ModelRefs / Agent Assist — Canonical Workflow
Agent Assist — Canonical Workflow
Agent Assist: provisional AI workflow implementation reference with candidate models, providers, tools, and architecture.
Overview
Agent assist surfaces real-time support to human agents during live customer conversations. As the conversation progresses, a streaming language model monitors the dialogue, retrieves relevant knowledge-base articles, suggests next-best-reply options and flags policy violations before the agent sends a response. The system operates with sub-second latency without interrupting the agent's flow. All suggestions are logged with retrieved sources so quality reviewers can audit decisions and improve the knowledge base.
Implementation profile
| Category | llms |
|---|---|
| Implementation maturity | production |
| Primary use cases | customer-support |
| Deployment options | managed-api, hybrid |
| Architectures | serverless-api, managed-container, edge-runtime |
Candidate models with published references
- BGE-M3
- GPT-5
- GPT-5 Mini
- Claude Sonnet 4.5
- Claude Opus 4
- Gemini 3 Pro
- Llama 4 Scout
- DeepSeek R1
- Mistral Large 2
- Command R+
- o3
- o4 Mini
Coverage means the model is a candidate worth evaluating for this workflow, not a ranking or a recommendation. Models whose reference pages are still in review are omitted.
Benchmarks relevant to this workflow
- Chatbot Arena ELO — LMSYS crowd-sourced pairwise preference leaderboard across open and closed models.
- τ-bench — Tool-augmented agent benchmark on retail & airline customer-service tasks.
- MMLU — Massive Multitask Language Understanding — 57 academic and professional subjects.
These are the benchmarks whose task shape bears on this workflow. Each one only describes its own protocol and date, so confirm the harness matches your workload before treating a score as evidence.
Continue your research
Use these connected ModelRefs sections to compare alternatives, inspect implementation paths, and review the evidence and governance boundaries relevant to Agent Assist — Canonical Workflow.