1:1 Prep Briefs from Live Engineering Signals
Category: Engineering / People Ops
Tools Used
- Claude
- Slack MCP
- GitHub MCP
- Confluence (Atlassian MCP)
- Google Drive MCP
Role
Engineering Manager / Director of Engineering
Time Saved
2–3 hours/week across a typical 1:1 schedule of 6–10 reports
Automatically synthesizes Slack activity, GitHub output, Confluence pages, and Google Drive into a structured pre-meeting brief for each direct report — so every 1:1 starts from current facts, not memory.
The Problem
Engineering managers carry context on 6–10 direct reports simultaneously, but that context goes stale fast. By the time a 1:1 arrives, you're working from memory or skimming Slack for 20 minutes right before the call. The signals are all there — recent PRs, active threads, Confluence pages authored, OKR updates — but they're scattered across four tools with no unified view. The result is 1:1s that are reactive and generic instead of specific and high-value.
How It Works
Before each 1:1, give Claude the person's name and ask for a pre-meeting brief. Claude runs the following in parallel:
- Slack — looks up the person's user ID, then searches their recent messages across public and private channels to identify active workstreams, blockers they've flagged, cross-team asks, and tone/engagement signals.
- GitHub — searches recent PRs authored or reviewed by the person, noting merge status, PR descriptions, open review age, and any notable comments. Surfaces whether output has been landing or stacking up.
- Confluence — searches pages the person has authored or been mentioned in recently; surfaces design docs, sprint updates, or technical proposals worth discussing.
- Google Drive — searches for documents they own or have recently edited; useful for goal docs, PDP progress, or project specs that aren't in Confluence.
Claude synthesizes all four sources into a structured brief: team/role context, what they've been doing this week (Slack signals), what they've shipped recently (GitHub), longer-form artifacts (Confluence/Drive), and 4–5 specific suggested 1:1 topics ranked by importance — including open questions, potential blockers, and anything that looks like it deserves a direct conversation.