Examples

Twelve real workflows, explained

See Sparsi in action across a range of production patterns. These examples demonstrate how to move from "prompt-only" automation to robust, deterministic-first workflows—drastically reducing token usage and eliminating hallucinations by using AI only where judgment is required.

01

Customer Support Ticket Triager

AI reads a free-text ticket and decides its category; deterministic rules route it down the matching lane, those lanes run in parallel, and the results merge into one structured brief. The canonical classify-route-fan-out shape.

Classification Routing Parallel
02

Recipe Difficulty Analyzer

Three AI extractors read the recipe in parallel; a deterministic formula turns the counts and cook time into a difficulty score, which routes to targeted cooking advice. AI reads the prose, code does the maths.

Parallel Classification Routing
03

GitHub README Quality Report

Fetches a repository's README, runs five independent AI quality probes at once, then averages the scores deterministically and appends a coverage warning. Independent AI assessments combined by code.

Parallel Verification
04

Weather-Aware Outfit Advisor

AI reads messy live weather text into numbers and classifies the conditions; deterministic rules derive temperature band and wet/windy flags, then AI drafts outfit advice with a separate extreme-weather check.

Classification Routing Parallel
05

HackerNews Topic Brief

Runs an AI check over every story title in parallel, filters the results deterministically, lets the dominant theme pick a brief style, then summarizes in technical, business, or policy form.

Parallel Classification Routing
06

Faithful Summary

One model summarizes a source document; a second, independent model checks that every claim is grounded in the source. The clearest demonstration of an independent model as a quality gate against hallucination.

Cross-model Verification
07

Local MCP — Google Search & Per-URL Screenshots

Drives a real local browser: one session searches Google and pulls the first three result URLs, then three parallel sessions each open a URL and capture a screenshot. Tool use with session continuity and fan-out.

Tool use Parallel
08

Remote MCP — Cloudflare Docs Search

Calls a public remote documentation-search tool over HTTP — no subprocess, no API keys. Shows how a remote tool endpoint becomes a single reliable step in the workflow.

Tool use Retrieval
09

Stock Analyzer — zero custom ops

A full live-data workflow built entirely from pre-built steps — no custom code. Fetches market data in parallel, parses it, computes the change deterministically, and scores headline sentiment with AI before assembling the analysis.

Parallel Classification
10

RAG (BM25) — local knowledge base with citations

Answers a question from a local knowledge base, asks the model to cite its sources, then deterministically filters every citation against the documents actually retrieved — hallucinated sources can't survive.

Retrieval Verification
11

RAG (Gemini embeddings) — vector similarity

The same retrieval workflow as the previous example, with the retriever swapped to vector similarity over embeddings — the rest of the process is untouched. Shows how the retrieval backend is pluggable without changing the workflow.

Retrieval Verification
12

WithRepair — AI-assisted recovery

A two-stage pipeline where malformed input and a broken business rule are each detected and repaired by a bounded second AI pass — automatically, without failing the run. Deterministic detection, AI recovery.

Verification Recovery
Browse all examples on GitHub