muhammad.yousaf
All work
2024 – PresentTech Lead → Project ManagerClosed-source

LeadLyft

Months of user activity turned into reports that read written-by-coach, not by-model — three AI surfaces sharing one context-bundle layer, 30+ FastAPI endpoints.

Three surfaces · One context-bundle layer

Reports, chat, insights — grounded in the same history

Three independent surfaces, one shared retrieval layer. The same context-bundle abstraction backs the report pipeline, the chat assistant, and the daily insights feed — different bundle profiles, one source of truth.

30+
API surface
3
Surfaces
1
Source of truth
Context-bundle layer · PostgreSQL
Hover a surface to see its bundle profile
Multi-step Claude pipeline

Four focused prompts, not one giant one

Shared by:MONTHLYP3·CTXP3·BEH
Step 1 of 4ContextBundle.summarise

Summarise

> prompt: Condense N months of activity into key themes

Reads the user's structured context bundle — daily check-ins, behaviour segments, rolling aggregates, prior reports. Outputs a tight thematic summary, not a draft. The job is what to write *about*, not how.

Input
  • context bundle (full)
  • report-type config
Output
  • thematic summary block
  • candidate angles
Why this step
  • One prompt that tries to summarise *and* draft does both badly. Splitting the summarisation step lets the model focus on shape before voice.
Step 1 / 4— auto-advancing · click any step to pin
After step 4 — render
MarkdownJinja2WeasyPrintPDF
PythonFastAPIPostgreSQLClaude APIReactAzure
30+
APIs shipped
3
Surfaces
1
Source of truth

Summary

A US-based behavioural-coaching SaaS was shipping charts and tables; users couldn't read their own data. LeadLyft is the AI services layer behind it — generating long-form personalised reports, a daily insights feed, and a chat assistant grounded in each user's history. Designed the architecture, built v1 end-to-end as the only engineer, then continued through the AnalyzeEQ document-intelligence module before being promoted to PM / Tech Lead. In production today with paying customer organisations.

Highlights

  • Designed the 30+ API surface across reports, chat, and insights
  • Multi-step Claude pipeline (summarise → analyse → draft → revise) per report type
  • Reusable context-bundle abstraction shared across all three surfaces
This project is closed-source (built for a Kcube AI client). I'm happy to walk through the architecture, trade-offs, and code on request.