The AI-Engineer Growth Framework weekly rhythm for the Techies engineering team: developers submit a changelog and self-set targets, Claude Code audits GitHub to quantify performance, and achievement is tracked against target — all aligned to our AI-oriented SDLC.
What we are proposing and why.
Each developer submits a short weekly report combining a narrative changelog and self-set targets with a % achievement. In parallel, Claude Code automatically audits GitHub to produce objective metrics across all four Techies Pulse categories (productivity, quality, AI adoption, delivery). The developer's self-report and the machine audit sit side by side, giving us a fast, fair, weekly read on performance that is hard to game and cheap to run.
Changelog + targets + claimed % achievement. Owned by the developer.
Claude Code reads GitHub and quantifies the same period objectively.
Manager compares the two, coaches on the gap, rolls up a team view.
A repeatable five-step loop, every week.
A lightweight Markdown template, committed to the repo so it is versioned and visible.
WEEKLY-REPORT.md# Weekly Report — [Name] — Week of [YYYY-MM-DD] ## 1. Targets set this week - [ ] Target 1: ... - [ ] Target 2: ... - [ ] Target 3: ... ## 2. Changelog (what shipped) - Feature/fix: ... (PR #__) - Feature/fix: ... (PR #__) - Refactor / AI-assisted: ... (PR #__) ## 3. Blockers & risks - ... ## 4. AI usage notes - Where Claude Code helped / where it didn't ... ## 5. Self-rated achievement - Overall: __ % (rationale: ...)
Format proposed: Markdown for the narrative + an Excel tracker (Component C) for the numbers. Both can be generated as starter files once approved.
An automated weekly read of GitHub that quantifies each developer across all Techies Pulse measurement areas — approved and in rollout.
/weekly-audit) runs against the GitHub repos for a given author and date range.| Category | Auto-pulled from GitHub |
|---|---|
| Productivity & velocity | Merged PRs, cycle time, median PR size, time-to-first-review |
| Code quality | Change failure rate, review pass rate, reverts/hotfixes, rework within 21 days |
| AI adoption | % of PRs flagged AI-assisted, CLAUDE.md / shared prompt contributions |
| Delivery & reliability | Deploy frequency, lead time, CI pass rate, MTTR on linked incidents |
# Saved as a Claude Code slash command: /weekly-audit
Audit GitHub activity for AUTHOR=[username] over the last 7 days
(REPO=[org/repo...]). For that window, compute and report:
Productivity : merged PRs, median cycle time, median PR size, time-to-first-review
Quality : change-failure rate, review pass rate, reverts, 21-day rework
AI adoption : % AI-assisted PRs (by label), CLAUDE.md / prompt contributions
Delivery : deploy frequency, lead time, CI pass rate, MTTR (linked incidents)
Output a one-page scorecard table: metric | this week | target | % to target | trend.
Flag any metric >20% off target. Do not infer effort from commit count or LOC.
Devs and manager run /weekly-audit manually each Friday. Simplest; no infra. Recommended to start.
A recurring weekly task runs the Pulse audit automatically and posts the scorecard. More automated; set up after the command is proven.
An Excel tracker where each developer sets weekly targets and achievement is calculated against the audited result.
| Column | Source | Example |
|---|---|---|
| Metric / target | Dev sets Monday | Cycle time < 2 days |
| Target value | Dev | 2.0 |
| Actual (audited) | Claude Code audit | 2.4 |
| % achievement | Auto-formula | 83% |
| Self-rated % | Dev | 90% |
| Gap / note | Manager | Reviews slow mid-week |
% achievement auto-calculates from target vs audited actual, so the number is objective. The self-rated column captures the developer's own view; the gap between the two is the coaching signal.
Illustrative output of the audit + tracker for one developer. Numbers are placeholders.
| Metric | This week | Target | % to target | Trend |
|---|---|---|---|---|
| Merged PRs | 6 | 5 | 120% | ▲ |
| Cycle time (days) | 2.4 | 2.0 | 83% | ▼ |
| Change failure rate | 10% | <15% | on target | ▲ |
| Review pass rate | 78% | 85% | 92% | — |
| AI-assisted PRs | 67% | growth | ▲ vs last wk | ▲ |
| CI pass rate | 88% | 90% | 98% | ▲ |
| Self-rated achievement: 90% · Audited composite: ~88% · Gap: small, well-calibrated | ||||
Sets targets Mon · records changelog · submits Fri · runs self-audit · self-rates % achievement.
Runs consolidated team audit · compares self-report vs audit · coaches on gaps · maintains team rollup.
Receive the rolled-up trend · approve targets and weightings · use the data for review cycles, not weekly policing.
Approved rollout plan — now in progress.
| Item | Options | Approved approach |
|---|---|---|
| GitHub audit access | Read scope, who holds the connection | Read-only, manager-held to start |
| Automation level | On-demand command vs scheduled job | Start on-demand, schedule later |
| Targets & weights | Per the Techies Pulse policy weights | Baseline 4 weeks before grading |
| Use of the data | Coaching vs formal review | Coaching first; formal at quarter |
WEEKLY-REPORT.md template and the Excel tracker./weekly-audit Claude Code command on one repo.