Idea to create a blog explaining the concepts behind GitLab’s processes and approach to operations.
Must discern between docs, handbook, and internal.
Noted a quote on DRIs: they don’t owe anyone an explanation for decisions, and forcing too much explanation can derail a DRI and discourage a bias for action.
Collected a list of eight traits (e.g., detail-oriented with strategic perspective, calm under pressure, strong listener, adept at anticipating problems, resilient, consistent) relevant to this topic.
An agent uses a trained LLM to translate a prompt into an output; useful mainly for basic, direct questions.
Planning has an agent feed its own output back in as input repeatedly until a reasonable response is found, though quality degrades fast.
Planning with feedback adds action-observation loops governed by specialized prompts, but each step has no memory of the last.
Planning with feedback and memory adds short-term and long-term memory to consolidate steps, improving output quality; different memory formats (key/value, embedded, DBs) are worth considering.
Tools are external APIs (GitLab, Google Search API, code interpreters, formatters, parsers, image analysis, chart generators, static analysis) that agents can call as part of their steps.
Agent 6679 (Engineering - Core Development, Expansion) is the People-Business Partner contact for talent assessment questions, like when self evaluations are due
Reviewed definitions: Key Talent - Box 4 or more, SPOF (Single Point of Failure), SSOT (Single Source of Truth)
Found that the talent development program chart links to the wrong URL for 360 feedback
Same broken-link issue exists for the Career Development Conversations link
ryer.io