Cross-FunctionalFinance
Deal research. Found, then drafted.
Makes prior deal history searchable and drafts a cited investment memo from comparable transactions — so a new opportunity doesn't start from a blank page. Built for investment teams evaluating dozens of opportunities a quarter.
14 cited fields per memo. Built on Sphere AI Foundry.
deal_memo — opportunity #DM-61033LIVE
00:00Ingest → new opportunity, mid-market SaaS, $8M ARRread
00:03Search → deal archive, 2022-2026passed
00:05Match → 3 comparable transactions foundpassed
00:07Terms check → one comp used an earnout structureflagged
00:08Disposition → Route to deal team, 1 term to reviewrouted
memo time 8 minfields cited 14/14deal lead sign-off required
Built on Sphere AI Foundry·Every comp cited to source·21 years, 300+ clients
Manual deal research doesn't scale with opportunity volume
A single investment memo means an analyst searching old deal files, trying to remember which prior transaction looked similar, and asking around because the person who ran that deal two years ago changed teams. At low volume that's manageable. Across dozens of opportunities a quarter, it's the reason every memo starts from scratch instead of building on what the firm already knows.
77%
faster first-draft memo vs. manual deal research
14
fields extracted & cited per memo
100%
of comparable-deal references traceable to the source file
Opportunity in, cited memo out
Four steps, every one logged and citable back to the deal archive.
01
Ingest
Reads the new opportunity directly from your systems
Deal profile, financials, and structure — read from your deal-tracking system or CRM. No separate upload step.
Source document
DM-61033 — mid-market SaaS, $8M ARR
02
Search prior deals
Searches prior deal history for comparables
Prior transactions searched by sector, size, and structure — semantic search across the deal archive, not just a keyword match on company name.
Example query
"Have we seen a similar mid-market SaaS deal before?"
03
Cite every comparable
No comparable without a citation
Each comparable links back to the exact deal file it came from — the citation travels with the reference, not as a separate lookup.
Cited finding
Comparable transaction DF-4471 used an earnout structure tied to ARR retention — worth considering for this deal's structure.
cited to Deal File DF-4471, closed 2024-0304
Classify & route
One disposition, one drafted memo
The agent returns Memo Ready, Terms to Review, or Needs Deal Team, with the drafted memo and comparable-deal citations routed for sign-off.
Disposition
Memo readyTerms to review ✓Needs deal team
10 fields, every one cited
What the agent extracts into every memo.
Memo summary & disposition
Opportunity profile verification
Comparable transaction matches
Deal structure & terms comparison
Financial summary & key metrics
Prior deal outcome context
Consolidated citation list
Risk or deviation flags
Drafted investment memo
Deal lead review checklist
Typical inputs
What the agent reads, and what it connects to.
Documents
- Deal profile and financials
- Prior deal files and closing documents
- Investment committee memo template
Systems
- Deal-tracking system or CRM
- Document repository
- Data room platform, where applicable
Is this the right fit?
Built for a live deal archive — not a one-off opportunity.
✓ Works best for
- Investment teams evaluating 10+ opportunities a quarter
- Firms with a searchable archive of prior deals
- Deal leads wanting every comparable traceable to source
Too small for
- A single opportunity an analyst can memo faster than configuring the search
- Replacing deal lead judgment on the investment decision itself
- Firms with no documented deal archive to search
Grounded in the deal file, not a black box
Compliance-first, the same standard every Sphere agent is held to.
The agent drafts only from documented prior deals and the new opportunity's own data — it flags a gap rather than inventing a comparable that doesn't exist. Every memo sits between opportunity intake and the deal team's own sign-off, never past it.
Comparable-deal references cite the specific deal file directly — the same audit-trail standard every Sphere agent on the Foundry is held to.
Prerequisites deal archive connected
A searchable archive of prior deal files is required before the agent will draft with confidence.
Human review required
A deal lead confirms every memo before it informs an investment decision — never fully autonomous.
Source grounding deal-file-cited
Comparable-deal references cite the specific deal file directly in every memo.
Foundation Sphere AI Foundry
Access controls and audit trail configured here carry forward to every other agent you deploy.
Frequently asked
Does the Investment Memo & Deal Research Agent decide whether to pursue an investment?
No. It drafts the memo and finds comparable deals — the deal team still makes the investment decision.
What deal types does it support?
Any deal type with a searchable prior deal archive to draw comparables from.
How does it integrate with our deal-tracking system?
It reads directly from your deal-tracking system or CRM — no separate upload step required. Integration scope is confirmed during deployment planning.
Is every comparable traceable to a real deal file?
Yes. Every comparable cites the specific deal file it came from — there is no reference without a citation back to the source.
How is this different from a generic memo template?
It actually searches your own deal history for real comparables and cites them, rather than a fill-in-the-blank template. It runs on Sphere AI Foundry, so the access controls and audit trail configured here carry forward to other agents you deploy.
Start here
See it on your own opportunity
Bring a real new opportunity to the demo. We'll show the deal research live — comparables, citations, and the drafted memo, from your own archive.
Looking for a different workflow? Browse the full Agent Catalog.
Talk to a solutions architect
Direct to a senior architect — never a sales queue. Replies within one business day.
By submitting, you agree to be contacted about this request. We never share your details.