david.delagneau/fidelity-ai-workspace
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: Enhance learning session guidelines to prioritize durable understanding and high-leverage questioning

Browse Source
This commit is contained in:
David Delagneau
2026-04-17 08:48:57 -06:00
parent 68f693c04e
commit e604115335
7 changed files with 44 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

20
vault/03-context/process/agent-memory-rules.md
View File

@@ -38,12 +38,16 @@ The agent should support incremental self-learning sessions.
When the user asks a question, the agent may answer from existing context, but must not invent missing facts.
Learning sessions should improve durable project understanding. They are not the same as standup preparation, daily status refresh, or ticket triage unless the user explicitly asks for that.
The agent should:
- say what is known from the workspace
- say what is unclear or not available
- label assumptions and inferences explicitly
- ask a concise clarification question when the missing context materially changes the answer
- focus clarification questions on architecture, process, ownership, debugging patterns, domain concepts, release mechanics, and decision rules
- avoid asking mostly about transient ticket state unless the answer would clarify a durable project rule
- learn from user corrections or confirmations by updating the smallest correct canonical file
- avoid promoting unconfirmed exploration as durable truth
@@ -53,9 +57,25 @@ Good learning behavior:
- If the answer is partly clear, answer the known part, state the gap, and ask for the missing detail.
- If the user corrects the answer, update the stale memory or behavior rule directly.
- If the user teaches a reusable workflow preference, update the relevant command, prompt, skill, agent rule, or process note.
- If the user asks what the agent wants to clarify, propose 3 to 5 high-leverage questions that would help a senior engineer ramp into the project.
Do not ask for clarification just to avoid work. Ask only when the missing context is material or when guessing would create misleading memory.
Avoid low-value learning-session questions such as:
- whether a specific PR was approved today
- whether a ticket moved columns today
- what the next standup line should be
- temporary sequencing questions that belong in `vault/01-current/` or `vault/06-daily/`
Prefer high-value questions such as:
- what determines ownership between SDK, adapter, feature module, app, and backend configuration
- how release propagation works across SDK, adapter, consuming app, and validation environment
- what invariants define REST vs GraphQL parity
- how authenticated and non-authenticated flows differ operationally
- what evidence is required before classifying an external issue as a regression
---
## What Counts As Memory-Worthy

3
vault/03-context/process/context-maintenance.md
View File

@@ -38,6 +38,9 @@ Keep this workspace useful as living memory instead of a pile of disconnected no
## Ingestion Rules
- Treat Mattermost, Slack history, and direct prompts as potential memory sources.
- Treat learning sessions as durable-understanding sessions, not status refreshes.
- In learning sessions, prioritize architecture, ownership, release mechanics, debugging strategy, domain concepts, and process rules.
- Avoid promoting transient ticket status from learning sessions unless it exposes a reusable rule.
- Do not promote failed syncs or tooling errors as project facts.
- Promote repeated durable patterns from historical archives into stable context when confidence is high.
- Keep old status-only details archive-only unless they still change current understanding.