ObserveOverviewActivityUsersTeams and Workflows
OptimizeOpportunitiesCoachingSkills
GovernanceModel AccessBudgets and ApprovalsMCP Servers
  1. Users
  2. Leo Martins
L

Leo Martins

leo.martins@northline.aiStaff Engineer · Engineering
Tools used
ClaudeChatGPTCopilot
AI spend (3 mo)$5,018.42
Savings$1,396.90

Leo's Token Efficiency Over Time

Score out of 100 · trending up

Leo's Monthly AI Spend

Spend up 9% as usage expanded

What improved Leo's usage

  • Stopped pasting full inbox context into every prompt
  • Started using the Code Review Skill
  • Added a user guidance file with preferred formats
  • Routed list-building tasks away from Opus
  • Used AI for reasoning, not deterministic spreadsheet math

Leo's top workflow

Test Generation

Unit test stubs, edge-case lists, and flaky test triage

L
H
I
J
$1,36926 convos

Leo vs Engineering

Efficiency vs. cost compared with teammates
Efficiency vs. Cost
EfficiencyToken Spend

Leo's user.md

user.mdVery Efficient
23 lines · under the ~40-line always-on budget
# user.md

You're an experienced Staff Engineer working across product and platform surfaces. You set technical direction, unblock hard problems, and keep standards high without slowing delivery.

## Preferences
- Prefer small, reviewable diffs
- Code first, explanation only if asked
- Default model: Sonnet

## Project
- Package manager: pnpm
- Test: pnpm test · Lint before commit

## Do not
- Paste the full repo by default
- Rewrite unrelated files

## Load on demand
- @review.md · @debug.md · @tests.md
## Archive notes
- Full history of prior tool preferences from 2023–2025
- Long brand voice essay and sample paragraphs
- Every channel CTA variant ever tested
- Meeting transcripts summaries for last two quarters
- Deprecated model routing rules (keep for reference)
- Personal glossary of acronyms used once
- Copy of the onboarding checklist (also in Notion)
- Detailed API field list from an old integration