Signal SentrySearchUpdated Nov 20, 05:30 UTCAM Drop
Agents · industry

Agents in Knowledge work

Agent deployments and launches in Knowledge work, from the Drops.

From the Drops

AgentsKnowledge workTestingHuman in loop: unclear

Preprint: a 4B agent trained on 4k real-file tasks beat a 235B model on GDPval

Researchers report that Agent-R^2, built from real job seeds and web-sourced files, trained a 4B model that scored 51.0% on GDPval versus 48.0% for Qwen3-235B-A22B-Thinking-2507, and 14.8% vs 13.8% on OfficeQA.

Why it matters: For office-task agents, training data grounded in real files and deliverable rubrics may matter as much as model size. Test a small tuned model on your own tasks before paying for a large one.

From Drop #088 · Sun, Nov 15, 2026 · Evening
AgentsKnowledge workLiveHuman in loop: unclear

Perplexity launches always-on Teammates agents for $200-a-month Max users

The Verge reports Perplexity's Teammates run around the clock on assigned jobs, draw on existing projects, skills and memory, and can be reached in Slack. It follows similar work agents from OpenAI and Anthropic.

Why it matters: Background work agents now come from several vendors. Before a pilot, check what each one may do inside Slack and who answers for its actions.

From Drop #069 · Fri, Nov 6, 2026 · Morning