Carta onboarding plugin with Claude

TL;DR

Carta made a strategic bet on agentic AI for internal staff workflows. Multi-entity onboarding was one of the pioneering processes to prove that bet in production — averaging 18 days per case, entirely manual, and undocumented.

I led design strategy, workflow architecture, and implementation — mapping IM processes end to end, defining the skill orchestration system, collaborating with engineers on CLI commands, and shipping PRs alongside the team.

Problem

IMs managed multiple multi-entity companies simultaneously, each requiring all entities to be onboarded together. Three things made this consistently slow and error-prone.

• Volume and document chaos. Customer documents arrived in bulk, unclassified and ungrouped by entity. IMs sorted, classified, and cross-referenced operating agreements, grant agreements, and PIU awards manually before any Carta configuration could begin.
• Complex relationship mapping. Linking entities as stakeholders across cap tables, configuring corresponding interests, and matching securities required precise ordered execution. Any misstep meant undoing work already done in Carta.
• Constant document referencing. Every configuration decision traced back to a specific document clause. IMs managed this entirely in personal annotated PDFs and spreadsheets — invisible to the system, lost between cases.

Approach

Started with direct observation — mapping how IMs worked through both single entity and multi-entity onboardings, identifying every customer data touchpoint, and finding where time and cognitive load were highest.

From that, we designed the agentic workflow — defining where Claude operated autonomously, where it surfaced to the IM, and what each handoff looked like across the full flow.

Three principles shaped every decision:

• Surface ambiguity, don't resolve it. Claude handles the deterministic work. Uncertain extractions, ambiguous matches, unresolved IDs are flagged and routed to the IM — never auto-resolved.
• Checkpoint by default. Every step writes output to disk. IMs resume from any point without rerunning earlier work.
• Source traceability at every step. Every inference traces to the source document. IMs verify claims on live client calls without leaving the plugin.

Solution

A Claude Code plugin built as six orchestrated skills — each owning a single domain, outputting structured data for the next step.

`onboarding-orchestrator` sequences the full flow and handles resume from any step. `setup-entitygroup` creates the entity group in Carta. `link-entity-stakeholder` infers and links entity relationships across cap tables. `setup-corresponding-interest` parses legal agreements to extract share class mappings and CI configuration. `link-securities` matches grants across OpCo and ManCo by quantity and issue date. `multi-entity-provisioning` handles downstream configurations post-linking.

Every skill reads and writes through CLI commands built for this workflow — fetching live Carta data, creating stakeholder links, confirming security matches — so every action is grounded in the same system of record IMs use directly.

Three review artifacts sit at the center of the IM experience — interactive interfaces rendered inside Claude showing the current state of the data, source document overlays for every inference, and inline actions to accept, override, or flag. Designed with deliberate visual familiarity to Carta's core UI so IMs orient immediately.

Slack delivers the handoff. When an artifact is ready for review or a pre-flight confirmation is needed before a Carta write, a notification surfaces that moment to the IM. The plugin does the work. IMs act when the decision is theirs to make.

Impact

Converted an undocumented, IM-memory-dependent process into a repeatable, auditable system. Onboarding time dropped from 18 days to 6.5 days. IMs handle 2.4× more cases simultaneously. Silent failures on entity linking dropped to zero.

The plugin established the pattern for how agentic workflows are designed and shipped across Carta's internal staff tooling.

Key learnings

• Trust is earned through transparency. The moments that built the most IM confidence were when Claude showed its working — source overlays, flag gates, explicit confirmation before writes. Automation without proof erodes trust faster than it builds it.
• Artifacts take over the interaction. When a visual artifact is present, the chat thread disappears from the IM's attention entirely. What lives in the artifact versus the conversation is a consequential design decision — mixing action surfaces breaks the mental model.
• Tracking agentic workflows is an unsolved problem. Session analysis depended on user-submitted Claude usage reports, not instrumented data. As agentic AI expands across Carta, native observability into where agents act and where they hand off to humans is a critical open design problem.
• The gates matter more than the skills. The hardest design work was defining exactly where Claude stops and waits. Too many gates and the plugin loses value. Too few and IMs lose trust. The right gate is wherever a wrong decision in Carta is irreversible.