How NPS/CSAT Response Intelligence Decodes Survey Data
The Problem
Your support team closed 340 tickets last week. Average resolution time: 4.2 hours. But 23 of those tickets were escalations that sat for 6+ hours before anyone noticed the SLA clock. A team lead spends 1–2 hours daily pulling reports from Typeform, Notion, Slack, cross-referencing with CRM data, and writing up findings. By the time the analysis is done, the queue has moved on.
The result is reactive support instead of proactive operations. SLA risks surface after the breach. Routing problems persist because nobody has time to audit the rules. Agent coaching happens based on gut feel, not pattern data. NPS/CSAT Response Intelligence automates the customer intelligence and account management workflow, delivering structured analysis from Typeform, Notion, Slack data without manual report-building.
Support leads typically spend 1–2 hours daily on manual analysis. NPS/CSAT Response Intelligence automates the entire workflow, delivering structured output before the next shift starts.
What This Blueprint Does
Four Agents. Six Themes. Weekly Sentiment Intelligence.
The NPS/CSAT Response Intelligence pipeline runs 4 agents in sequence. Fetcher pulls data from Typeform and Notion and Slack, and Formatter delivers the output. Here is what happens at each stage and why it matters.
- Fetcher (Schedule + Code): Schedule Trigger fires weekly (Friday 08:00 UTC) or manual Webhook for on-demand runs.
- Assembler (Code-only): Computes NPS score from raw responses, classifies each into promoter (9–10), passive (7–8), or detractor (0–6) segments, and groups response text for thematic analysis.
- Analyst (Tier 2 Classification): the analysis model receives ONE aggregate call with the entire weekly response batch.
- Formatter (Tier 2 Classification): the analysis model generates three outputs: (1) Notion weekly thematic analysis report with 8 sections — Executive Summary, NPS Score + Trend, Theme Distribution, Promoter Highlights, Detractor Analysis, Feature Gap Inventory, Competitor Intelligence, Week-over-Week Comparison; (2) Slack weekly summary via Block Kit; (3) Slack at-risk detractor alerts — one per actionable detractor with score, themes, verbatim quote, and recommended follow-up..
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 23-node n8n workflow — import and deploy
- Weekly Schedule Trigger (Friday 08:00 UTC) or manual Webhook for on-demand runs
- Typeform API pagination for NPS and CSAT survey responses over 7-day lookback
- NPS score computation with promoter/passive/detractor segmentation
- 6-theme taxonomy: product_quality, support_experience, pricing_value, feature_gaps, competitor_mentions, advocacy_signals
- NPS trend comparison vs prior week with delta tracking
- Per-detractor actionable insights with verbatim quotes and recommended follow-up
- Notion weekly thematic analysis report with 8 sections (Executive Summary through Week-over-Week Comparison)
- Slack weekly summary (Block Kit) + at-risk detractor alerts with recommended actions
- AGGREGATE architecture: single Analyst + Formatter calls — $0.072/run regardless of response count
- Dual the analysis model: no the primary reasoning modelrequired
- ITP 8 variations, 14/14 milestones, $0.072/run measured
SLA thresholds, escalation rules, and routing logic are configurable in the system prompts — customize for your ticket volume and priority structure. This means NPS/CSAT Response Intelligence adapts to your specific process, terminology, and integration requirements without forking the entire workflow.
SLA thresholds, routing rules, and escalation logic are all configurable in the system prompts. Adapt to your ticket volume and priority structure without code changes.
How the Pipeline Works
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 NPS/CSAT Response Intelligence execution flow.
Step 1: Fetcher
Tier: Schedule + Code
The pipeline starts here. Schedule Trigger fires weekly (Friday 08:00 UTC) or manual Webhook for on-demand runs. Fetcher paginates Typeform API for NPS and CSAT survey responses over a configurable 7-day lookback window. Extracts response scores, text feedback, respondent metadata, and submission 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: Assembler
Tier: Code-only
Computes NPS score from raw responses, classifies each into promoter (9–10), passive (7–8), or detractor (0–6) segments, and groups response text for thematic analysis. Produces a unified weekly response payload with segment counts, NPS delta vs prior week, and response text corpus for the Analyst.
Why this step matters: The result is a prioritized action queue, not just a data dump.
Step 3: Analyst
Tier: Tier 2 Classification
the analysis model receives ONE aggregate call with the entire weekly response batch. Performs thematic analysis across 6 categories: product_quality, support_experience, pricing_value, feature_gaps, competitor_mentions, and advocacy_signals. Generates NPS trend comparison vs prior week, theme distribution, and per-detractor actionable insights.
Every field in the output is structured for the next agent to consume without parsing.
Step 4: Formatter
Tier: Tier 2 Classification
This is the final deliverable — what lands in your inbox or dashboard. the analysis model generates three outputs: (1) Notion weekly thematic analysis report with 8 sections — Executive Summary, NPS Score + Trend, Theme Distribution, Promoter Highlights, Detractor Analysis, Feature Gap Inventory, Competitor Intelligence, Week-over-Week Comparison; (2) Slack weekly summary via Block Kit; (3) Slack at-risk detractor alerts — one per actionable detractor with score, themes, verbatim quote, and recommended follow-up.
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.
This blueprint executes in your own n8n environment using your own API credentials. Zero external data sharing.
Why we designed it this way
n8n strips error prefixes during message propagation. An error thrown as "VALIDATION_ERROR: Missing required field" arrives at the error handler as "Missing required field." Every error handler matches on content that survives the pipeline — forbidden phrases, field names, status codes — not on prefixes that get stripped.
— ForgeWorkflows Engineering
Cost Breakdown
Every metric is ITP-measured. The NPS/CSAT Response Intelligence agent analyzes your weekly Typeform survey responses — computing NPS score, segmenting respondents, performing thematic analysis across 6 categories, and delivering an 8-section Notion report with Slack summary and detractor alerts at $0.072/run.
The primary operating cost for NPS/CSAT Response Intelligence is the per-execution LLM inference cost. Based on Independent Test Protocol (ITP) testing, the measured cost is: Cost per Run: $0.072/run (ITP-measured average). 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 $40–60/hour for a support team lead’s analysis time at a fully loaded rate (salary, benefits, tools, overhead). If the manual version of this workflow takes 1–2 hours daily, 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 $0.31/month (weekly runs) + Typeform/Notion/Slack free tiers, depending on your usage volume and plan tiers.
Quality assurance: Blueprint Quality Standard (BQS) audit result is 12/12 PASS. ITP result is 8 variations, 14/14 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.
Monthly projection: if you run this blueprint 100 times per month, multiply the per-execution cost by 100 and add your infrastructure costs. Most teams find the total is less than one hour of manual labor per month.
What's in the Bundle
5 files — workflow JSON, system prompts, scoring guide, and complete documentation.
When you purchase NPS/CSAT Response 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 historyREADME.md— Setup and configuration guideTDD.md— Technical Design Documentnps_csat_response_intelligence_v1.0.0.json— n8n workflow (main pipeline)system_prompts/analyst_system_prompt.md— Analyst system promptsystem_prompts/formatter_system_prompt.md— Formatter system prompt
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.
Who This Is For
NPS/CSAT Response Intelligence is built for Customer Success, Product 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 customer success or product 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: Typeform account (NPS/CSAT forms with Personal Access Token), Notion workspace (API access), Slack workspace (Bot Token with chat:write scope)
- You have API credentials available: Anthropic API, Typeform (httpHeaderAuth), Notion (httpHeaderAuth), Slack (Bot Token, httpHeaderAuth)
- 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 analyze support tickets — that is what Support Pattern Analyzer does
- Does not recover abandoned forms — that is what Form Abandonment Recovery does
- Does not monitor CRM engagement health — that is what Account Health Intelligence Agent does
- Does not modify Typeform surveys or send follow-up emails — read-only analysis
- Does not scrape external websites — all data from Typeform API
- Does not track individual customer journeys — provides aggregate weekly thematic intelligence
Review the dependency matrix and prerequisites before purchasing. If you are unsure whether your environment meets the requirements, contact support@forgeworkflows.com before buying.
All sales are final after download. Review the full dependency matrix, prerequisites, and integration requirements on the product page before purchasing. Questions? Contact support@forgeworkflows.com.
Edge cases to know about
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 analyze support tickets — that is what Support Pattern Analyzer does
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 recover abandoned forms — that is what Form Abandonment Recovery does
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 monitor CRM engagement health — that is what Account Health Intelligence Agent does
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.
The dead letter queue captures any records that fail processing. Check it after your first production run to validate data coverage.
Getting Started
Deployment follows a structured sequence. The NPS/CSAT Response Intelligence bundle is designed for the following tools: n8n, Anthropic API, Typeform, Notion, Slack. Here is the recommended deployment path:
- Step 1: Import workflow and configure credentials. Import nps_csat_response_intelligence_v1_0_0.json into n8n. Configure Typeform httpHeaderAuth credential (Personal Access Token), Anthropic API key, Notion httpHeaderAuth credential (Bearer token), and Slack httpHeaderAuth credential (Bearer token) following the README.
- Step 2: Configure schedule and Typeform form IDs. The Schedule Trigger defaults to weekly (Friday 08:00 UTC). Adjust the cron expression to match your reporting cadence. Configure the Typeform form IDs for your NPS and CSAT surveys, the lookback window (default 7 days), and Slack channel for weekly summary and detractor alerts.
- Step 3: Activate and verify. Enable the workflow in n8n. Trigger a manual run via the Webhook URL. Verify the Notion weekly report is created with all 8 sections, Slack summary posts to the configured channel, and at-risk detractor alerts fire for respondents with low scores and actionable themes.
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 NPS/CSAT Response Intelligence product page for full specifications, pricing, and purchase.
Run a manual test with sample data before switching to production triggers. This catches credential misconfigurations and API endpoint issues before they affect real workflows.
Frequently Asked Questions
How does it differ from Support Pattern Analyzer?+
Complementary products covering different feedback channels. SPA analyzes Freshdesk support tickets weekly for pattern clustering and health scoring. NCRI analyzes Typeform NPS/CSAT survey responses for thematic intelligence and NPS trends. SPA tells you what customers are complaining about in support; NCRI tells you what customers think about your product overall.
What are the six theme categories?+
Product Quality — reliability, performance, usability feedback. Support Experience — response time, resolution quality, interaction satisfaction. Pricing/Value — pricing perception, value for money, plan tier feedback. Feature Gaps — missing features, requested integrations, capability gaps. Competitor Mentions — competitor comparisons, switching intent, alternative tools. Advocacy Signals — referral intent, positive word-of-mouth, loyalty indicators.
What does the Notion report contain?+
Eight sections: Executive Summary (response count, NPS score, key themes), NPS Score + Trend (current vs prior week with delta), Theme Distribution (counts and percentages per category), Promoter Highlights (what promoters love most), Detractor Analysis (top pain points with verbatim quotes), Feature Gap Inventory (requested features ranked by frequency), Competitor Intelligence (mentioned competitors and context), and Week-over-Week Comparison (key metric deltas). The README walks through configuration in under 10 minutes, including test data for validation.
Why is it so cheap at $0.072/run?+
AGGREGATE architecture. Instead of making one LLM call per response (which would cost $0.02×N), the entire weekly batch is assembled by code-only nodes and sent to the Analyst in a single call. The Formatter also receives one call. Two Sonnet 4.6 calls total regardless of response count. 52 weekly runs = $3.74/year in LLM costs.
How many survey responses can it handle?+
The Analyst receives the full weekly response batch in one call. Sonnet 4.6 handles context windows up to 200K tokens. Practical limit depends on your weekly response volume and verbatim length — typical SaaS with 20–200 weekly responses fits comfortably. For very high volume (500+), consider running bi-weekly.
Does it use web scraping?+
No. All data comes from the Typeform API: response scores, text feedback, respondent metadata, and submission timestamps. No web_search, no external data sources, no scraping. This makes the pipeline fast, reliable, and deterministic.
How does it differ from Account Health Intelligence Agent?+
Different data sources and signals. AHIA monitors HubSpot engagement health (deals, tickets, engagements) per account. NCRI monitors customer sentiment health from Typeform NPS/CSAT survey responses across your customer base. AHIA tells you who is disengaged from your CRM; NCRI tells you how customers feel about your product. Use both for complete customer health coverage.
Is there a refund policy?+
All sales are final after download. Review the Blueprint Dependency Matrix and prerequisites before purchase. Questions? Contact support@forgeworkflows.com before buying. Full terms at forgeworkflows.com/legal.
What should I do if the pipeline dead-letters a record?+
Check the dead letter output for the failure reason — the error context includes which agent failed and why. Common causes: missing input fields, API rate limits, or malformed data. Fix the underlying issue and reprocess. The error handling matrix in the bundle documents every failure mode and its recovery path.