AriesDevs

Sample project · Paperkite

A knowledge assistant for 2,000 support agents

Sample project: an illustration of how we approach this kind of work, not a real client engagement.

Smiling support agent wearing a headset at a laptop
Sample project · Paperkite

Industry

AI · Retrieval-based support assistant

Timeline

10 weeks

Team

1–2 senior engineers

Stack

  • TypeScript
  • OpenAI-compatible LLMs
  • pgvector
  • Next.js
  • Azure

01 · The challenge

What was getting in the way

Paperkite’s support agents searched six tools to answer one customer question: a wiki, two folders of policy PDFs, a ticket archive, release notes and a chat history. New hires needed months before they could find answers quickly.

An earlier chatbot experiment had been shelved because it answered confidently from outdated policies and could not show where an answer came from.

02 · Our solution

What we built and how

We indexed policies, resolved tickets and release notes with team-level access rules, and built a retrieval pipeline that returns an answer only when supporting sources are found. Every answer carries citations that open the original document at the right paragraph.

Documents carry owners and review dates, so stale content is flagged and ranked lower. An evaluation set of 400 real questions ran on every change, which let the team improve answer quality without guessing.

03 · Results

What changed after Paperkite went live.

Sample figures for this illustrative case study, measured against the period before launch.

70%

faster lookup

Median time to find an answer, measured in agent screen recordings.

2,000

agents using it

Weekly active agents within three months of rollout.

93%

cited answers

Answers backed by at least one source the agent could open.

−35%

onboarding time

Time for a new agent to reach the average handling-time target.

Keep reading

More sample case studies from other industries.

View all case studies

Limited slots

Your project could be
the next case study.

Tell us the outcome you need. We will outline an approach and the metric we would measure it by.