How is this different from comments in our spreadsheets?

Spreadsheet comments are buried and easy to miss. Glen gives agents memory they retrieve and write automatically in one MCP call, so the relevant assumption or caveat surfaces in context while the agent analyzes or drafts.

Does the whole finance team share one memory?

Yes. Glen is org-shared, so every team member's agents read and write the same store. A definition or caveat one analyst records is immediately applied by everyone else's agents, keeping the numbers and the narrative consistent.

Shared memory for finance teams

Finance teams run on context that rarely lives in the numbers themselves: why a forecast assumption changed, which accrual is one-time versus recurring, how a metric is defined for the board versus internally, the reason a variance looked alarming but was benign. That knowledge sits in the head of whoever built the model, in cell comments, and in email threads, so when the close comes around or someone inherits the model, it all has to be reconstructed. As finance teams adopt AI agents to analyze spend, draft commentary, or reconcile data, those agents have none of that institutional context and produce analysis that is technically correct and practically misleading. Glen, shared memory for AI agents, gives those agents a durable, team-shared memory through a single MCP tool that retrieves the relevant context and records new findings in one round trip.

Connect Glen to the agents your finance team uses, a spend-analysis assistant, a reporting commentary drafter, a reconciliation helper, and each gets one tool that reads the relevant context and writes back what it learned. Before an agent explains a variance, it pulls what the team already knows: that a vendor's invoice timing shifts the monthly trend, that a metric excludes a particular cost center, that last quarter's spike was a one-time true-up. After it produces analysis, it records the assumption and the caveat it relied on so the next month's close and the next analyst inherit a consistent basis. You stop re-deriving the same definitions and stop shipping commentary that contradicts last quarter's.

The key change is that financial context becomes shared and durable rather than trapped in one person's model and memory. Glen is org-scoped, so the memory spans every member of the finance team and every agent they use. One analyst's agent records that a specific line item is non-recurring; every other agent treats it consistently, so reports reconcile and the board sees one story. Because Glen is a standard MCP server, the same memory is readable from any MCP client, so a spend-analysis agent, a commentary drafter, and a reconciliation assistant all draw on one consistent record of how your finances are defined and explained. Wire it in once over OAuth or an API key and let your team's financial context compound instead of being rebuilt every close.

FAQ

How is this different from comments in our spreadsheets?: Spreadsheet comments are buried and easy to miss. Glen gives agents memory they retrieve and write automatically in one MCP call, so the relevant assumption or caveat surfaces in context while the agent analyzes or drafts.
Does the whole finance team share one memory?: Yes. Glen is org-shared, so every team member's agents read and write the same store. A definition or caveat one analyst records is immediately applied by everyone else's agents, keeping the numbers and the narrative consistent.