5 days → 30 mins. Redesigning Caribou's client onboarding from a manual task list to an AI-first data-dump flow
Timeline
2026
There were 3 similar organisations with 4 entities each.
Org A took 3 weeks to explain their setup to an expert.
Org B needed 5 days.
Org C did it 30 mins.
How?Simple. Information lives in documents. What if instead of making people hunt for it and then type it in, we used AI to map the right info to the right field?
Caribou already disrupted the old way, replacing the 2 to 3 weeks of functional interviews that traditional consultancies ran with a deterministic digital process. But even the product's own task-list approach still took customers 4 to 5 days of work. I designed the flow that collapsed that to under an hour.
The Problem
Before Caribou existed, onboarding a new client meant the traditional consultancy playbook: weeks of functional interviews across multiple stakeholders, manually extracting entity details, financials, contracts, people data, and more. For a typical organisation with 3 entities, that process took 2 to 3 weeks. Not because the information was complex, because the process of getting it out of people was slow, fragmented, and entirely manual.
Caribou's product replaced that with a structured task-list approach, which was a genuine step forward. It brought the timeline down to 4 to 5 days. It still involves a lot of work filling in forms covering 100+ fields, and the information already exists somewhere in documents the customer has on hand.
The data wasn't missing. It was just trapped in scattered files, spreadsheets, and people's heads. The task list gave it structure, but customers were still doing all the extraction themselves, field by field.
Before: Caribou's structured task list requesting information. It replaced weeks of consultancy interviews, but was still a long list of tasks that compounded
What I did
Identified the data-dump flow as the single highest-leverage onboarding problem. Caribou had already replaced the slow per-hour billing consultancy approach. The remaining bottleneck wasn't "customers don't have the information", it was "we're still making them type it all in manually."
Proposed a fundamentally different approach: let customers upload their existing documents, process and classify them automatically, and present the extracted insights as one-click suggestions inside the same forms they'd otherwise fill by hand.
Scoped the MVP with engineering. The full vision was ambitious, and the shippable version needed to be useful from day one without waiting for perfect extraction accuracy. We designed for graceful degradation: if the AI was confident, one click. If it wasn't, the field was still there for manual entry. No dead ends.
Designed the end-to-end flow:
1. Upload: Customer uploads their existing documents (financials, contracts, org charts, whatever they have)
2. Process & classify: The system ingests, parses, and classifies the content, mapping it to the relevant forms and fields
3. Form-by-form review: Customer moves through each form (entity details, accounting, people, contracts, production, etc.). In each field, processed insights are surfaced and available to accept with one click
4. Confirm without skipping:The flow ensures every key field is addressed. The user could accepted from a suggestion, edit an accepted suggestion, or manually enter from scratch.
Shipped the flow to customers (May 2026), replacing the task-list approach entirely. The new analytics in place include time on task and time to completion of flow. Additional tracking for acceptance rate for AI suggestions.
Design decisions that mattered
One-click accept, not auto-fill: It would have been easier to just dump the extracted data into every field automatically. But trust matters. When you're entering financials and contract details, you want to see what the system found and say "yes, that's right", and not discover later that it guessed wrong! The one-click pattern gave users control without giving them work.
Form-by-form, not all at once: 100+ fields on one screen would be overwhelming. Breaking it into logical forms (entity details, then financials, then people, then contracts) meant each step felt manageable. You're never staring at the whole mountain, just the next stretch. This also made it scalable to larger organisations, where user roles come into play… where Hannah from HR could own all tasks related to people data, while Bill from Accounting filled in the financials.
Graceful degradation: The AI extraction wasn't perfect. Some fields would have high-confidence suggestions, some would have low-confidence ones, some would have nothing. The design handled all the different states without breaking the flow. Only suggestions with a high level of confidence were shown, to build trust and prevent noise. Manual entry was always an option.
Confirmation without skipping: The old task-list approach at least had one advantage: every field was explicitly required. The new flow needed the same discipline. Every required field had to be explicitly addressed before moving on, either by accepting a suggestion as is, editing it, or typing something in.
The Outcome
Onboarding time: Traditional consultancy method took 2-3 weeks → Caribou's task-list approach brought it to 4–5 days → The data-dump flow I designed brought it to 30–45 minutes (even filled entirely manually, ~1 day; still a 5x improvement over the previous product experience)
Forms covered: 8–12 per typical engagement, 100+ fields total
Feature flagged with PostHog for A/B testing
Why this matters for what I do next
Going AI-first changed my approach to designing experiences. The solution had to adapt to varying outputs of the system, and dealt with edge cases and states outside human error.
Through this project I've learned to treat an automated system as a distinct stakeholder, and design for it to be able to give the optimal output. This gives me an edge in designing for all upcoming AI-native projects.
