Observed Signal · Aug 31, 2026 · Other · Source: Lennys Newsletter · Impact: 2/5 · Sentiment: Positive
PM Uses Claude for 70–80% of Workday
Product manager Daniel Blum (Melio) built a self-improving AI workflow that performs roughly 70–80% of his daily work tasks. Using Claude and a coordination layer (Cowork) to manage his Notion board, scan Slack and email, and learn from edits, the system produces daily briefs, asks targeted clarifying questions, and runs weekly improvement loops that compare drafts with final outputs. He also created a 15-minute onboarding flow so colleagues can personalize the system quickly. The piece emphasizes architecture, ongoing context refreshes, feedback telemetry, and persistence limitations (the system cannot yet autonomously run in the cloud while devices are off).
Practical case study of an enterprise product manager using LLMs and agent orchestration to automate a large portion of knowledge-work; relevant to MarTech/enterprise AI adoption but not platform-level policy or major product launches.
Track Optimizely Signals & Market Shifts in Real-Time
Polaris7 autonomous intelligence agents track regulatory filings, primary sources, executive changes, and deal flow 24/7. Create your free Explorer workspace to monitor these entities.
Key Takeaways & Evidence Grounding
- Daniel Blum is a product manager at Melio.
- Blum built a self-improving AI system that now handles an estimated 70% to 80% of his workday.
- The system uses Claude and Cowork to manage his Notion board, scan Slack and email, generate morning briefs, and learn from his edits.
- He created a 15-minute onboarding flow that personalizes the AI system for other Melio employees.
- The system includes weekly 'self-improvement loops' and feedback telemetry that compare drafts to final outputs and log friction points for updates.
Connected Companies & Entities
1 Entity mapped“**Optimizely**—Your AI agent orchestration platform for marketing and digital teams (sponsor line: "Brought to you by: Optimizely — Your AI ...”
Ontology Mapping & Concepts
Related Market Signals & Shifts
Recent verified developments and strategic activity across this market segment.
PM builds self-improving Claude productivity system
Daniel Blum, a product manager at Melio, describes a year-long project building a Claude- and Cowork-based productivity system that automates his Notion board, processes Slack and email, and runs weekly self-improvement loops without prompting. He created a 'Workstation' onboarding plugin that configures a personalized Claude setup for any Melio employee in about 15 minutes, and uses features such as a morning brief, an 'Improve' skill to filter tips, and automatic jargon capture. Blum reports running roughly 70–80% of his workday through Cowork/Claude while noting remaining capability gaps that prevent fully replacing workflows.
VP Product Uses Claude to Avoid 'Slop'
This case study profiles Matt Wensing, VP of Product and Design at Customer.io, and how he uses the Claude family of AI assistants to produce leadership-grade outputs without generating low-quality drafts (“slop”). Wensing favors long, iterative Claude sessions with layered context, voice-mode interactions, and a disciplined reveal of domain specifics to avoid generic or premature suggestions. Customer.io pairs Claude desktop work with three internal tools: a Snowflake-connected analysis bot, a Slack channel scanner that surfaces threads needing product input, and “Chiefys,” a company-docs bot that checks new work against official strategy. The post explains practical prompts and workflows (reformatting transcripts to strategy themes, iterating slides then generating talk tracks) and highlights governance: human review of non-deterministic results and data-team oversight for analytics. The article includes tool recommendations and an AI toolstack list used by the author.
Build a Self-Improving AI PM OS with Claude Code
Aakash Gupta’s May 14, 2026 podcast episode and newsletter explains how product managers can build a self-improving AI-powered PM operating system using Anthropic’s Claude ecosystem—Chat, Cowork, Claude Code and Dispatch. Guest Pawel Huryn demonstrates practical workflows: when to use each surface, how to connect real files and tools via MCP connectors, and how to design persistent, iterating knowledge systems (CLAUDE.md router pattern, skills marketplace, hooks, subagents). The piece contrasts personal automation (Claude Code) with production automation (n8n), outlines a 24/7 PM workflow across devices, and gives actionable patterns (three-line self-improving prompt) to make agentic systems learn from data and improve over time.
Track Real-Time Market Signals & Shifts
Set up custom watchlists to receive automated, evidence-grounded executive digests whenever material signals or shifts occur across your tracked landscape.