Part 1 The problemWhy teams need this
01 · THE PROBLEM
First-look research is the same routine for every deal, and it eats hours before anyone knows if the deal deserves them. Doing it on arrival means the partner meeting starts from a memo, not from a company name.
Part 2 How it worksWhat it does, step by step
02 · WHAT IT DOES
For VC and PE firms. When a deal lands in your CRM, the workflow pulls company data, recent news, competitors and filings, then writes a structured deal memo with an AI score against your thesis. Your analysts save 4+ hours per deal.
03 · HOW IT RUNS
Step by step, as built.
Catch the new deal
A new Affinity deal triggers the run and pulls its details.
Research in parallel
Company data, recent news, competitors and filings are fetched side by side and merged.
Write the memo
Claude writes a structured deal memo from the research.
Score against the thesis
A scoring step checks the memo against the fund's criteria.
Deliver
The memo goes into a Google Doc, the CRM gets the score and link, and the deal team sees it in Slack.
04 · WHERE A PERSON STAYS IN
The machine drafts. A person decides.
The score informs the partner meeting, it doesn't replace it. Every memo links back to its sources.
05 · TOOLS AND APPS
Built around the systems already in the process.
06 · WHEN SOMETHING BREAKS
Failure is designed in.
- 10nodes retry automatically when an external API fails.
- ✓Anything unhandled triggers our central error workflow, so a crash gets reported instead of failing silently.
Standard on every build
- Schema validation before downstream writes
- Retry and error routes for external API failures
- Duplicate-safe processing and idempotent updates
- Human approval where the action carries business risk
- Execution logging for support and audit review
Part 3 The impactWhat it's worth, and how we'd build yours
07 · PROJECTED IMPACT
What it should change in the business.
Projections for a typical deployment. The calculation below shows the math, and you can put in your own numbers.
08 · ROI CALCULATION
How it pays back in your business.
The starting numbers are a hypothetical deployment sized to the projections above. Change any of them to your own volumes and costs, and the math updates underneath.
- Full-time equivalent freed
- 1.1 people
- Gross value
- $77,760
- Running cost
- −$720
- Return per $1 of running cost
- $108
The math: 40 deals researched × 270 min × 12 months × 90% ÷ 60 = 1,944 hours a year × $40/hour = $77,760. Net value = gross value − $720 running cost a year.
09 · HOW WE'D BUILD YOURS
How we'd build yours.
- Discover: map the current process, systems, volumes, owners and exceptions.
- Design: define the canonical data model, approvals, retries and system boundaries.
- Build: implement credentials, nodes, validation and observable error routes.
- Prove: run controlled data through success, duplicate and failure scenarios.
- Operate: publish runbooks, ownership and measurable service levels.
