Run a weekly churn risk review: pull together usage, health, support, billing, and notes for at-risk accounts, name the real risk driver for each, pick a save play with an owner and a date, and write a one-page review plus a meeting agenda.
Convert Anthropic and OpenAI usage exports, or your own app's token logs, into one usage schema with customers, tasks, cached and uncached tokens, and cost from a price table you edit. Fixes the classic mistake of counting cached tokens twice, and lists unmapped keys and unpriced models.
Measure an activation funnel from an events CSV: how many users or accounts reach each step within a time window, conversion step to step, median time between steps, the biggest drop, and splits by plan or any segment. Writes markdown, CSV, JSON, and a list of who got stuck.
Score customer health from usage, support, and billing signals with weights you can read and edit. Bands every account green, yellow, or red, names the top drivers, tracks change since the last score, and flags at-risk accounts renewing soon. Works from one CSV.
Build weekly or monthly retention cohorts for users or accounts from an events CSV. Writes the cohort table, a size-weighted average curve, where the curve flattens, and the best and worst cohorts, as markdown, CSV, and JSON.
Turn a product events CSV (timestamp, account_id, user_id, event) into one self-contained HTML dashboard: DAU, WAU, MAU, stickiness, active accounts, top features, activation rate, weekly retention, and accounts trending down. No external scripts; open it in any browser or attach it to an email.
Turn LLM usage logs into one self-contained HTML cost dashboard for an agentic product: cost per customer, per task, per successful outcome, model mix, cache hit rate, and gross margin when you add revenue by customer. Prices blank costs from an editable price table.
Plan an enrichment waterfall with real math. Give it your providers with cost, match rate, and accuracy (or a sample test run), and it tries every order to find the cheapest setup that hits your fill target, with cost per usable record, the marginal cost of each step, and where to stop. Vendor-neutral.
Define your ICP and size the market from a companies CSV (a CRM export or any company list). Applies market filters for SAM, scores every company into A, B, and C tiers with reasons, values each layer with ACV by size band, and writes a tiered account list ready for territories or outbound.
Measure search quality with a fixed set of real queries: hits, misses, and false positives at the current cutoff and across a sweep of cutoffs, so ranking and threshold changes are chosen from data instead of guesses. Works for keyword, semantic, or hybrid search.
