes where autonomous AI agents make decisions, take actions and coordinate tasks with minimal human intervention.
Why it matters → this allows AI systems to adapt and complete tasks even when conditions change, reducing the need for human intervention on routine work while also generating higher-quality outputs that can help train future AI models more effectively.
Use IBM Bob in compatible editors like IntelliJ and Zed.
ACP (Agent Client Protocol) defines how Bob and the client exchange prompts, tool-call updates and permission requests.
Explore ACP: ibm.co/6015EV7cb
Bob docs: ibm.co/6016EV7cj
4
1,094
IBM Developer retweeted
That’s a wrap on #Current26 San Francisco! 💙
Here’s to the people, the energy, and the moments that made this week unforgettable.
IBM Developer retweeted
Spend less time troubleshooting pipeline breaks and painful cluster migrations and more time building your Streamhouse.
Check out the new updates that make Confluent Cloud and Confluent Cloud simpler to build on, simpler to run and more cost-effective: ibm.co/6017EV0CH
The unofficial #IBMTechXchange numbers are in.
Which stat belongs in your end-of-week report?
5
937
IBM Developer retweeted
Today, in collaboration with @IBMResearch, we are launching ScarfBench (Self-Contained Application Refactoring Benchmark), an open benchmark designed to test whether coding agents can successfully migrate enterprise Java apps across frameworks like Jakarta EE, Quarkus, and Spring while maintaining the app’s expected behavior.
Moving between frameworks takes coordinated changes across dependency injection, persistence, build systems, and deployment infrastructure. An agent can easily generate a migration that looks fine or compiles, only for the app to fail when deployed. ScarfBench puts that to the test.
ScarfBench evaluates each model with its harness over 204 migration tasks. Gemini 4 Argon with Antigravity scores 75.2%, followed by Claude Opus 5.5 with Claude Code at 70.5%, and Claude Opus 5 with Claude Code at 69.8%.
Two-word horror stories. 🎃
Which one scares you most?
12%Code bug
31%Production Friday
31%AI slop
27%Production broke
26 votes • Final results 1
1,336
You don’t have to be in Atlanta to be part of IBM TechXchange.
Catch the ideas and announcements as they happen, then revisit sessions on demand after the event: ibm.co/6017EViMN
Bring the questions that will shape your next build.
At @IBM TechXchange, get into implementation details, discuss tradeoffs with experts and explore approaches that fit your project’s requirements.
Plan your experience: ibm.co/6010EVklA
What will you bring back from IBM TechXchange?
For IBM Champion Darren Surch, it was sharper technical skills and fresh ideas from conversations with people working on AI, quantum computing and IBM Z.
Those conversations led to collaborations that helped shape his company.
His advice on what to bring?
“Bring your laptop, your curiosity, and your openness for fun. You'll need all three.”
Explore the sessions and labs at IBM TechXchange 2026: ibm.com/events/techxchange
3
319
More Bobcoins to build, debug, and iterate with IBM Bob, at no extra cost.
Free trial: 1.25× more Bobcoins
Pro: 1.25× more
Pro Plus: 1.125× more
Ultra: 2× more
Explore the update: ibm.co/6016Epa9E
🔐 Self-hosted Bob includes a Keycloak-based identity service that integrates with LDAP or Active Directory for corporate sign-in, access management, and user provisioning.
1
3
265
ICYMI: Self-hosted deployment for IBM Bob is officially GA.
Run the Bob backend on Red Hat OpenShift, on premises or in your own cloud account, and connect through Bob IDE or Bob Shell.
Here’s what the setup involves: 🧵
1
13
4,686
Once deployed, Bob IDE and Bob Shell connect to your organization’s hosted backend.
Teams can use these clients with the backend running on infrastructure their organization manages.
1
1
143