Skip to main content
Memory is freeform notes Swan keeps around across conversations — the place for context that doesn’t fit a structured field in org knowledge, like a standing preference, a fact someone told Swan in passing, or a nuance about how to handle a particular account. Swan writes to memory itself as it learns things from you; you can also read and edit it directly. There are three levels:
  • Org memory — durable facts and preferences that apply to the whole organization (e.g. “never mention pricing before a demo is booked”). Org memory is loaded into every conversation automatically. Writing to it is Admin-only. Where: the Org tab at agent.getswan.com/memory.
  • User memory — your own personal preferences and notes (e.g. how you like emails written, your calendar habits). Only you can write to your user memory, and it’s loaded into your own conversations. Where: the Personal tab at agent.getswan.com/memory.
  • Company memory — account-specific context tied to a single company (e.g. “this account had a bad support experience in 2024, mention carefully”). Swan reads and updates company memory when it’s actively working on that account, rather than loading it into every conversation by default. Where: the memory card on that company’s page (https://agent.getswan.com/companies/{companyId}), or the full-page view at https://agent.getswan.com/companies/{companyId}/memory.

​
The 2,500-character cap

Each memory — one per org, per user, per company — is a single document capped at 2,500 characters of plain text. Markdown formatting (headers, bold, bullet points) doesn’t count against the cap, so you’re free to structure a memory for readability without it eating into your budget. When you ask Swan to check a memory’s status, it reports how much capacity is used. Once a memory crosses roughly 70% full, Swan flags it and will consolidate or trim it before adding more — collapsing redundant notes, dropping stale information, tightening phrasing — so you don’t lose new information to a hard limit. If an edit would push a memory over the cap, the write is rejected rather than silently truncated.

​
Versioning and restore

Every update to a memory is versioned, with a short summary of what changed and who (or what) changed it. If an edit goes wrong or removes something you wanted to keep, a prior version can be restored.

​
Memory vs. org knowledge vs. skills

  • Org knowledge is structured (value prop, competition, ICP segments) and drives how Swan researches and writes outreach at a category level.
  • Memory is unstructured — a running set of notes at the org, user, or company level.
  • Skills are instructions for how to do something, not facts to remember. See skills.
If you’re not sure where a piece of context belongs: a fact (“this account renews in March”) goes in memory; a fixed field about your business (target market, competitors) goes in org knowledge; a procedure (“when qualifying a lead, always check X before Y”) is a skill.

​
Common questions

Who can see company memory? Anyone in your org working with Swan on that account can read it, the same way any other Swan data is scoped to your org. Can I edit a memory directly instead of asking Swan to? Yes — you can open a memory and edit the text yourself at agent.getswan.com/memory (or, for a company, its memory card/page); Swan also writes to it conversationally as it learns things. What happens if my memory is already full and I need to add something important? Ask Swan to consolidate it first — it will tighten existing notes to free up space — or manually trim less important content before adding the new note. Does org memory apply to every user in the org, or just Admins? Every user’s conversations load org memory as context; only Admins can write to it. Is there a memory for individual contacts, separate from companies? The memory levels exposed to you are org, user, and company — there’s no separate per-contact memory tier. Can I see the version history of a memory? Yes, past versions are kept and can be restored if needed.