# Manus — How we built a data agent with Manus to help every team make better decisions

- Company: Manus (manus.im)
- Announced: 2026-11-06
- Category: not stated
- Coverage: not counted
- Announcement: no
- Group: routine
- Source: https://manus.im/blog/how-we-built-a-data-agent
- Record: https://forck.live/items/34003-how-we-built-a-data-agent-with-manus-to-help-every-team-make-better-decisions
- Subject: Manus

Manus's four-person data team built a data agent on Manus that more than 40 colleagues now use every week, after Slack requests for numbers outran the team's capacity. The team says it took about a week to reach a first working version, and users ask two to three questions each on average, with heavy users asking a dozen or more a day. The agent queries detailed data directly rather than only dashboards, so it can answer questions no dashboard covers, and a knowledge base maps how each metric is defined and how tables relate. Answers for business users cover what the data suggests, what is solid enough to act on, and what still needs checking with the data team. Access is split by topic for privacy and governance, and a question touching a table a user cannot see triggers an approval request to the right data owner before the agent resumes. The agent lives in Slack, and the team keeps updating the knowledge base as tables and definitions change.

## Evidence

Verbatim from https://manus.im/blog/how-we-built-a-data-agent:

> Manus's four-person data team built a data agent that more than 40 people use every week. We sat down with Ben Zhong, whose Slack title is "Data Guy," to hear how it came together, and what other teams can take from it.
> 
> For a long time, if someone at Manus wanted to understand some data, they messaged the data team. Why did usage jump on Tuesday? What are people really building with Manus? There were only four people on the team, and the questions kept coming.
> 
> Today, more than 40 people get answers to those questions every week by talking to a data agent built on Manus. Today, we share a bit about how our data team gets it done with Manus.
> 
> At a glance
> 
> • 4 people on the data team
> 
> • 40+ people use the data agent every week
> 
> • 2–3 questions per person on average, and heavy users ask a dozen or more a day
> 
> • ~1 week to a first working version
> 
> Why it matters: every team needs data, but analysts are limited
> 
> The reason for building a data agent was simple: there weren't enough people. Almost every team at Manus makes decisions with data, but people rarely have the access or the time to dig into all the questions they have.

---

Record: https://forck.live/items/34003-how-we-built-a-data-agent-with-manus-to-help-every-team-make-better-decisions
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md
