G2 - Build Always-On PEAK Performance Review Evidence Bank

Performance review self-assessments require recalling six to twelve months of work, but the evidence lives scattered across Asana, Slack, Gmail, meeting notes, Jira and Confluence. Most people write their review from memory in a single painful weekend, under-claim their own impact, and lose credit for real work — especially quantified outcomes that were never captured when they happened. By review season, the numbers that would make the strongest case are unrecoverable.

1. Download the attached setup kit and gather the eight inputs listed in its Part 1: exact job title, one-sentence mandate, Slack member ID, task-tracker project IDs, priority channels, Jira/Confluence spaces if used, meeting-notes tool, and the 2–4 flagship stories of the year so far.

2. Create a folder on your computer, create a Claude Cowork project connected to it, and connect the connectors you actually use (Asana, Slack, Gmail, Google Calendar, Atlassian, Granola or Zoom).

3. Fill in the placeholders in the kit's project-instructions template and paste it into the project's instructions. The template defines the review framework and weightings, the review period, each source's search parameters, and the guardrail "flag, don't fabricate — never invent tasks, quotes or metrics."

4. Paste the kit's single bootstrap prompt into your first conversation. It tests every connector, creates the two system-of-record files (an append-only Evidence_Log.md and a STATE.md for scan anchors and open items), runs the baseline scan across the whole review period, generates the first evidence bank document plus a metrics tracker, and reports your three biggest evidence gaps. If — and only if — every check passed, it then creates the daily scheduled scan itself; approve the one permission prompt and setup is finished. If a connector failed, it names the fix and waits instead of automating a broken config.

5. Let the daily task append new evidence with source citations and value tags from there on. Say "refresh" around the 1st of each month to fold the log into the formatted evidence bank, with new items tagged [NEW].

6. Watch the metrics tracker monthly: close or consciously drop any row still empty as the review window approaches, while there's still time to capture the number.

Setup is one pasted prompt and roughly thirty minutes; after that the system runs itself. The self-assessment gets written from a stocked, source-cited evidence bank instead of memory — months of work that would otherwise be forgotten is captured the day it happens, with the metrics attached, and review-season prep drops from days of archaeology to a drafting session. The system also transfers: the same kit has been adopted by other team members running their own copies for the same review cycle.

Start from the attached setup kit rather than building from scratch — it contains the full project-instructions template, the bootstrap prompt, and the lessons from six months of running the system.

Note the deliberate gate in the bootstrap prompt: the daily scheduled task is only created if the connector tests and baseline scan pass cleanly, because a daily automation that fails silently is worse than none. Dedupe everything by stable source IDs (Asana task gid, Slack permalink, Jira key, Gmail thread ID) so daily scans never double-log. Pick one source as the chronology anchor — task-tracker completion dates work; Slack timestamps are unreliable. Keep the append-only log separate from the generated document so automation can never corrupt the deliverable. Anchor every scan window to the log's most recent entry rather than a fixed date. Log connector failures as their own entries instead of silently skipping a source. Tag items added since the last document build as [NEW] so review-prep sessions focus on what changed.

Requires the relevant connectors (Asana, Slack, Gmail, calendar, meeting notes) to be authorised, and a scan can silently under-collect when a connector is down — which is why failures are logged rather than skipped, and why the daily automation is only created once checks pass. Scheduled tasks run while the Claude desktop app is open and catch up on next launch, so a machine that stays shut for a week scans nothing until it reopens. The framework, channels and search parameters are company- and role-specific and need adapting before reuse. Evidence quality depends on work leaving traces in tools: undocumented meetings and hallway decisions never enter the log. Daily scans need tightly scoped search parameters or they get slow and noisy.