{"type":"post","id":"mercury-agent-1-4-1-adds-learned-work-39078b","slug":"mercury-agent-1-4-1-adds-learned-work-39078b","title":"Mercury Agent 1.4.1 adds learned work preferences and self-saved skills","description":"Mercury Agent 1.4.1 adds an inspectable, evidence-backed store for learned working preferences and lets the agent turn successfully completed multi-step procedures into reusable skills.","retrieval_nugget":"Mercury Agent 1.4.1 adds an inspectable, evidence-backed store for learned working preferences and lets the agent turn successfully completed multi-step procedures into reusable skills. For builders, the important shift is not merely personalization: the release makes some learned behavior visible, reversible, bounded, and available across Mercury’s interfaces.","published_at":"2026-10-28","updated_at":"2026-10-28","record_date":"2026-10-28","date_kind":"published_at","topics":["evals","context-engineering"],"entities":["Cosmicstack Labs","Mercury Agent","Brave Search"],"related_patterns":["skills-become-portable-capability-layer","company-memory-needs-write-loops"],"novelty_label":"new_fact","what_changed":"Mercury Agent 1.4.1 adds learned work preferences, self-saved skills, and renewed search—new capabilities beyond 1.4.0’s plugin integrations.","prior_refs":["memory:b13fc8d8-aae6-8940-ad96-2d11246e887c","memory:0521b0ba-206c-8059-a75f-4b211b8551da"],"source_url":"https://github.com/cosmicstack-labs/mercury-agent/releases/tag/v1.4.1","source_urls":["https://github.com/cosmicstack-labs/mercury-agent/releases/tag/v1.4.1"],"schema_version":"newruntime-agent-readable-v0.2","stable_id":"post:mercury-agent-1-4-1-adds-learned-work-39078b","status":"published","visuals":[],"editor":{"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]},"routes":{"html":"https://newruntime.com/posts/mercury-agent-1-4-1-adds-learned-work-39078b/","markdown":"https://newruntime.com/posts/mercury-agent-1-4-1-adds-learned-work-39078b.md","json":"https://newruntime.com/posts/mercury-agent-1-4-1-adds-learned-work-39078b.json"},"next_reads":[{"type":"topic","path":"/topics/evals/","url":"https://newruntime.com/topics/evals/","title":"Evals","reason":"Explore the evals topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/evals.md","json_url":"https://newruntime.com/topics/evals.json"},{"type":"topic","path":"/topics/context-engineering/","url":"https://newruntime.com/topics/context-engineering/","title":"Context Engineering","reason":"Explore the context-engineering topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/context-engineering.md","json_url":"https://newruntime.com/topics/context-engineering.json"},{"type":"collection","path":"/posts/","url":"https://newruntime.com/posts/","title":"Field Notes","reason":"Open the latest editorial analysis.","media_type":"text/html","json_url":"https://newruntime.com/posts.json"},{"type":"collection","path":"/source-ledger.json","url":"https://newruntime.com/source-ledger.json","title":"Source Ledger","reason":"Inspect the public source evidence graph.","media_type":"application/json"}]}