How PostHog Trial Conversion Intelligence Scores PQLs

Your team runs this workflow every week: pull records from Posthog, Pipedrive, Gmail, Slack, cross-reference with a second source, apply judgment, format the output, and route it to 3 different stakeholders. Last Tuesday it took 30–60 minutes per cycle. This Tuesday the person who usually runs it is out sick, and nobody else knows the exact steps. The output varies by who runs it and when.

The core issue is data fragmentation. The information exists, but assembling it into actionable intelligence requires manual effort that does not scale with headcount. PostHog Trial Conversion Intelligence closes that gap by automating the trial conversion and product led growth workflow from data extraction through structured output delivery.

Five Agents. Daily PQL Scoring. automated Conversion Outreach.

The PostHog Trial Conversion Intelligence pipeline runs 5 agents in sequence. The Fetcher pulls data from Posthog and Pipedrive and Gmail and Slack, and The Formatter delivers the output. Here is what happens at each stage and why it matters.

• The Fetcher (Code-only): Retrieves trial user event data from PostHog API — page views, feature usage events, session counts, unique days active, team invitations, and integration activations.
• The Assembler (Code-only): Computes 5 PQL (Product Qualified Lead) dimensions for each trial user: activation_depth (30%) — completion of key activation milestones, usage_velocity (25%) — session frequency and recency trend, feature_breadth (20%) — count of distinct features used vs power feature list, team_signal (15%) — team invitations, shared workspaces, collaborative events, engagement_recency (10%) — days since last activity and session trend direction..
• The Scorer (Tier 2 Classification): Computes weighted PQL score (0-10) and classifies each trial user: HOT (≥8) — ready for sales touch, WARM (5-7) — nurture with product-led content, COLD (<5) — low engagement, deprioritize or product intervention needed.
• The Writer (Tier 3 Creative): Generates personalized conversion outreach email drafts per PQL tier.
• The Formatter (Code-only): Creates Gmail draft emails for HOT and WARM users, creates Pipedrive deals for HOT users (if not already tracked), and posts a daily Slack summary with PQL distribution, conversion funnel metrics, top 5 HOT users, and feature adoption gaps across the trial cohort..

When the pipeline completes, you get structured output that is ready to act on. The blueprint bundle includes everything needed to deploy, configure, and customize the workflow:

• ITP-tested n8n workflow (31 nodes + 3-node scheduler)
• 5-dimension PQL scoring (activation_depth, usage_velocity, feature_breadth, team_signal, engagement_recency)
• 3-tier PQL classification (HOT ≥8, WARM 5-7, COLD <5)
• Personalized conversion outreach drafts per PQL tier
• Automatic Pipedrive deal creation for HOT users
• Feature adoption gap analysis across trial cohort
• Gmail draft creation with usage-specific messaging
• Daily Slack summary with PQL distribution and top 5 HOT users
• Configurable: trial length, PQL thresholds, activation events, power features, draft mode
• Full technical documentation and system prompts

All scoring criteria, output formats, and routing rules are configurable in the system prompts — no workflow JSON edits required. This means PostHog Trial Conversion Intelligence adapts to your specific process, terminology, and integration requirements without forking the entire workflow.

Understanding how the pipeline works helps you customize it for your environment and troubleshoot issues when they arise. Here is a step-by-step walkthrough of the PostHog Trial Conversion Intelligence execution flow.

Step 1: The Fetcher

Tier: Code-only

The pipeline starts here. Retrieves trial user event data from PostHog API — page views, feature usage events, session counts, unique days active, team invitations, and integration activations. Filters to users within the configurable trial window and assembles per-user behavioral profiles with event counts and timestamps.

This stage ensures all downstream agents receive clean, validated input. If this step returns incomplete data, every downstream agent works with a degraded picture.

Step 2: The Assembler

Tier: Code-only

Computes 5 PQL (Product Qualified Lead) dimensions for each trial user: activation_depth (30%) — completion of key activation milestones, usage_velocity (25%) — session frequency and recency trend, feature_breadth (20%) — count of distinct features used vs power feature list, team_signal (15%) — team invitations, shared workspaces, collaborative events, engagement_recency (10%) — days since last activity and session trend direction.

Why this step matters: The result is a prioritized action queue, not just a data dump.

Step 3: The Scorer

Tier: Tier 2 Classification

Computes weighted PQL score (0-10) and classifies each trial user: HOT (≥8) — ready for sales touch, WARM (5-7) — nurture with product-led content, COLD (<5) — low engagement, deprioritize or product intervention needed. Generates per-user conversion strategy with specific feature adoption gaps and recommended next actions.

Every field in the output is structured for the next agent to consume without parsing.

Step 4: The Writer

Tier: Tier 3 Creative

Generates personalized conversion outreach email drafts per PQL tier. HOT users get direct sales outreach with pricing and plan options. WARM users get feature discovery content based on unused power features. COLD users get re-engagement content highlighting the features they used most. Each draft references specific usage data.

Why this step matters: This step narrows the dataset so downstream agents only process records that matter.

Step 5: The Formatter

Tier: Code-only

This is the final deliverable — what lands in your inbox or dashboard. Creates Gmail draft emails for HOT and WARM users, creates Pipedrive deals for HOT users (if not already tracked), and posts a daily Slack summary with PQL distribution, conversion funnel metrics, top 5 HOT users, and feature adoption gaps across the trial cohort.

The entire pipeline executes without manual intervention. From trigger to output, every decision point follows a documented path. Every execution produces a traceable audit trail.

All nodes have been validated during Independent Test Protocol (ITP) testing on n8n v2.7.5. The error handling matrix in the bundle documents the recovery path for each failure mode.

7 of 20 fixtures had wrong expected values — the test author used simplified math instead of the pipeline's actual weighted formula. The fixtures said LUS 7, the pipeline correctly calculated LUS 6. We were debugging a "bug" that was actually correct behavior. Lesson: expected values must come from the same formula the pipeline uses.

— ForgeWorkflows Engineering

Daily trial conversion intelligence with 5-dimension PQL scoring, 3-tier classification, and automated outreach from PostHog behavioral data delivered via Gmail, Pipedrive, and Slack.

The primary operating cost for PostHog Trial Conversion Intelligence is the per-execution LLM inference cost. Based on Independent Test Protocol (ITP) testing, the measured cost is: Cost per Run: $0.086 per user. This figure includes all API calls across all agents in the pipeline — not just the primary reasoning step, but every classification, scoring, and output generation call.

To put this in context, consider the manual alternative. A skilled team member performing the same work manually costs $50–75/hour for an operations analyst at a fully loaded rate (salary, benefits, tools, overhead). If the manual version of this workflow takes 30–60 minutes per cycle, the per-execution cost in human labor is significant. The blueprint executes the same pipeline for a fraction of that cost, with consistent quality and zero fatigue degradation.

Infrastructure costs are separate from per-execution LLM costs. You will need an n8n instance (self-hosted or cloud) and active accounts for the integrated services. The estimated monthly infrastructure cost is Daily cost ~$0.086/user (~$50-80/month for 20-30 trial users/day), depending on your usage volume and plan tiers.

Quality assurance: Blueprint Quality Standard (BQS) audit result is 12/12 PASS. ITP result is 20/20 records, all milestones PASS. These are not marketing claims — they are test results from structured inspection protocols that you can review in the product documentation.

All cost and performance figures are ITP-measured — tested against real data fixtures on n8n v2.7.5 in March 2026. See the product page for full test methodology.

6 files. Main workflow + scheduler + prompts + docs.

When you purchase PostHog Trial Conversion Intelligence, you receive a complete deployment bundle. This is not a SaaS subscription or a hosted service — it is a set of files that you own and run on your own infrastructure. Here is what is included:

• CHANGELOG.md — Version history
• README.md — Setup and configuration guide
• docs/TDD.md — Technical Design Document
• posthog_trial_conversion_intelligence_v1_0_0.json — n8n workflow (main pipeline)
• system_prompts/analyst_system_prompt.md — Analyst system prompt
• system_prompts/writer_system_prompt.md — Writer system prompt
• workflow/ptci_scheduler_v1_0_0.json — Scheduler workflow

Start with the README.md. It walks through the deployment process step by step, from importing the workflow JSON into n8n to configuring credentials and running your first test execution. The dependency matrix lists every required service, API key, and estimated cost so you know exactly what you need before you start.

Every file in the bundle is designed to be read, understood, and modified. There is no obfuscated code, no compiled binaries, and no phone-home telemetry. You get the source, you own the source, and you control the execution environment.

PostHog Trial Conversion Intelligence is built for Growth, Sales teams that need to automate a specific workflow without building from scratch. If your team matches the following profile, this blueprint is designed for you:

• You operate in a growth or sales function and handle the workflow this blueprint automates on a recurring basis
• You have (or are willing to set up) an n8n instance — self-hosted or cloud
• You have active accounts for the required integrations: PostHog with trial user event tracking, Pipedrive CRM, Anthropic API key, Gmail account, Slack workspace (Bot Token with chat:write)
• You have API credentials available: Anthropic API, PostHog (API Key), Pipedrive (API Token), Gmail (OAuth2), Slack (Bot Token, httpHeaderAuth Bearer, chat:write)
• You are comfortable importing a workflow JSON and configuring API keys (the README guides you, but basic technical comfort is expected)

This is NOT for you if:

• Does not modify PostHog data or feature flags — read-only event analysis
• Does not replace product analytics platforms — it adds conversion intelligence on top of PostHog data
• Does not handle payment processing — it identifies and routes conversion-ready users to sales
• Does not send emails automatically by default — draft mode for human review
• Does not track post-conversion usage — focused on trial-to-paid conversion window

Review the dependency matrix and prerequisites before purchasing. If you are unsure whether your environment meets the requirements, contact support@forgeworkflows.com before buying.

Every pipeline has boundaries. These are intentional design decisions, not oversights — understanding them helps you deploy with the right expectations and plan for edge cases in your environment.

Does not modify PostHog data or feature flags — read-only event analysis

This is intentional. We default to human-in-the-loop for actions that carry reputational or financial risk. Once your team has validated output accuracy over 20+ cycles, you can adjust the pipeline to auto-execute — the workflow JSON supports it, but the default is conservative.

Does not replace product analytics platforms — it adds conversion intelligence on top of PostHog data

We scoped this boundary after ITP testing revealed inconsistent results when the pipeline attempted this. The agents handle what they handle well — extending beyond this scope requires custom prompt engineering specific to your data shape.

Does not handle payment processing — it identifies and routes conversion-ready users to sales

This keeps the pipeline focused on a single workflow. Adding this capability would introduce branching logic that varies by organization, and the tradeoff between complexity and reliability was not worth it for a reusable blueprint. Fork the workflow JSON if your use case demands it.

Deployment follows a structured sequence. The PostHog Trial Conversion Intelligence bundle is designed for the following tools: n8n, Anthropic API, PostHog, Pipedrive, Gmail, Slack. Here is the recommended deployment path:

1. Step 1: Import workflows and configure credentials. Import both workflow JSON files into n8n (main + scheduler). Configure PostHog API Key, Pipedrive API Token, Gmail OAuth2, Slack Bot Token (httpHeaderAuth with Bearer prefix, chat:write scope), and Anthropic API key following the README.
2. Step 2: Configure trial parameters and PQL thresholds. Set POSTHOG_PROJECT_ID, TRIAL_LENGTH_DAYS (default 14), PQL_HOT_THRESHOLD (default 8), PQL_WARM_THRESHOLD (default 5), ACTIVATION_EVENTS (array of key milestone event names), POWER_FEATURE_LIST (array of power feature event names), PIPEDRIVE_PIPELINE_ID, GMAIL_DRAFT_MODE (default true), and SLACK_CHANNEL in the scheduler Build Payload node.
3. Step 3: Activate scheduler and verify. Update the webhook URL in the scheduler to match your main workflow webhook path. Activate both workflows. Send a test POST with _is_itp: true and sample PostHog event data. Verify PQL scoring in Pipedrive and the Slack summary appears.

Before running the pipeline on live data, execute a manual test run with sample input. This validates that all credentials are configured correctly, all API endpoints are reachable, and the output format matches your expectations. The README includes test data examples for this purpose.

Once the test run passes, you can configure the trigger for production use (scheduled, webhook, or event-driven — depending on the blueprint design). Monitor the first few production runs to confirm the pipeline handles real-world data as expected, then let it run.

For technical background on how ForgeWorkflows blueprints are built and tested, see the Blueprint Quality Standard (BQS) methodology and the Inspection and Test Plan (ITP) framework. These documents describe the quality gates every blueprint passes before listing.

Ready to deploy? View the PostHog Trial Conversion Intelligence product page for full specifications, pricing, and purchase.