.png){kind=logo}
Partner AI Training · Part 2 · May 2026
01 / 00
The capabilities we have built, the ones we are building, and the path forward together
AdventLabs is tool-agnostic. We work across all three to bring the best capabilities to every deal team
More cost-effective and good enough for most everyday tasks: casual use, image and video, general research. Every employee has access. Our skills are coming to it soon
Open chatgpt.com →Proprietary knowledge, pre-ingested deal folders, 50+ portfolio agents, workflow automation. Does things LLMs cannot
Open AdventGPT →More cutting-edge and the constitutional AI is less sycophantic, more skeptical. 40+ codified skills today, continually growing. Ideal for structured analytical work and document production
Open claude.ai →Tools like Claude Code, Codex, and the Claude/ChatGPT chat apps are powerful harnesses around a state-of-the-art model, but they aren't purpose-built for large-scale document indexing or company-specific workflows. Pointed at a deal folder, they have no prior knowledge of the firm and no structured understanding of our deal drives. Every search is like a new hire with zero training, feeling their way through the room. AdventGPT shows up with that structured understanding already in place, which is why it produces richer answers than a cold chat harness can. The four below are concrete examples; the pattern generalizes
The boundary keeps moving. Claude and ChatGPT will absorb more features over time, and AdventGPT will stay focused on the gaps that matter for PE work: deep document indexing, persistent scheduled workflows, and structured prior knowledge of the firm's deals
⁺ Plus Outlook email and calendar, with more sources coming online each quarter
Four interlocking layers, each capturing a different shape of knowledge
Curated language for every PE task. 6 categories from sourcing to productivity, with zero learning curve
Browse the library →Persistent AI analysts. Portfolio company agents plus VDR Mapper, LOI Drafter, Fisher Dashboard, and IC Knowledge Agent
Open agent example →Packaged expertise. The firm's best version of every recurring analysis, codified into one-call workflows
See Skills · Live todayEnd-to-end pipelines. Email-to-dashboard, news digest, CIM-to-LBO, inbox triage. Always on, zero human input
Open Fisher dashboard →Build a public information book? company-research. Recruit advisors? expert-network-builder. Kathy Fang's digital twin? In development now
One email. No login. No new tool. Just ask
A partner asked the Mind to map warm-intro paths into Lululemon via Advent's APN network. Here is how it played out
Click any skill name to launch it in Claude with a prefilled prompt
lbo-model · excel-lbo-modeler · excel-dcf-modeler · returns-bridge · customer-cube · excel-variance-analyzer
company-research · sector-overview · market-primer · leadership-mapper · buyer-universe-map · gen-ai-defensibility · expert-network-builder · executive-briefer
inbox-reviewer · email-company-counter · vcf-creator · advent-brand-guidelines · pe-deck-auditor · redline · logo-finder · interview-prep · working-group-slide · stock-chart · deal-page-builder
In early 2023, we published the firm's first AI prompt library. Since then, we took on the responsibility of maintaining an inventory of the best AI use cases across the firm, and we ran an AI use case competition to surface the most promising ideas
Every quarter we added a new layer. Prompts became micro agents and workflows, then came the skills paradigm. Today, the Advent Mind brings it all together: one system that routes your question to the right capability
AdventLabs is pursuing each of these aggressively. Scaling the deal team's productivity is a major goal for the firm, and these skills are the next tranche of capability the deal teams are asking for right now
The same question, asked four ways. Click any send button to fire the prompt at Claude
Each card below is a real example. Click the paper-plane to send the request to Mind from your inbox
Four interlocking layers, each capturing a different shape of knowledge
Curated language for every PE task. 6 categories from sourcing to productivity, with zero learning curve
Browse the library →Persistent AI analysts. Portfolio company agents plus VDR Mapper, LOI Drafter, Fisher Dashboard, and IC Knowledge Agent
Open agent example →Packaged expertise. The firm's best version of every recurring analysis, codified into one-call workflows
See Skills · Live todayEnd-to-end pipelines. Email-to-dashboard, news digest, CIM-to-LBO, inbox triage. Always on, zero human input
Open Fisher dashboard →Pick something you do often that the firm would benefit from doing the same way every time. We will brainstorm together, then each of you will pick one of the three approaches below and build it live
Type /skill-creator in Claude and describe the skill in plain English. The base Anthropic skill-creator (not the AdventLabs modified version) will interview you, scaffold the SKILL.md file, and walk you through testing
Run the task once end-to-end with Claude. Then ask it to generalize what just happened into a reusable skill: capture the inputs, the methodology, the output format. The example becomes the spec
Ask Claude to think like a top PE professional and write the prompt that would create this skill. Then feed that prompt back to skill-creator. The AI writing the AI. See From simple to expert for the full demo
Same task, two paths. We will run them side by side and look at the difference together. The point is not which one wins; it is to feel where Claude alone hits a wall, and where AdventGPT picks up
Open the VDR in SharePoint, share the folder URL with Claude, and ask it to summarize the contents and surface the most important findings. It will try. Watch what happens when context windows meet thousands of files
Send the same VDR to the VDR Mapper agent. It runs a cheaper model 1,000× across every file in parallel, returns a structured map of the entire data room, and surfaces the documents that matter, in minutes, at roughly 100× lower cost
Over time, the Mind specializes. Each sector team gets its own mailbox carrying its deal history, sector-specific skills, and the team's preferred analytical voice. CC the right one and the answer comes back already steeped in context
This month: 4 group sessions and individual interactions with 30+ people across AdventLabs and IT, from power users like Dov and Eli to people still figuring out where to start
Curated prompt templates across the full PE workflow. Click any prompt to open Claude with it prefilled, then replace the {placeholders} and send
More prompts ship every week via #advent-ai-exchange and the AI Corner. Treat each as a starting point and refine with follow-ups
Persistent workflows triggered on a schedule or by an event, with no human input required. Output lands where you need it: inbox, dashboard, or shared folder
Scans a virtual data room file by file, classifies the contents, and produces a structured map of the entire room, ready for diligence kickoff
Prepares, reviews, and negotiates Letters of Intent. Highlights material terms, generates redlines, and tracks alignment across counterparties
Benchmarks a target's KPIs against portfolio peers and public comparables. Flags outliers and surfaces relevant precedents
Builds A-Method scorecards and tailored interview guides for management diligence and executive hiring, calibrated to the role and deal context
Reads any document or set of documents and produces a structured executive summary on demand. Handles CIMs, expert transcripts, board packs, and long-form research
Ingests portfolio company emails daily, extracts KPIs, maintains a database, and keeps a secure dashboard live 24/7. The reference design for an always-on portfolio agent
One agent per portfolio company, each having consumed thousands of files from the deal folder. Ask a question and get a sourced answer drawn from the full document history. We also operate firm-wide intelligence agents over IC memos, IC notes, and the AI use case repository
More agents are added as deals close and new firm-wide knowledge bases come online
⟨ mofax.ai ⟩