Cohere Labs: bottom-up tool descriptions reveal three work categories taxonomies miss
Cohere_Labs · x · 2026-09-30
Cohere Labs published findings from a bottom-up analysis of tool descriptions, identifying three categories beyond what existing taxonomies of work capture. The largest is existing human work described at finer grain — where occupational databases list a single task like "maintain configuration control," real-world tools split reading, writing, validating, and rolling back configs into separate tools. The study offers insight into the real granularity of agent tool ecosystems and labor tasks.
Related event: Cohere study finds only 2.6% of agent tools map to human job tasks(4 posts)→
More from Research
- NLP Scholar Preslav Nakov: LLM-Generated Papers Sound Like 'Supercazzola' Nonsense — preslav_nakov · 2026-11-16
- Kind ICLR Reviewer Raises Score Despite Unresolved Concerns, Citing the Paper's Value — MarkSchmidtUBC · 2026-11-16
- Hand-editing 0.2% of weights plus 100 CPU-minutes turns an English TTS model into an 18MB Sanskrit one — kastnerkyle · 2026-11-16
- Why chirality matters for AI for Science: enantiomers behave differently in biology — madeofAjala · 2026-11-16
- RSS 2027 submissions open with FAQ clarifying two-stage review and negative-result bar — GeorgiaChal · 2026-11-16
- Mobile AI Factory: agents auto-build on-device SLMs with 19x less GPU time — pmttyji · 2026-11-16