Freshdesk Agent Performance Intelligence

Weekly AI coaching briefs for every support agent — scores resolution speed, SLA compliance, CSAT, escalation rates, and throughput from Freshdesk data.

Weekly AI coaching briefs for every support agent — scores resolution speed, SLA compliance, CSAT, escalation rates, reassignment rates, and throughput from Freshdesk data. 6-dimension performance taxonomy with coaching priority classification (HIGH/MEDIUM/LOW). Delivers Slack team digest and per-agent Notion coaching briefs.

Four Agents. Per-Agent Performance Coaching. Slack + Notion Delivery.

Fetcher

Step 1 — Fetcher

Code Only

Pulls all tickets from the Freshdesk API for the configured lookback window (default 7 days). Groups tickets by agent with response times, CSAT ratings, escalation counts, reassignment counts, and complexity tiers. Zero LLM cost.

Assembler

Step 2 — Assembler

Code Only

Computes six performance dimension metrics per agent: resolution speed, first response SLA compliance, CSAT score, escalation rate, reassignment rate, and complexity-adjusted throughput. Calculates team baselines and assigns coaching priority (HIGH/MEDIUM/LOW). Zero LLM cost.

Analyst

Step 3 — Analyst

Tier 2 Classification

Scores each performance dimension 1-10 using defined rubrics, computes composite score (equal weight), verifies coaching priority, identifies strengths and improvement areas, and generates per-agent coaching briefs with specific action items. Sonnet 4.6 with chain-of-thought enforcement.

Formatter

Step 4 — Formatter

Tier 3 Creative

Generates two outputs: (1) Slack Block Kit team digest with per-agent composite scores, coaching priorities, top performer highlights, and coaching needs. (2) Notion per-agent coaching briefs with detailed dimension breakdowns and specific recommendations. Sonnet 4.6.

What It Does NOT Do

×

Does not modify Freshdesk tickets or agent assignments — it reads performance data only

×

Does not replace your team lead — it provides data-driven coaching signals for human managers

×

Does not work with Zendesk, Intercom, or other helpdesks — Freshdesk API only in v1.0

×

Does not predict future performance — it scores current performance from existing ticket data

×

Does not guarantee agent improvement — it identifies coaching opportunities for human follow-up

×

Does not handle real-time monitoring — it runs weekly aggregate analysis, not per-ticket

The Complete Customer Success Bundle

7+ files — workflow JSON (main + scheduler), system prompts, and complete documentation.

freshdesk_agent_performance_intelligence_v1_0_0.json — The 26-node n8n main workflow (AGGREGATE weekly performance coaching)
freshdesk_agent_performance_intelligence_scheduler_v1_0_0.json — The 3-node scheduler workflow (Monday 8:00 UTC trigger)
README.md — 10-minute setup guide with Freshdesk, Notion, Slack credentials and split-workflow configuration
docs/TDD.md — Technical Design Document with performance taxonomy and SINGLE-MODEL pattern
system_prompts/analyst_system_prompt.md — Analyst prompt (6-dimension performance scoring + per-agent coaching briefs)
system_prompts/formatter_system_prompt.md — Formatter prompt (Slack team digest + Notion coaching briefs)
CHANGELOG.md — Version history

Tested. Measured. Documented.

Every metric is ITP-measured. The Freshdesk Agent Performance Intelligence blueprint scores six performance dimensions per support agent — Sonnet 4.6 for analysis and formatting, weekly aggregate cost.

Workflow Nodes

26 + 3 (scheduler)

Blueprint Quality Standard

12/12 PASS

Agent Architecture

Fetcher (Code-only) → Assembler (Code-only) → Analyst (Sonnet 4.6) → Formatter (Sonnet 4.6)

Required Credentials

Freshdesk (httpHeaderAuth), Notion (httpHeaderAuth), Slack (httpHeaderAuth), Anthropic (anthropicApi)

Bundle Contents

7+ files

Cost per Run

$0.03–$0.10/run

ITP Milestones

8/8 variations · 14/14 milestones

n8n Compatibility

2.7.5

Freshdesk Agent Performance Intelligence v1.0.0────────────────────────────────────────Nodes          26 + 3 (scheduler)Agents         4 (Fetcher → Assembler → Analyst → Formatter)Model          Sonnet 4.6 (SINGLE-MODEL)Tool A         Freshdesk (httpHeaderAuth)Tool B         Slack (httpHeaderAuth Bearer)Tool C         Notion (httpHeaderAuth Bearer)Trigger        Schedule (Monday 8:00 UTC) + WebhookPattern        AGGREGATE — weekly per-agent coachingBQS            12/12 PASSITP            8/8 variations · 14/14 milestones

What You'll Need

Platform

n8n 2.7.5+

Est. Monthly API Cost

Weekly run cost ~$0.03-0.10/run ($0.13-$0.43/month)

Credentials Required

  • ▪Anthropic API
  • ▪Freshdesk API (httpHeaderAuth)
  • ▪Slack (Bot Token, httpHeaderAuth Bearer)
  • ▪Notion (httpHeaderAuth Bearer)

Services

  • ▪Freshdesk account (API key, any plan)
  • ▪Slack workspace (Bot Token with chat:write scope)
  • ▪Notion workspace (integration token)
  • ▪Anthropic API key

Setup Track

Quick Start

~15 min

All credentials live, n8n running

Full Setup

1–2 hrs

Needs API config + tables

From Scratch

2–4 hrs

No n8n, no credentials

Freshdesk Agent Performance Intelligence v1.0.0

$199

one-time purchase

What you get:

  • ✓Production-ready 26+3 node n8n workflow — import and deploy
  • ✓Weekly schedule: fires every Monday at 8:00 UTC (customizable)
  • ✓Six performance dimensions: resolution speed, first response SLA, CSAT score, escalation rate, reassignment rate, complexity-adjusted throughput
  • ✓Coaching priority: HIGH (<70% team avg) / MEDIUM (70-100%) / LOW (>avg)
  • ✓Per-agent coaching briefs with strengths, improvement areas, and specific action items
  • ✓Team baselines computed automatically from all agent data
  • ✓Slack Block Kit team digest with composite scores and coaching highlights
  • ✓Notion per-agent coaching briefs with detailed dimension breakdowns
  • ✓Split-workflow pattern: scheduler + main pipeline (both included)
  • ✓SINGLE-MODEL: Sonnet 4.6 for analysis and formatting — no Opus needed
  • ✓AGGREGATE pattern: one Analyst call per weekly run, not per agent
  • ✓ITP 8/8 variations, 14/14 milestones measured
  • ✓All sales final after download

Frequently Asked Questions

What are the six performance dimensions?+

Resolution Speed (average hours to resolve), First Response SLA (compliance rate for initial response), CSAT Score (customer satisfaction average), Escalation Rate (fraction of tickets escalated), Reassignment Rate (fraction of tickets reassigned), and Complexity-Adjusted Throughput (weighted ticket count based on difficulty tier).

How does coaching priority work?+

Each agent gets a composite score from the six dimensions. HIGH priority (<70% of team average) means immediate coaching needed. MEDIUM (70-100%) targets specific improvement areas. LOW (>100%) identifies top performers for recognition and best practice extraction.

How does this differ from Support Pattern Analyzer?+

SPA (#18) clusters ticket topics and patterns across your support queue. FAPI coaches individual agents on their personal performance metrics. Different lens: SPA looks at what customers are asking about; FAPI looks at how each agent handles those requests.

How does this differ from Sales Rep Performance Coach?+

SRPC (#35) coaches sales reps using HubSpot deal data. FAPI coaches support agents using Freshdesk ticket data. Same coaching philosophy, different team and data source.

Can I customize the coaching tone?+

Yes. Set COACHING_TONE to "constructive" (encouraging + specific), "direct" (straightforward assessment), or "supportive" (empathetic + growth-oriented). This affects how the Analyst frames improvement recommendations.

Does it use web scraping?+

No. All data comes from the Freshdesk API. No web_search or external scraping. Fully deterministic and fast.

Can I filter to specific agents?+

Yes. Set AGENT_IDS to an array of Freshdesk agent IDs to analyze only those agents, or leave empty to analyze all agents with tickets in the lookback window.

Why only Sonnet instead of Opus?+

The Fetcher retrieves ticket data from the Freshdesk API and the Assembler pre-computes all performance metrics and team baselines. The Analyst receives pre-computed numbers and applies a scoring rubric — classification-tier reasoning that Sonnet 4.6 handles accurately. No deep causal analysis required.

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.

Read the full guide →

Related Blueprints

Freshdesk SLA Risk Predictor

AI-powered per-ticket SLA breach prediction that scores risk across five factors — complexity, customer tier, agent capacity, historical patterns, and escalation signals — and alerts your team before deadlines slip.

$199

Freshdesk Customer Effort Scorer

AI-powered weekly customer effort scoring that bridges Freshdesk support data with Pipedrive deal value — identifies high-effort, high-value accounts at risk of churning before it's too late.

$199

Support Pattern Analyzer

AI reads your Freshdesk. Delivers a weekly support intelligence brief before standup.

$199