A Virtual Project Manager: Grounded Answers and Meeting Intelligence
Project status lived across a knowledge base, several tools and the last meeting. Our assistant attends meetings, cites its sources, and answers 'where is this?' on demand, with consent built in from day one.
- Service
- AI Business Applications
- Industry
- Professional Services & Staffing
- Region
- United States
- Engagement
- R&D Lab (joint innovation)
Outcomes
- Cited answers on demand
- Meetings become searchable record
- Fewer status meetings
Stack
Python · LLM + retrieval · Deepgram · Meeting APIs · Knowledge base
Written byOriental Nippon Team
An organisation running many projects at once had a simple question it could never answer quickly: where is this project? The answer was spread across a knowledge base, several tools, and whatever was said in the last meeting.
Getting it meant asking several people and reconciling their answers. Many meetings existed mostly to pass status around.
The problem
- Status by interrogation. Every answer meant chasing several people.
- Meetings as data transfer. An expensive way to move information.
- Lost decisions. What was agreed in a call often wasn't written down.
- Patchy updates. Writing updates competed with doing the work.
| Before | After | |
|---|---|---|
| "Where is this project?" | Ask around | Ask the assistant, with sources |
| Meeting notes | Whoever remembered | Captured and transcribed |
| Status updates | Written by people, irregularly | Daily and weekly, generated |
| Assistant presence | n/a | Visible to every participant |
What we built
A grounded assistant
Answers come from the organisation's knowledge base and cite the source.
Meeting capture
The assistant joins meetings, visibly, and transcribes them with Deepgram, so what is said becomes part of the record.
Automatic summaries
Daily and weekly progress updates produced from that record.
Direct Q&A
Progress, blockers and next steps on demand.
Technology and the role it played
| Technology | Role in this project |
|---|---|
| Python | Assistant services and integrations |
| LLM with retrieval | Grounded answers that cite the knowledge base |
| Deepgram | Meeting transcription |
| Meeting-capture APIs | Joining meetings visibly |
| Knowledge-base integration | Ingesting the authoritative project sources |
How we delivered it
The first step was deciding what counts as the record: which sources are authoritative, and what every answer must be grounded in.
- Define the sources. Authoritative sources, grounding rules and consent policy.
- Retrieval. Knowledge-base ingestion with citations back to source.
- Meeting capture. With explicit consent handling and a clear signal that the assistant is present.
- Summaries and Q&A. Checked against what a good project manager would have written.
- Pilot. A few projects, with output compared to human updates.
01Source definition
1–2 wks
Authoritative sources, grounding rules, consent policy
02Retrieval layer
3–4 wks
Knowledge-base ingestion, retrieval, citation
03Meeting capture
2–3 wks
Attendance, transcription, participant notification
04Summarisation and Q&A
3–4 wks
Daily and weekly updates, question answering
05Pilot
2–3 wks
A few projects, output compared against human updates
Risks and how we handled them
| Risk | How we handled it |
|---|---|
| Answers that aren't grounded | Authoritative sources defined and every answer cited |
| Recording people without consent | Consent handling and visible presence built in from the start |
| Summaries worse than a human's | Pilot output compared against human-written updates |
Outcome
Stakeholders get an accurate project answer on demand. A whole category of status meeting, and a lot of chasing, went away.
An assistant that joins meetings has to be visible to everyone in them. Building consent in from the start avoided a conversation nobody wants to have afterwards.
What the client keeps
- The assistant and its source
- Retrieval and grounding configuration
- The consent and notification policy as implemented
- Summary history
Sources and further reading
- Deepgram documentation, Deepgram
- Guidelines for human-AI interaction, Microsoft HAX Toolkit
- Top 10 for Large Language Model Applications, OWASP
Facing something similar? This is the kind of work our AI, Data Science & Automation team delivers every day. Talk to us about your stack.
