Work
Selected systems we’ve engineered.
Case files rather than a portfolio: the problem, the architecture, the decisions, and what was achieved.
01 Featured case fileAI Systems & Automation
Multimodal AI Sales Funnel
One system that passes through five of the six layers: messaging APIs, multimodal AI, retrieval over real product data, automation logic, and a human handoff.
An end-to-end sales funnel for a crypto-mining hardware enterprise: Instagram and WhatsApp leads qualified, answered from a catalog of 500+ ASIC miners, scored, and handed to sales.
Enters through01AI Systems & Automation
Read the case file- 1Instagram DMsAPIs
- 2Lead qualificationAutomation
- 3WhatsAppAPIs
- 4Multimodal AI (text, voice notes, images)AI
- 5Product knowledge retrievalData
- 6Lead scoringAutomation
- 7Human sales handoffApplication
- 8Automated follow-up or cold-lead archivingAutomation
02 Engineering range
Engineering range
Each project marked on the layers it worked in, foundation first. Two are data and infrastructure work with no AI in them; that is the point.
| Case file | Data | Infrastructure | APIs | AI | Automation | Application |
|---|---|---|---|---|---|---|
| Multimodal AI Sales Funnel | worked in this layer | no | worked in this layer | worked in this layer | worked in this layer | worked in this layer |
| AI Website Audit & Outreach Engine | worked in this layer | no | worked in this layer | worked in this layer | worked in this layer | no |
| 5 TB Zero-Downtime MySQL Migration | worked in this layer | worked in this layer | no | no | no | no |
| Enterprise Data Query Architecture | worked in this layer | worked in this layer | worked in this layer | no | no | worked in this layer |
| Voice AI Systems | worked in this layer | no | worked in this layer | worked in this layer | worked in this layer | worked in this layer |
- worked in this layer
- 01Data
- 02Infrastructure
- 03APIs
- 04AI
- 05Automation
- 06Application
03 Case files
Case files
Five systems, each entering through one service pillar and reaching into others. The capability case documents a class of system rather than a single client project, and says so.
Multimodal AI Sales Funnel
An end-to-end sales funnel for a crypto-mining hardware enterprise: Instagram and WhatsApp leads qualified, answered from a catalog of 500+ ASIC miners, scored, and handed to sales.
Verified factAirtable-backed catalog of 500+ ASIC miners
- 1Instagram DMsAPIs
- 2Lead qualificationAutomation
- 3WhatsAppAPIs
- 4Multimodal AI (text, voice notes, images)AI
- 5Product knowledge retrievalData
- 6Lead scoringAutomation
- 7Human sales handoffApplication
- 8Automated follow-up or cold-lead archivingAutomation
AI Website Audit & Outreach Engine
An automated pipeline from a list of target URLs to personalized, segmented outreach: crawling, contact extraction, PageSpeed analysis, LLM-written messages, and automated follow-ups.
Verified factEvery message grounded in a Google PageSpeed audit of the prospect’s site
- 1Target URLsData
- 2Crawling and contact/social extractionData
- 3Google PageSpeed APIAPIs
- 4Technical analysisAI
- 5LLM-generated personalized outreachAI
- 6SegmentationAutomation
- 7Automated follow-upsAutomation
5 TB Zero-Downtime MySQL Migration
A 24/7 production system on legacy MySQL 5.7 with roughly 5 TB of data, moved to a modern MySQL environment by replication with no service interruption at cutover.
Verified factApproximately 5 TB, zero service interruption at cutover
- 1Compatibility audit of MySQL 5.7 workloadData
- 2Deprecated variable remediationInfrastructure
- 3Replica build and synchronizationInfrastructure
- 4Replica promotion at cutoverInfrastructure
- 5Query modernization with CTEsData
Enterprise Data Query Architecture
Query architectures for analytical workloads across data platforms and data lakes, using distributed and embedded engines over Azure Data Lake storage.
- 1lake storageData
- 2query enginesInfrastructure
- 3federationAPIs
- 4analyticsApplication
Voice AI Systems
Voice systems on real telephony: AI receptionists, inbound support, outbound qualification, appointment booking, and CRM-integrated calling, with transcription, call analysis, and escalation to people.
- 1Telephony: inbound or outbound callAPIs
- 2Speech recognitionAI
- 3LLM conversation logicAI
- 4Tools and CRM actionsAutomation
- 5Speech synthesisAI
- 6Transcription and call analysisData
- 7Escalation and human transferApplication
04 Discuss a project
Have a system like one of these, or one that does not exist yet?
Describe the problem and the systems around it. If the answer is a workflow, a pipeline, a migration, an agent, or an application, that is the work we do.