Case studies

Workflows we built, in detail.

Anonymized engagements: what was broken, the platforms we wired together, how the build ran, and the numbers before and after. Client names withheld, everything else is what happened.

01 B2B SaaS Model Context ProtocolZendeskSalesforcePostgreSQLTypeScript MCP server

An MCP server that let a support agent stop reading and start acting

A B2B SaaS company had a support copilot that could summarize a ticket beautifully and do nothing about it. Every action still went through a human copying values between Zendesk, Salesforce, and an internal Postgres database. We designed and shipped an MCP server that gave the agent scoped, audited tools, and tier-1 resolution went from advisory to autonomous.

62% of tier-1 tickets now closed by the agent without a human touching them Read the build →
02 Manufacturing and distribution SalesforceNetSuiteTemporalPostgreSQLTypeScript services

A NetSuite and Salesforce sync that survived quarter-end

A distributor closed deals in Salesforce and fulfilled them in NetSuite, with a person in the middle rekeying every order. Two previous integration attempts had been switched off after they silently duplicated records. We rebuilt it as a proper bidirectional sync with conflict rules, idempotent writes, and a replayable error queue, and it held through its first quarter-end.

9 hours → 4 minutes Time from a closed deal in Salesforce to a sales order live in NetSuite Read the build →
03 Retail and procurement Python extraction workersVision model for scanned tablesPostgreSQLTemporalEmail intake

A pipeline that turned 200 supplier price lists into one queryable table

A retail group received supplier pricing as PDFs, spreadsheet attachments, and portal downloads, in around 200 different formats, and three analysts spent most of a week each month turning it into something the buying team could compare. We built an ingestion pipeline that collects, extracts, normalizes, and loads it automatically, with change detection so buyers see what moved rather than a full dump.

31 hours → 20 minutes Weekly effort to get current supplier pricing into the warehouse Read the build →
04 Financial services QdrantPostgreSQLEmbedding and reranking modelsPython retrieval serviceSlack

A RAG system that answers policy questions with the paragraph it came from

An operations team of about 400 people answered customer questions by searching a 3,000-document policy library that keyword search could not navigate. A first attempt at a chatbot had been abandoned after it confidently invented a refund rule. We rebuilt it as a retrieval system with citations, an evaluation suite, and a refusal path, and it went from a demo nobody trusted to a tool the team opens by default.

8 minutes → 40 seconds Median time to find a defensible answer to a policy question Read the build →