# Draft the quarterly "what changed" memo > Ground the quarter's shifts in imported commentary, then have chat shape it into a memo your PM can forward. - For: Analyst - Category: Finance, Investing & Due Diligence - MCP tools: deep_context, chat - HTML version: https://veridive.com/mcp/use-cases/quarterly-what-changed-memo ## The problem Every quarter ends with the same deliverable: the "what changed" memo. Not what happened — what *changed*: which narratives strengthened, which assumptions broke, where management language moved, what the smart commentary now worries about that it didn't in April. It's the highest-leverage document you write and the one that gets the least time, because it lands exactly when you're most buried. The raw material is the quarter's accumulated tape — the interviews, calls and expert commentary you (ideally) collected as they happened. The memo is a synthesis problem: read ninety days of record, difference it against the prior quarter, and write it up with sources. Which is precisely the kind of work that shouldn't start from a blank page. ## How veridive MCP helps **deep_context** does the differencing: with the quarter's commentary imported and tagged in your library, scope questions across it — *"what themes emerged this quarter that weren't present before? where did management language shift?"* — and get answers **cited to the exact chunks**. The synthesis runs over what was actually said, not what you happen to remember from June. **chat** does the shaping: take the grounded findings and draft the memo in your format — the sections your PM expects, the tone your desk uses, tight. It's the no-retrieval half of the workflow: pure writing over established facts. You review, adjust judgment calls, and ship a memo where every claim has a citation — in an afternoon instead of a lost weekend. ## How to run it 1. **Connect veridive MCP** — One-time setup: add the veridive MCP server to Claude, ChatGPT, Cursor or any MCP client and generate your API key. Takes about two minutes. 2. **Difference the quarter** — Scope deep_context across this quarter's tagged imports and ask the delta questions — new themes, dead narratives, language shifts. ``` Across my library items tagged ' ': what themes emerged, what concerns faded, and where did management or expert language shift versus the '' items? Cite the chunks. ``` 3. **Pressure-test the deltas** — For each claimed shift, pull the before/after evidence — the memo's credibility lives in these pairs. ``` For each shift you found, give me the before-and-after: what was said last quarter versus this quarter, with citations for both sides. ``` 4. **Draft in your format** — Hand the findings to chat with your memo skeleton. It writes; you exercise judgment and ship. ``` Using these findings, draft the quarterly memo in this structure: . Keep every claim's citation inline. Tone: concise, desk-style. ``` ## Problems it solves - The quarter's most important memo gets written at the quarter's worst moment, from memory. - Recency bias: September's narrative overwrites July's in recall, and the memo misses the actual arc. - Before/after evidence pairs — the memo's spine — take hours to reconstruct manually. - Unsourced synthesis invites the PM's least favorite question: 'says who?' ## Why it's valuable - The differencing runs over the record, not over memory — the arc survives recency bias. - Every shift ships with its before/after citation pair; 'says who' is pre-answered. - Drafting starts from grounded findings, not a blank page — an afternoon, not a weekend. - The workflow compounds: this quarter's memo file becomes next quarter's baseline automatically. ## Example prompts ``` Across items tagged ' ': what emerged, faded, or shifted vs ''? Cited. ``` ``` Before/after quotes for each shift, both sides cited. ``` ``` Draft the memo in this structure: — citations inline, desk tone. ``` ## FAQ **What's the split between deep_context and chat here?** deep_context is the grounded half — every factual claim comes from your imported commentary with chunk citations. chat is the writing half — no retrieval, just shaping established findings into your format. Facts from one, prose from the other. **What if I didn't import commentary during the quarter?** Backfill: import the quarter's key interviews and calls now (see the earnings-triage use case for the collection habit), then run the differencing. The workflow is better fed continuously, but it works retroactively. **Can the memo cover multiple names or a whole sector?** Yes — tag imports per name and run the delta questions per tag, or across the sector tag for the thematic layer. deep_context scopes up to 20 items per question, so slice by name or theme. ## Related use cases - [Triage earnings season across your watchlist](https://veridive.com/mcp/use-cases/earnings-season-triage.md) — Import the calls and interviews that matter, batch key-quotes and summaries, and walk into the week with a stack of one-pagers. - [Build an investment-thesis file from expert commentary](https://veridive.com/mcp/use-cases/investment-thesis-file.md) — Collect the strongest bull and bear cases into a library, then stress-test your thesis against all of them in one chat. - [Detect positioning shifts across a year of videos](https://veridive.com/mcp/use-cases/positioning-shift-detection.md) — Compare how a rival described their product a year ago vs today; answers cite the exact moments the pitch changed. --- Part of the veridive MCP use-case library: https://veridive.com/mcp/use-cases.md Server docs for agents: https://veridive.com/mcp.md