AI Agent Workflow Collection

Monitors LTX API runtime performance, latency, error rates, and throughput. Alerts on performance degradation or errors.

Monitor and analyze backend GPU costs for LTX API and LTX Studio. Use when analyzing cost trends, detecting anomalies, breaking down costs by endpoint/model/org/process, monitoring utilization, or investigating cost efficiency drift.

Build a structured data spec document for analytics topics by exploring the dbt codebase, identifying relevant events/models/columns, and producing a ready-to-use markdown reference. Use when: (1) starting a new data analysis, (2) documenting events for a feature or domain, (3) creating a reference for an agent or analyst.

Analyzes Gong sales call transcripts from a product team perspective. Extracts what customers love, what they dislike, missing features they request, objection categories, sentiment, and conversion blockers. Use when the user wants to analyze sales calls, understand product feedback, identify feature gaps, or generate a product intelligence report from call data.

Generate the LTX weekly leadership Slack post covering Open Source (HuggingFace LTX-2 family), API (revenue, endpoints, leads, industries), and Studio Enterprise (contracts, pilots, LTX-model consumption share). Runs every Monday via n8n: BigQuery → JSON parse → Slack render → LLM TL;DR → Slack webhook. Use when: weekly exec update, leadership Slack channel automation, or when asked for 'last week's LTX numbers'.

Generate LTX Studio marketing & sales daily report with lead gen, spend, PELs/PQLs, sales metrics, and top org usage vs 7-day averages. Use when: daily marketing standup, GTM review, or when asked for 'marketing numbers' or 'lead performance'.

Generate LTX Studio product daily report with revenue, usage by segment (Enterprise, Pilot, Paying Non-Enterprise, Free), and DoD/DOW-avg comparisons. Use when: daily product standup, executive reporting, or when asked for 'yesterday's product numbers'.

Generate LTX Studio sales opportunities report and credit limit alerts. Covers pipeline by rep/product (yesterday + QTD), new PELs/PQLs, future meetings, and enterprise orgs at 80%+ token usage. Use when: sales standup, pipeline review, account health check, or when asked for 'sales numbers' or 'credit alerts'.

Monitors revenue metrics, tracks subscription changes, and alerts on revenue anomalies or threshold breaches.

Adds the analyst layer (segmentation framing, filter/KPI surfacing, LTX-specific definitions, contextual follow-ups) on top of any Data MasterMind data interaction for LTX stakeholders (PMs, marketers, design, leadership). Wraps get-data / validate-data / understand-data / visualize-data — dialing intensity from a full guided session (for "look into X", "investigate Y", "do an analysis of ...") down to a compressed wrap (for "what's MRR?", "is this number right?"). Output mode (chat-only or HTML artifact) is chosen up front for session-style asks. Always asks about Enterprise / paid non-Enterprise / Free segmentation and Studio-feature tier-gating when relevant. Do NOT use only when the user explicitly opts out ("just give me the number, no extras") or for templated feature dashboards (that's the Hex-based dashboard-builder).