This Is Actually Broken for My Life

Why It Matters

Automating personal CRM creation eliminates manual data entry and equips professionals with instant, context‑rich insights for every interaction, driving efficiency and more informed decision‑making.

Key Takeaways

• Hourly bot sync pulls emails, calendar into local CRM.
• Meeting prep channel aggregates past interactions for daily briefings.
• AI notetaker transcribes meetings, feeding data into personal CRM.
• Prompt includes smart filtering to exclude newsletters, bots, outreach.
• Personal CRM runs continuously, providing real-time relationship context.

Summary

The video showcases a hands‑on demonstration of building a personal Customer Relationship Management (CRM) system using OpenClaw. By configuring an hourly bot, the creator automatically downloads emails and calendar entries, extracts relevant contacts, and stores them in a locally hosted CRM, ensuring the database stays up‑to‑date without manual effort.

Key components include a meeting‑prep channel that scans the day’s agenda, pulls historical conversation notes, and surfaces takeaways for each participant. An AI‑powered notetaker, Fathom, joins every call, transcribes the discussion, and feeds the transcript back into the CRM, creating a continuously enriched relationship profile. Crucially, the prompt incorporates smart filtering to weed out newsletters, bots, and cold‑outreach messages, keeping the contact list signal‑rich.

The creator emphasizes, “This is definitely the number one use case for OpenClaw,” and stresses, “Filter. This is critical. Most contacts are noise.” By sharing the exact prompt in the description, the video provides a reproducible template for viewers to replicate the workflow on their own machines.

Automating contact capture and meeting preparation transforms personal productivity, allowing professionals to focus on strategic conversations rather than data entry. The approach demonstrates how AI‑driven automation can replace traditional, fragmented CRM tools with a seamless, real‑time personal knowledge base, potentially reshaping relationship management across industries.

Original Description

Prompt:

Build me a personal CRM system that automatically tracks everyone I interact with, with smart filtering so it only adds real people — not newsletters, bots, or cold outreach.

Data sources:

- Connect to my email (Gmail API or IMAP) and scan the last 60 days of messages.

- Connect to my calendar (Google Calendar API) and scan the last 60 days of events.

- Run this ingestion on a daily cron schedule.

Contact extraction from email:

- Extract sender/recipient email addresses and names from messages.

- Estimate the number of exchanges (back-and-forth threads, not just raw message count): Math.min(Math.floor(totalMessages / 2), threadCount).

- Collect sample subject lines and message snippets for classification.

Contact extraction from calendar:

- Only include meetings with 1-10 attendees (skip large all-hands).

- Only include meetings at least 15 minutes long (skip quick check-ins that are really just reminders).

- Extract attendee names, emails, and the meeting title.

Filtering — this is critical. Most contacts from email are noise. Use a two-stage filter:

Stage 1 — Hard filters (always reject):

- My own email addresses and domains.

- Emails from family or personal contacts I've explicitly excluded (configurable list).

- Contacts already in the CRM or previously rejected.

- Generic role-based inboxes: info@, team@, partnerships@, collabs@, noreply@.

- Marketing/transactional domains matching patterns like: noreply@, tx., cx., mail., email. prefixes.

Stage 2 — AI classification (use a fast, cheap LLM like Gemini Flash or Haiku):

Send the candidate's name, email, exchange count, and sample subject lines/snippets to an LLM with these rules:

- REJECT clearly automated or notification-only senders.

- REJECT if all sample subjects look like newsletters, digests, or automated reports ("weekly roundup", "monthly update", "AI news").

- REJECT cold outreach with low engagement — if exchanges are low relative to total emails, it's one-way pitching.

- REJECT if snippets show repetitive promotional content (product launches, feature announcements, affiliate reports).

- APPROVE only if it looks like a real person with genuine two-way interaction or a meaningful business relationship.

- Higher confidence for real back-and-forth conversations with varied, substantive topics.

Contact scoring (used for ranking, not filtering):

- Base score: 50

- +5 per email exchange (max +20)

- +3 per meeting (max +15)

- +15 if their title matches preferred titles (CEO, Founder, VP, Head of, Engineer, Partner, etc.)

- +10 if they appeared in small meetings (≤3 attendees)

- +10 if last interaction was within 7 days, +5 if within 30 days

- +25 bonus if the person appears in both email AND calendar (stronger signal)

- +10 if they have a recognizable role, +5 if they have a company

For each approved contact, store:

- Name, email(s), company, role/context

- Interaction timeline with dates

- Last-touch timestamp (auto-updated)

- Contact score

- Tags or categories

Learning system:

- Maintain a learning.json config with:

- skip_domains: domains to always reject (populated over time from rejections)

- prefer_titles: titles that boost contact scores

- skip_keywords: subject-line keywords that indicate spam

- min_exchanges: minimum exchange threshold (default 1)

- max_days_between: max days since last interaction (default 60)

- max_attendees: meeting size cap (default 10)

- min_duration_minutes: meeting length minimum (default 15)

- When I reject a contact, learn from it — add their domain to skip_domains if appropriate.

Deduplication:

- When a new contact is found, check by email, then by name+company combination.

- Merge records rather than creating duplicates.

Semantic retrieval:

- Generate embeddings for each contact record.

- Let me ask natural-language questions like:

- "Who did I meet from [company] last month?"

- "When did I last talk to [name]?"

- "Show contacts I haven't spoken to in 30+ days."

Storage: SQLite with WAL mode and foreign keys enabled.

Notifications: After each ingestion run, send a summary of new contacts, merges, rejections, and any issues.

Follow me ► x.com/matthewberman

Instagram ► https://www.instagram.com/matthewberman_ai

Media/Sponsorship Inquiries ► https://bit.ly/44TC45V