No single agent has the whole picture
Merivex does not run one general-purpose model over your data. The analysis is split across 15 specialist agents, each with a short tool list and a narrow memory scope, and a verifier whose job is to disagree with the rest. Every one of them reads your workspace brief.
Coordinate
Ingest
Understand
Evaluate
Verify
Discover
Coach
Report
Govern
Coordinate
01 / 15Supervisor / Router
Routes analysis tasks to the right specialist and coordinates multi-agent workflows.
- Tools
- 3
- Reads
- organisation
- Writes
- organisation
The stages
Nine stages, one direction of travel.
Every agent belongs to a stage, and the stages run in order: coordinate, ingest, understand, evaluate, verify, discover, coach, report, govern. Nothing skips the verifier.
Decides which specialist runs, and in what order. Holds no analytical opinion of its own.
- Supervisor / Router
Gets the data into one shape and pulls the history a judgement needs.
- Ingestion / Normalization Agent
- Context & Knowledge Retrieval Agent
- Call Transcription Agent
Classifies what the conversation was about and how it moved, before it is scored.
- Intent Agent
- Sentiment / Emotion Timeline Agent
Scores the interaction against your rubric and surfaces policy risk, every claim tied to a turn.
- Evaluation Agent
- Compliance & Risk Agent
Re-reads the conclusions and rejects anything the cited evidence does not support.
- Critic / Verifier Agent
Rolls individual findings into patterns, and puts the human review queue in priority order.
- Pattern Intelligence Agent
- Review Triage Agent
Turns the evidence into a specific, per-person plan.
- Coaching Agent
Writes the executive narrative over live metrics. Reads only.
- Analytics Agent
Keeps memory clean and the connectors healthy.
- Memory Curator
- Data Quality / Integration Health Agent
Workspace brief
How does Merivex know your QA standards?
You write a workspace brief on the AI agents page. Every AI agent reads it, and so do the automatic evaluation and the coaching, so scores, findings and coaching reflect your own standards rather than generic ones.
What a brief holds
- Your business
- Who you serve
- Your working protocol
- What great looks like
- Goals
- Non-negotiables
- Escalation rules
- Tone of voice
- Glossary
- Any extra context
The brief is context, not instructions: it cannot change permissions or the platform’s safety rules.
Call Transcription Agent
What does the Call Transcription Agent do?
It runs after each call recording is transcribed and before the call is evaluated. It reads the transcript and fills in the customer, the human agent, the topic, a one-sentence summary and the contact reason.
Upload formats, limits and retention are on the call recording transcription page.
- It never overwrites anything the uploader entered. It only fills empty fields.
- It never creates people: the speaking agent is matched to exactly one existing team member, or left unassigned.
- Switch it off and mapping stops. Transcription and evaluation carry on.
- A mapping failure never blocks the evaluation.
Scoped authority
An agent cannot quietly become authoritative.
Each agent is restricted to an explicit set of tools and explicit memory read and write scopes. It operates inside the same tenant isolation and authorization model as a human user, with no bypass.
- Short tool lists: most agents can call between three and nine tools, and nothing else.
- Three agents (Analytics, Memory Curator, Call Transcription) write nothing to memory. They read and report.
- A conclusion only becomes authoritative after the Critic / Verifier agent has failed to break it.
- Merivex AI agents never write to a system you connect. Read-only, by design.
The authorization boundaries are described in full on the security page, covering what each agent may touch, and why a scoped toolset is a control rather than a limitation.
Read the security page →Two kinds of agents
Your people, and the AI that studies their work.
Merivex uses the word deliberately in two places. They are never the same thing.
Intelligence → Agents
Your workforce
The people handling customer conversations. Merivex measures their work, tracks quality over time and builds individual coaching plans, organised by team, by interaction and by evidence.
Platform → AI Agents
Merivex's internal AI agents
Merivex's own analysis engine. Specialists for ingestion, call transcription, evaluation, compliance, intent, sentiment, patterns, coaching, verification and memory, each with a scoped toolset and no authority beyond it.
See it against your own conversations
The agents above run over real interactions and cite the turn every conclusion came from. Tell us how your quality programme works today and we will show you what comes back.