A domain track
Partners, analysts and platform teams at VC and investment funds who already lean on AI to read a memo or research a company, but still slog through due diligence and LP reporting by hand when deal flow spikes. This track turns your term sheets, data rooms and portfolio reports into work Claude can screen, flag and summarize the same day.
23 topics
At a fund, the tension is between the number of decks arriving and the time a partner has to read them. The workshop practices deal flow triage. Claude reads an inbound deck, pulls out the claim, the market and the team, and returns one page that says what is missing before the company earns a meeting.
The risk the training is built around is a partner's conviction resting on a skim. So in the due diligence exercises every claim in the memo gets checked against the document it came from, whether that is a data room, a SAFE or a cap table. Claude quotes the passage and the page, and whoever writes for the investment committee sees what the document does not say as well. A conclusion without a source stays a guess, and gets marked as one.
The work continues after the investment. Participants assemble an LP update from portfolio company numbers, write the quarterly letter in the fund's own voice, triage the founder updates piling up in the inbox down to what needs a reply this week, and build a market map that can be refreshed without starting over. All of it runs on material that stays inside the fund, under confidentiality rules the team sets and rehearses itself.
A live opening session built to shift the room, not lecture it: real demos of what Claude can already do inside your workflows, run in front of the group. Participants leave with a working sense of where AI helps and where it doesn't, and enough curiosity to start using it that afternoon.
What tokens, context windows and hallucinations mean, explained without the math and without the hand-waving. Once a team understands why a model sometimes gets things wrong, it stops either trusting it blindly or dismissing it after one bad answer. Every other module in the program builds on this one.
Before the work starts, we walk the Claude screen together: a new conversation, uploading files, choosing a model, and where Projects, Artifacts and Skills live. Face to face it is a live demo; in the online course it is a recorded tour. Ten minutes that save weeks of fumbling.
Claude Skills turn a procedure your team already does well into something Claude can repeat on its own: the same checklist, the same tone, the same edge cases covered every time. You build it once with the person who actually knows the process, and from then on every teammate gets that expertise on demand. For teams where quality depends on one or two people, this is how that stops being a bottleneck.
Structure, context and role framing: the craft of asking in a way that gets a usable result on the first try instead of the fifth. Participants practice on real prompts from their own work, not toy examples, so what they take home already fits the job. Every other module assumes this fluency, which is why it comes early.
Claude Projects hold your documents and instructions in one persistent workspace, so every conversation starts already knowing your company, your terminology and your rules. Teams that set this up once save the ten minutes of re-explaining context at the start of every session, every day. For anyone running the same kind of task repeatedly, this alone changes the math.
Artifacts are documents, dashboards and small interactive tools Claude builds live inside the conversation, editable on the spot instead of copied out and reformatted. The session covers static outputs and interactive artifacts alike, with an eye on what a non-technical teammate can actually ship without engineering help. It's the module that convinces people Claude is a builder, not just a chatbot.
The shift from asking Claude a question to handing it a multi-step task it completes on its own, checking in only where it matters. Participants learn what actually counts as an agent, when handing over work beats doing it turn by turn, and how supervision needs to change once Claude is running unattended. Get this wrong and you either babysit an agent that didn't need it or trust one that did.
In the Claude chat you can hand over a whole job instead of asking a question. Claude plans the steps, searches the web, reads your files, runs code and hands back a finished document, spreadsheet or deck. On a big task it can split the work between several sub-agents running at once. Participants learn which work is worth handing over and how to brief it the way they'd brief a colleague, then practice staying in control while Claude works. They finish by turning a weekly chore into a scheduled task that runs on its own.
A full pass across the Office suite: drafting and redlining in Word, tables and analysis in Excel, decks in PowerPoint, and inbox triage in Outlook, taught as one connected workflow rather than four separate tricks. Every exercise uses documents close to what participants actually produce at work. It's the broadest module in the program, and the one most teams come back to most after training.
Claude inside Excel: building and checking models, tracing a formula back through six sheets to find where the logic breaks, and producing outputs you can stand behind. This is for teams whose spreadsheets are the actual product, not a side task. Formula archaeology alone tends to pay for the session.
Tasks Claude runs on its own, on a schedule: a morning brief from your calendar and inbox, a weekly report, a competitor watch. Participants learn to tell a routine from its schedule, connect only the connectors it needs, and test every routine before it runs alone. They leave with one routine that works from the next morning.
Connecting Claude to the systems your team actually runs on: drives, CRMs, databases, through connectors and MCP, with the permission boundaries covered before the connection ever gets made. Participants leave knowing exactly what to expose and what to keep out of reach. This is the module that turns Claude from a smart typewriter into something acting on real, current data.
Real engineering workflows built agent-first: how a task moves from a prompt in the terminal to reviewed, shipped code. The module is built for developers, but the data-analysis half works just as well for a non-developer who lives in spreadsheets and needs that same rigor applied to a script. Teams leave with a working setup running in their own repo.
CLAUDE.md is a plain text file Claude Code reads at the start of every session, so whatever you'd explain to a new hire on day one, you write there once. Participants learn what goes in it and what stays out, when it's read, and where it lives: the organization, you, the project and a subfolder, all loading together. They leave with a draft from /init and one rule for growing it: what you corrected twice goes in the file.
How to build an agent without writing code: it gets a job description, a badge that limits what it can touch, and a bottom line it hands back. Participants see why the work goes to a separate room, take an agent file apart, and fill in the one-page charter that turns into the agent's file. They learn to hire for a role, not a task, and to tell when a job needs an agent rather than a skill. They leave knowing the hard part is the charter, and that the charter is their own expertise, written down.
A plugin carries the agents, skills and hooks a team built, so another team installs the same department instead of rebuilding it. Participants see what goes in the box and what stays home: CLAUDE.md and the permission rules belong to each team. Then they ask Claude to build one, try it in a fresh session, and share it through a marketplace.
How context windows, memory and cost interact, and what to do about it before a long working session starts drifting or the bill surprises someone. Participants learn to spot when Claude is still hauling a task that should have been closed an hour ago, and how to reset without losing what mattered. A short module with an outsized effect on both output quality and the invoice.
The rules every employee needs before their first real session: what data is safe to share, what isn't, and what org-level guardrails should exist so individual judgment isn't the only safeguard. This module is usually the one legal and IT ask for by name. It replaces vague anxiety about compliance with a clear, specific policy people can actually follow.
Where people belong in an AI-assisted workflow: which steps need a review gate, which need an approval, and how to calibrate trust so oversight isn't either everywhere or nowhere. This pilot module gives teams a concrete framework instead of a gut feeling about what to check. Get the calibration right and quality goes up without slowing anything down.
Permissions, prompt injection and data boundaries: what makes an agent that can act also one that can go wrong, and how to run it anyway without carrying the risk. This pilot module is built for organizations moving agents past read-only demos into things that write, send and change data. It's the module security teams should sit in on.
Coming soon: preparing and governing the data an AI system actually works from, structure, access and quality, before automation gets layered on top of it. This syllabus item is for teams that already tried an AI project and hit a data problem they weren't expecting. Skipping this step is the single most common reason automation projects stall.
Coming soon: writing the AI policy an organization actually needs, usage rules, risk tiers and rollout governance, instead of a generic template nobody follows. This syllabus item is for leadership and compliance stakeholders shaping how AI gets adopted company-wide. Built to produce a document teams can point to, not a discussion that goes nowhere.
Four working outputs, built in the session on real decks and documents from your fund.
A fixed routine for reading an inbound deck, with a question list that repeats every time and a one-page decision sheet. A partner sees quickly which decks deserve a meeting and what is missing from the rest.
A draft memo where every statement points to a document and a page. A gap check highlights contradictions between the deck, the data room and what the founders said in the first calls.
A map of players in a sector the fund is studying, with clear definitions for each category, so each quarter you add new companies instead of rebuilding the map.
A quarterly update for limited partners built from portfolio company data, in one consistent tone, with every figure linked to the report it came from.
3 min read
Not another chatbot that reads a pitch deck faster. The three skills a VC fund builds first with Claude, and why the order you build them in matters.
Your pipeline
The practice decks are swapped for the ones that reached you this month, and the sample data room for a real one opened for the session. The team works on decisions that are actually on the table.