All docs

Practice guide: agent runtime files at a glance

My agents in a workspace have runtime materials on the server (you edit them on Web pages; you do not hunt disk paths). The table uses UI names first; implementation filenames are

Source help/en/guides/runtime-files-map.md

In user language: My agents in a workspace have runtime materials on the server (you edit them on Web pages; you do not hunt disk paths). The table uses UI names first; implementation filenames are in parentheses for interop and troubleshooting.

Overview table

User-facing nameImplementation file (relative to that agent)Where to maintainRough role in chat
PersonaSOUL.mdAgents → PersonaTone, stance, brevity, expression boundaries; high priority
Operating rulesAGENTS.mdAgents → Operating rulesHow to do it: steps, tool/skill constraints, how to compute dates
End-user profileUSER.mdAgents → Memory page topWho you are: how to address you, stable background (optional)
Long-term memoryMEMORY.md + memory/entries/*.mdAgents → Memory entries; or Messages Remember; can correct/delete in chatPreferences, decisions, project milestones, where to look — across conversations
Tidy logmemory/.maintain/log.jsonlAgents → MemoryAuto-tidy logChange notes from nightly/manual tidy (read-only)
Daily notesmemory/YYYY-MM-DD.mdSame (pick “daily note”) or system auto-archiveTemporary progress in recent days
TasksTASKS.mdAgents → TasksTo-dos, goals, drafts; excerpts injected in chat
Agent knowledge baseknowledge/*.mdAgents → Knowledge baseRole metrics, business notes; retrieve related articles by question
Workspace knowledge baseWorkspace-side directoryWorkspace collaboration → Manage workspace knowledgeTeam-shared policy, process, background
SkillsWorkspace Skills Center (DB)Skills CenterRepeat an operation by steps (APIs, scripts), not background knowledge
Available data and skillsAgent config (config_json)Agents → Overview → Available data and skillsLimit or prefer this agent’s data connections and workspace skills (does not expand member grants)

The help agent has none of these personal runtime files; it reads the system knowledge base (this help/ / help/en/ tree).

Assembly order in chat (simplified)

System-side material sent to the model roughly stacks in this order (earlier ≈ harder constraint):

  1. Base system prompt
  2. Persona (SOUL.md)
  3. Operating rules (AGENTS.md)
  4. User profile (USER.md, if any)
  5. Memory (long-term list + a few related full entries + today/yesterday daily-note excerpts)
  6. Task excerpts (if any)
  7. Retrieved knowledge base / skill snippets
  8. Current conversation messages

So: do not invent APIs as an execution constraint belongs in operating rules (plus the skill body), not in memory or persona alone.

What each file should and should not say

Persona (SOUL.md)

Write: how to speak (brief/formal/conclusion then steps), attitude to the user, which topics to treat carefully, term habits. Do not write: concrete API paths, relative-date formulas, one-off facts that only apply to you.

Operating rules (AGENTS.md)

Write: which tool first, how to compute date ranges, what to ask when a parameter is missing, only APIs declared in skills, how to explain failure to the user. Do not write: humor style, long business background (put that in the knowledge base).

User profile (USER.md)

Write: stable identity — “I am finance, I do not read code”, “call me Xiao Li”. Do not write: changing project progress (use memory · project progress or daily notes), team-wide policy (use workspace knowledge).

Long-term memory (MEMORY.md index + entries)

Write: your personal preferences and corrections, confirmed decisions, personal project milestones, personal “where to look”. Do not write: team-wide metrics (workspace knowledge), agent role setup (agent knowledge), steps that must run every time (operating rules).

See USER.md and memory: templates and split.

Daily notes

Write: what you are doing today, this round’s temporary conclusions. Do not write: preferences that should last (promote to long-term memory).

Tasks (TASKS.md)

Write: to-do lists, stage goals, draft outlines you noted yourself. Do not write: finished stable decisions (those belong in long-term memory or the knowledge base).

Knowledge base vs skills

Knowledge baseSkills
Answers“What / why / what the metric is”“In what order to call APIs, where parameters come from”
Typical contentPolicy, product notes, FAQhttp_request steps, scripts, templates
Maintain entryWorkspace / agent Knowledge baseSkills Center

Next