Memory Management Decoding User Input Tiered Lookup

Decoding User Input (Tiered Lookup) (+3)

Decoding User Input (Tiered Lookup)

Always decode shorthand before acting on requests:

1. AGENTS.md (hot cache)     → Check first, covers 90% of cases
2. memory/glossary.md        → Full glossary if not in hot cache
3. memory/people/, projects/ → Rich detail when needed
4. Ask user                  → Unknown term? Learn it.

Example:

User: "ask todd to do the PSR for oracle"

AGENTS.md lookup:
  "todd" → Todd Martinez, Finance ✓
  "PSR" → Pipeline Status Report ✓
  "oracle" → (not in hot cache)

memory/glossary.md lookup:
  "oracle" → Oracle Systems deal ($2.3M) ✓

Now Codex can act with full context.

Adding Memory

When user says "remember this" or "X means Y":

1. Glossary items (acronyms, terms, shorthand):

   • Add to memory/glossary.md
   • If frequently used, add to AGENTS.md Quick Glossary

2. People:

   • Create/update memory/people/{name}.md
   • Add to AGENTS.md Key People if important
   • Capture nicknames - critical for decoding

3. Projects:

   • Create/update memory/projects/{name}.md
   • Add to AGENTS.md Active Projects if current
   • Capture codenames - "Phoenix", "the migration", etc.

4. Preferences: Add to AGENTS.md Preferences section

Recalling Memory

When user asks "who is X" or "what does X mean":

1. Check AGENTS.md first
2. Check memory/ for full detail
3. If not found: "I don't know what X means yet. Can you tell me?"

Progressive Disclosure

1. Load AGENTS.md for quick parsing of any request
2. Dive into memory/ when you need full context for execution
3. Example: drafting an email to todd about the PSR
   • AGENTS.md tells you Todd = Todd Martinez, PSR = Pipeline Status Report
   • memory/people/todd-martinez.md tells you he prefers Slack, is direct