Jake Diego.

Systems I've built

A working sample of the operational software built for one customer success team. The flagship systems are the most substantial builds: where an outcome was measured it is shown and traceable to a logged figure, and the rest describe the capability that shipped. A second set runs in daily use but has no published measured figure yet, and none is shown for those.

Flagship systems

The most substantial builds. Where an outcome was measured, the figure is shown and traces to a logged measurement; the others describe the capability that shipped, with no measurement implied.

Customer success command center

A live dashboard for tracking customer health, at risk flags, renewals, and team workload in one place, replacing scattered spreadsheets.

33 at risk customers tracked to an outcome (20 retained, 5 churned, 8 open)
Python, a lightweight web dashboard, spreadsheet backed data model

Read the full case study →

Market intelligence pipeline

An automated research pipeline that collects public market data on a schedule, scores it for growth signal, and hands back a ranked opportunity report, no manual pull required.

4-stage pipeline: collection, scoring, synthesis, ranked output
Python, public API scraping, SQLite, spreadsheet export

Read the full case study →

AI visibility audit (AEO / GEO)

A structured, multistage audit of how well a site is positioned to be found, trusted, and quoted by AI answer engines, run on this very site: it found the machine readable gaps and shipped the fixes.

Six stage audit: 4 domain passes, 2 validations, 2 expert debate rounds, GO verdict
Multiagent audit pipeline, schema.org / JSON LD, robots.txt and sitemap, FAQ and comparison content

Read the full case study →

Email drafting with voice calibration

Drafts outbound customer emails automatically, then learns from a person's edits so the drafts converge on their actual writing voice over time.

Measured 45.9% run time reduction on the drafting pipeline (measured in testing; live confirmation pending)
Python, a calibration loop, prompt based drafting
Editing effort per batch Loop 1 Loop 6 converged

Editing effort per batch fell toward zero across six calibration rounds as the drafts learned the writer's voice.

Value / ROI engine

An internal accounting layer that credits the customer success system with the revenue it actually retains, so the team's impact is a number, not a narrative.

$30,321 in retained revenue credited to the workflow (20 retained customers)
Python, a spreadsheet backed ledger, event sourcing

See the outcome breakdown →

Price history tracker

Built for a small coffee roaster whose supplier sends a new price sheet every couple of weeks, each one a standalone spreadsheet with no memory of the last one. Stitches every sheet into one running, item level price history that updates itself.

5+ items tracked across every price run, refreshed with one click
Spreadsheet native data pipeline, folder based ingestion, auto date stamping

See the project →

Data entry / form fill automation

Automates a repetitive multifield data entry task that previously required manual copy paste across systems.

Measured 73% time reduction on the form fill step (measured in testing; live confirmation pending)
Python, browser automation, a dry run verification harness
Manual form fill, per record 9.46 s
Automated form fill, per record 2.53 s
▼ 73% faster, measured in testing

Video to documentation pipeline

Takes one monthly walkthrough recording and turns it into a full set of polished, branded release documents automatically.

4 deliverables generated per release: detailed guide, interactive guide, a reassign strategies guide, and a poster
Python, transcript extraction, templated document generation

Read the full case study →

Workshop

Built and in daily use. These run every day, but none carries a published measured impact figure yet.

AI customer service agent

A chat agent that lives where customers already are (starting with Discord) and runs the whole front line of customer service. It walks new customers through onboarding step by step, answers support questions instantly from a maintained knowledge base, points people to the right channel or resource, and hands off cleanly to a human when a question needs one.

Onboarding, support, and everyday customer service in one agent, backed by a maintained knowledge base
Python, a knowledge base index, chat platform integration (Discord today, extendable to others)

Support hub SOP library

A structured library of standard operating procedures and quick start reference cards, one per support channel, so new team members and customers get consistent answers.

18+ channel quick start cards plus a full SOP set
Markdown based docs pipeline, a validation gate before publishing

Personal knowledge wiki

A searchable internal wiki that organizes reference material into a browsable, linked knowledge base instead of scattered notes and documents.

Replaced scattered notes and loose documents with one linked, searchable reference base
Static site generation, linked markdown pages

Screen recorder app

A lightweight native screen recorder, built as a simpler, faster alternative to general purpose recording tools for quick walkthroughs.

A lighter, faster alternative to general purpose recorders for quick walkthroughs
Native desktop app

Skill / automation framework

A framework for turning a manual process, once it's been done a few times by hand, into a repeatable, validated automated skill.

Turns a proven manual process into a gated, self running skill
Modular task specs, a validation gate for each new automated skill
Manual process
done by hand, a few times
Validated pattern
steps confirmed repeatable
Automated skill
runs itself, gated before shipping
Free systems audit

See what any of this would look like for your business

Walk me through the manual process that eats the most of your team's week. In a free 30 minute audit I'll tell you honestly whether software can fix it, what I'd build, and what it would cost. No obligation, and every project ships with a measured before/after. I reply to every audit request within two business days.

Request the free audit →