Building a Deal Flow Triage Agent for VCs with OpenClaw

What Does a Deal Flow Triage Agent Actually Do?

A deal flow triage agent monitors your inbox, extracts pitch deck data, scores each opportunity against your investment thesis criteria, and pushes ranked summaries to Slack. It turns a 6-hour daily screening grind into a 15-minute review of pre-scored deals.

The problem it solves is volume. According to PitchBook’s 2025 US VC Activity Report, active venture firms receive between 5,000 and 10,000 inbound pitches per year. DocSend’s 2025 Fundraising Research found that the average VC spends just 2 minutes and 24 seconds on a first-pass deck review. That’s not analysis — that’s pattern matching under duress. Most firms rely on associates to handle initial screening, but even a sharp associate can only review 30-40 decks per day before quality drops.

We’ve built this exact agent for VC clients at beeeowl. Here’s the full architecture, configuration, and deployment walkthrough.

How Is the Agent Architecture Structured?

The agent runs five sequential steps for every inbound pitch: email monitoring, attachment extraction, data enrichment, thesis scoring, and alert delivery. Each step is an OpenClaw skill connected through a channel.

Here’s the high-level flow:

Inbound Email (Gmail) → Attachment Extraction → Data Enrichment (Crunchbase/PitchBook) → Thesis Scoring → Slack Alert

The agent runs on a Mac Mini deployed in your office — or a MacBook Air if your partners travel. All processing happens locally. No pitch deck data, founder details, or scoring output leaves your network.

OpenClaw’s skill-based architecture makes this modular. Each step is a separate skill you can modify independently. If you switch from Gmail to Outlook, you swap one skill. If you add a new data source like Harmonic or Affinity, you add one skill. Nothing else changes.

How Do You Configure the Investment Thesis?

The thesis configuration is the core of the scoring engine. It defines what you’re looking for — sector, stage, revenue range, geography, team characteristics — and how much each criterion matters.

Here’s an example thesis config for a Series A-focused enterprise SaaS fund:

thesis:
  name: "Enterprise SaaS Series A"
  version: "2.1"

  criteria:
    sector:
      targets:
        - enterprise-saas
        - developer-tools
        - data-infrastructure
        - cybersecurity
      weight: 0.25
      floor: 0.3

    stage:
      targets:
        - series-a
        - series-a-extension
      preferred_raise: { min: 8000000, max: 25000000 }
      weight: 0.20
      floor: 0.5

    revenue:
      arr_minimum: 1500000
      arr_preferred: { min: 3000000, max: 15000000 }
      growth_rate_minimum: 0.40
      net_retention_preferred: 1.10
      weight: 0.25
      floor: 0.4

    geography:
      targets:
        - united-states
        - canada
        - united-kingdom
      weight: 0.10
      floor: 0.0

    team:
      prefer_repeat_founders: true
      prefer_technical_ceo: true
      minimum_team_size: 5
      weight: 0.20
      floor: 0.2

  scoring:
    pass_threshold: 0.65
    fast_track_threshold: 0.85
    output_format: "summary-with-highlights"

Each criterion has a weight (how much it matters) and a floor (the minimum score for that criterion alone). A company in an off-thesis geography but with strong revenue still passes if its weighted total clears 0.65. The agent ranks, it doesn’t filter — your team sees everything, sorted by fit.

According to a16z’s 2025 Marketplace Report, the best-performing VC firms evaluate deals across 8-12 structured criteria. Unstructured “gut feel” screening correlates with lower fund returns. Preqin’s 2025 LP Survey confirmed that 71% of institutional LPs now ask whether their GPs use systematic deal evaluation frameworks.

How Does the Agent Extract Data from Pitch Decks?

The agent monitors a designated Gmail inbox (or label) using Composio’s Gmail integration. When an email arrives with a PDF attachment or a DocSend link, the extraction skill triggers automatically.

Here’s the email monitoring configuration:

skills:
  - name: inbox-monitor
    type: gmail-watch
    config:
      labels: ["INBOX", "pitch-decks"]
      attachment_types: [".pdf", ".pptx"]
      link_patterns: ["docsend.com", "pitch.com", "docs.google.com/presentation"]
      polling_interval: 300  # seconds
      composio_connection: gmail-oauth

For PDF decks, the agent extracts text, tables, and figures. It looks for specific data points: company name, sector, raise amount, ARR, growth rate, team size, and geography. For DocSend links, it captures the shared deck content through authenticated access.

The extraction output is structured JSON:

{
  "company": "Meridian Data Systems",
  "sector": "data-infrastructure",
  "stage": "series-a",
  "raise_amount": 15000000,
  "arr": 4200000,
  "arr_growth_yoy": 0.85,
  "net_retention": 1.18,
  "geography": "united-states",
  "hq_city": "Austin",
  "team_size": 22,
  "founder_names": ["Sarah Chen", "Marcus Webb"],
  "repeat_founders": true,
  "technical_ceo": true,
  "source_email": "sarah@meridiandata.io",
  "received_at": "2026-03-28T09:14:00Z",
  "deck_url": null,
  "attachment": "Meridian_Series_A_Deck.pdf"
}

When the deck doesn’t include a data point — maybe they left out net retention or didn’t mention team size — the agent flags it as missing rather than guessing. Missing fields reduce that criterion’s score but don’t block the overall evaluation.

How Does External Data Enrichment Work?

Raw deck data isn’t enough for accurate scoring. Founders round up ARR, omit churn metrics, and describe their market size creatively. The enrichment skill cross-references extracted data against Crunchbase and PitchBook.

skills:
  - name: data-enrichment
    type: api-lookup
    config:
      sources:
        - provider: crunchbase
          api_key_ref: composio-vault://crunchbase-api
          lookups:
            - funding_history
            - founder_background
            - competitor_landscape
            - employee_count_trend

        - provider: pitchbook
          api_key_ref: composio-vault://pitchbook-api
          lookups:
            - valuation_comparables
            - investor_overlap
            - sector_deal_volume

      match_strategy: company_name + domain
      cache_ttl: 86400  # 24 hours

Notice the api_key_ref values — those point to Composio’s credential vault, not to keys stored in the agent’s config. The agent never sees your Crunchbase or PitchBook API credentials. This is critical when you’re running an AI system that processes thousands of external requests per month — see connecting to tools via Composio.

According to Crunchbase’s 2025 State of Private Markets report, companies that received Series A funding in 2025 had a median of 3.2 prior funding rounds tracked in public databases. That history helps the agent verify what founders claim in their decks.

The enrichment step also pulls competitor data. If a deck says “no direct competitors,” but Crunchbase lists four funded companies in the same category, the agent flags that discrepancy in the scoring output.

What Does the Scoring Output Look Like?

After extraction and enrichment, the scoring skill runs the data through your thesis criteria. Here’s a real example of what the agent produces:

{
  "company": "Meridian Data Systems",
  "overall_score": 0.88,
  "recommendation": "FAST_TRACK",
  "scored_at": "2026-03-28T09:16:42Z",

  "criteria_scores": {
    "sector": { "score": 0.95, "weight": 0.25, "note": "Data infrastructure — direct thesis match" },
    "stage": { "score": 0.90, "weight": 0.20, "note": "Series A, $15M raise within preferred range" },
    "revenue": { "score": 0.92, "weight": 0.25, "note": "ARR $4.2M, 85% YoY growth, 118% NRR" },
    "geography": { "score": 1.00, "weight": 0.10, "note": "Austin, TX — US target" },
    "team": { "score": 0.75, "weight": 0.20, "note": "Repeat founders, technical CEO, 22 employees" }
  },

  "highlights": [
    "ARR growth (85%) is 2x the Series A median of 42% (PitchBook 2025)",
    "Net retention (118%) indicates strong expansion revenue",
    "Repeat founders — Sarah Chen previously founded DataLayer (acquired by Snowflake, 2023)"
  ],

  "flags": [
    "Crunchbase shows 3 funded competitors in same category (Dataweave, Census, Hightouch)",
    "Deck claims TAM of $47B — cross-reference suggests $12-18B addressable"
  ],

  "enrichment_delta": {
    "employee_count_deck": 22,
    "employee_count_crunchbase": 19,
    "last_funding_verified": true,
    "founder_background_verified": true
  }
}

The output gives your partners everything they need in 30 seconds: overall score, recommendation tier, criterion-level breakdown, highlights worth noting, and flags that warrant follow-up. The enrichment_delta section shows where deck claims diverge from public data.

How Does Agent-Assisted Triage Compare to Manual Review?

Here’s what we’ve measured across VC firms using the agent versus manual-only screening:

McKinsey’s 2025 report on AI in financial services found that firms using structured AI screening reviewed 3.4x more opportunities with 28% higher conversion to term sheet. The throughput increase matters more than the time savings — you’re not just faster, you’re seeing deals your competitors miss because they can’t process the volume.

Cambridge Associates’ 2025 VC Benchmark Study showed that top-decile fund performance correlates with deal volume reviewed at 0.72 — the more deals you systematically evaluate, the better your returns.

How Does the Slack Alert Delivery Work?

The final step pushes scored summaries to a Slack channel where partners review them. The agent formats alerts differently based on score tier.

skills:
  - name: slack-alerts
    type: slack-post
    config:
      composio_connection: slack-oauth
      channels:
        fast_track: "#deal-flow-priority"
        standard_pass: "#deal-flow-review"
        below_threshold: "#deal-flow-archive"

      templates:
        fast_track: |
          :fire: *FAST TRACK: {{company}}* (Score: {{overall_score}})
          Sector: {{sector}} | Stage: {{stage}} | Raise: ${{raise_amount}}
          ARR: ${{arr}} | Growth: {{arr_growth_yoy}} | NRR: {{net_retention}}
          {{#highlights}}
          - {{.}}
          {{/highlights}}
          {{#flags}}
          :warning: {{.}}
          {{/flags}}
          Deck: {{attachment_link}} | Founder email: {{source_email}}

Fast-track deals (score above 0.85) hit the priority channel immediately. Standard passes (0.65-0.85) go to the review channel in a daily digest. Below-threshold deals are archived but still accessible — nothing gets deleted, which matters when a company pivots six months later and re-enters your thesis.

The alert includes a direct link to the deck (stored locally on your hardware) and the founder’s email for quick response. Partners can react with an emoji to claim a deal, and the agent logs the assignment.

Why Does Deal Flow Data Require Private Infrastructure?

This is the part most VC firms overlook when they cobble together a triage workflow using ChatGPT, Claude, or Google Gemini. Those services process your data on external servers. Pitch decks contain revenue figures, cap tables, customer names, founder compensation, and strategic plans — all shared under NDA.

According to Institutional Limited Partners Association (ILPA) guidelines updated in 2025, GPs have a fiduciary duty to protect deal information from unauthorized third-party access. The ILPA’s reporting template now includes a specific section on AI tool usage and data handling. Sending pitch decks through OpenAI’s or Anthropic’s APIs means that data hits external servers — even if those providers don’t train on it, the transmission itself may violate your LP agreement.

The SEC’s 2025 examination priorities explicitly mention AI data handling for registered investment advisers, and VC firms with over $150M AUM fall under that umbrella. The regulatory direction is clear: if you’re using AI to process deal data, you need to demonstrate data sovereignty.

An OpenClaw agent running on a Mac Mini in your office processes everything locally. Pitch decks are parsed on your hardware, scored against your thesis on your hardware, and stored on your hardware. API calls to Crunchbase and PitchBook go through Composio’s credential isolation — the enrichment data comes back to your machine, not to a third-party AI provider.

We’ve deployed this exact architecture for VC firms managing between $50M and $800M AUM. The conversation always starts the same way: “We’ve been copying deck data into ChatGPT.” That stops on day one.

How Do You Deploy This Agent with beeeowl?

The full deployment takes one day. Here’s what happens:

1. Hardware ships — A pre-configured Mac Mini ($5,000) or MacBook Air ($6,000) with OpenClaw, Docker, and all security hardening already installed. Hardware cost is included.

2. Thesis configuration — We build your scoring criteria from your existing investment thesis document. Most funds have this written down already. If you don’t, we’ll structure it during a 30-minute call with a partner.

3. Inbox connection — Gmail or Outlook connected through Composio. Your OAuth credentials never touch the agent. The agent gets permission to read emails and attachments in specific labels — nothing else.

4. Enrichment API setup — Crunchbase and PitchBook API credentials stored in Composio’s vault. If you use Harmonic, Affinity, or other data providers, we connect those too.

5. Slack integration — Channels configured, alert templates customized, partner assignments set up.

6. Security hardening — Docker sandboxing, firewall allowlists, authentication, audit trails. This isn’t optional — every beeeowl deployment includes the full security stack — see our security hardening approach.

The agent starts processing your inbox immediately after deployment. There’s no training period, no “learning phase,” no two-week ramp. Your thesis criteria are explicit rules, not machine learning predictions. The agent scores accurately from minute one.

What Customizations Do VC Firms Typically Request?

Every fund runs differently. Here are the most common modifications we build:

Co-investor overlap detection — The agent checks whether known co-investors from your network have already invested in the company. Crunchbase’s investor data powers this. If Sequoia or Accel is already on the cap table and you have a relationship, that’s a signal worth surfacing.

LP conflict screening — For funds where LPs operate in specific sectors, the agent flags potential conflicts. If your LP is a Fortune 500 healthcare company and a health-tech startup is pitching, the agent notes it before a partner accidentally takes the meeting.

Weekly digest reports — Beyond real-time Slack alerts, a weekly summary email to the managing partner showing deal volume trends, sector distribution, average scores, and response times. This becomes your fund’s operating dashboard.

CRM sync — Scored deals automatically create entries in Affinity, DealCloud, or Salesforce. No manual data entry. The agent populates company name, sector, score, and partner assignment. According to Affinity’s 2025 VC Workflow Report, firms that automate CRM entry from deal flow spend 62% less time on data hygiene.

How Do You Get Started?

If you’re running a fund and spending more than an hour a day on inbox triage, this agent pays for itself in the first week. We’ve deployed it for early-stage micro-funds and growth-stage firms with the same architecture — the thesis config is what changes, not the infrastructure.

The full deployment starts at $5,000 for the Mac Mini package, which includes the hardware, OpenClaw installation, security hardening, thesis configuration, and all integrations. One agent is included. If multiple partners each need their own scoring criteria or inbox monitoring, additional agents are $1,000 each.

Request your deployment at beeeowl and we’ll have your deal flow agent running within a week.