Claude for IB Pitchbook and CIM Engine
What this workshop covers
This is a 1-hour hands-on session showing investment bankers, advisors, and deal teams how to produce a first-draft pitchbook section set on their own template, with a clean source trail, using Claude AI agents inside Claude Cowork.
We walk you through a production-ready multi-agent workflow that turns a mandate brief, target data, and your firm template into a drafted section set where every number traces to a source, so by the end of the session you can go from mandate to first draft without starting from a blank deck.
Limited slots available. First come, first served.
Section 1: Running the Full Pitchbook Workflow How to have Claude run the entire engine in one sequence. An Orchestrator lays out the section list, the audience, and the data each section needs, and flags any data you have not provided. A Comps Builder builds the comparable set from your uploaded or connected data only, leaving any unsourced figure as a labeled data request. A Profiler drafts the company overview and market section from the materials. A Narrative Drafter writes the deal story in the firm's voice, the thesis, the positioning, and the three messages that must land. Then Brand Compliance reformats everything to your template. You watch each section build from real data, not memory.
Section 2: Turning the Workflow into a Reusable Skill How to capture the run order as a Claude skill so it executes the same way for every mandate. We build the skill that encodes each seat, the template logic, and the source-discipline rules, so producing a first-draft section set becomes a single instruction rather than a sequence you reassemble each time.
Section 3: Root Files and Workspace Configuration How the files driving the workflow actually work: the workspace identity and house style guide that hold the firm's voice and standards, the skill file for the pitchbook engine, the editable criteria that define what counts as a sourced figure and what gets flagged as a gap, and the agent files behind the Source Watch Dog. Configure these once and every pitch you run gets drafted, formatted, and source-checked against the same house standard.
Section 4: The Scheduling Prompt How to keep the comparable set live so it never goes stale between pitches. Configure Claude to refresh the comps on a schedule, so the Comps Builder maintains a current set in the background and each new pitch starts from fresh numbers rather than a manual rebuild.
What you leave with
All root files, prompts, workflows, and input templates ready to run on your own company tomorrow. 30-minute Q&A with Ayub.
Who this is for
Investment bankers, advisors, principals, and analysts who want to compress the time between winning a mandate and having a first-draft, on-template, source-checked section set on the table.