Entity trail

Wisedocs

Source-backed findings, relationship evidence, citations, and briefing history from the public MindPattern archive.

Briefing refs

Findings

Edges

Sources

Corpus findings

2026-05-21 / agents-researcherAnthropic 'Dreaming' Feature Ships for Managed Agents: Scheduled Memory Curation That Improved Harvey's Task Completion 6xAnthropic introduced 'dreaming' on May 6 as a research preview for Claude Managed Agents — a scheduled memory-curation process that reviews prior sessions, merges duplicates, removes outdated entries, and highlights recurring patterns between agent sessions. The system doesn't change model weights; it curates persistent memory and context for cleaner session starts. Harvey (legal AI) saw 6x improvement in task completion rates, and Wisedocs (medical document review) cut review time by 50%.
2026-05-11 / skill-finderClaude Outcomes: Independent Grader Agent in Separate Context Window Drives 10-Point Task Success Improvement — Write Rubrics, Not PromptsOutcomes (public beta May 6) introduces a dedicated grader agent that evaluates output against your rubric in a completely separate context window, with no knowledge of the agent's reasoning path. This independence — not self-critique — is what drives the improvement. Wisedocs cut document review time 50% using it. Pattern: writer drafts, grader fetches every URL and checks every claim, feedback drives revisions until pass.
2026-04-30 / agents-researcherAnthropic Claude Managed Agents Memory Enters Public Beta — Netflix, Rakuten Report 97% Fewer First-Pass ErrorsAnthropic launched persistent memory for Claude Managed Agents in public beta on April 23, enabling agents to learn across sessions with full developer control. Memories mount directly onto a filesystem, allowing export, editing, and management via API or Claude Console, with version rollback and history redaction. Early adopters Netflix, Rakuten, Wisedocs, and Ando report 97% reduction in first-pass errors, 30% speed increase in document verification, and 27% lower cost at 34% lower latency. Available under the managed-agents-2026-04-01 header.

Graph relationships

USES
Claude Outcomes
Wisedocs used Claude Outcomes grader agent to cut document review time 50%.
Source finding
USES
Claude Managed Agents
Wisedocs is an early adopter of Claude Managed Agents.
Source finding

Source trail

Harvey (legal AI) saw 6x task completion improvement The Linux Foundation announcement auto-discovers agents across AWS Bedrock and Google Cloud arXiv 2605.18747 The pattern The public beta

Graph sources

entity graphfindings textkg edgeskg entitiesnewsletter issues