CUGA Policy Playground
🛡
19
Two live CUGA agents, with and without policies
Jim Laredo
laredoj
AI & ML interests
LLM as they pertain to automation
Recent Activity
liked a Space 1 day ago
ibm-research/cuga-policy-playground upvoted an article 1 day ago
Same Model, Different Harness: CUGA, Hermes, and Deep Agents — When to Pick CUGA? published an article 1 day ago
Same Model, Different Harness: CUGA, Hermes, and Deep Agents — When to Pick CUGA?Organizations
liked a
Space 1 day ago
upvoted an article 1 day ago
Article
Same Model, Different Harness: CUGA, Hermes, and Deep Agents — When to Pick CUGA?
ibm-research
• • 33 published an article 1 day ago
Article
Same Model, Different Harness: CUGA, Hermes, and Deep Agents — When to Pick CUGA?
ibm-research
• • 33 upvoted an article 15 days ago
Article
ALTK-Evolve: How learned memory tops the τ²-bench leaderboard on customer service tasks without a frontier model
ibm-research
• • 27 upvoted an article about 2 months ago
Article
Your Agent Aced the Task. Will It Do It Again?
ibm-research
• • 123 upvoted 2
articles 3 months ago
Article
How Much Memory Does Your Agent Actually Need?
ibm-research
• • 83 Article
Thinking of ACE? We Can Do It with Fewer Tokens
ibm-research
• • 33 upvoted an article 4 months ago
Article
Model Routing Is Simple. Until It Isn’t.
ibm-research
• • 95 liked a
Space 4 months ago
upvoted an article 4 months ago
Article
Build real agentic apps using CUGA: two dozen working examples on a lightweight harness
ibm-research
• • 40 liked 4
datasets 5 months ago
upvoted a paper 5 months ago
upvoted an article 5 months ago
Article
Beyond LLMs: Why Scalable Enterprise AI Adoption Depends on Agent Logic
ibm-research
• • 92 upvoted 2
articles 7 months ago
Article
Inside VAKRA: Reasoning, Tool Use, and Failure Modes of Agents
ibm-research
• • 30 Article
ALTK‑Evolve: On‑the‑Job Learning for AI Agents
ibm-research
• • 32 liked a
Space 7 months ago
liked a
dataset 7 months ago