Chat modes let you control how much context Optimizely Opal Chat pulls into each response. Choose a mode to balance speed, quality, and credit cost for each task. Opal Chat processes every message you send in one of three chat modes: Auto, Fast, or Enriched. All three modes use your skills.
Switch between modes at any time using the chat mode selector in the chat input bar. The selector displays the current mode, such as Auto. Your selection applies to the next message you send.
Auto (default)
Auto mode evaluates each prompt you send and determines which capabilities produce the best response. It does not treat Fast and Enriched as a single either-or choice. Instead, it decides separately whether to include knowledge retrieval, memory, and tools, and which model tier to use. For a straightforward question, Auto mode can skip retrieval and memory while still applying the appropriate skills. A complex content request receives the full set of capabilities.
Auto mode requires high confidence before it skips any enrichment capability. When uncertain, Auto mode includes more context rather than less. You get efficient responses for simple prompts without losing quality on complex ones.
This per-message optimization also reduces credit consumption. Opal spends credits only on the capabilities each prompt needs, rather than applying full-context processing to every message. For most teams, Auto mode balances response quality, speed, and credit efficiency without manual switching.
Auto mode is the default. Optimizely recommends it for most users. See How Auto mode routes prompts.
Fast
Fast mode generates responses using your skills and lightweight application context only. It skips knowledge retrieval (Retrieval-Augmented Generation, or RAG) and memory. Opal does not pull in brand guidelines, campaign context, or other stored information. Response quality remains high, but without the added context that Enriched mode provides. Fast mode also uses fewer credits per response. Because Opal skips these lookups and works from a shorter prompt, Fast mode returns responses faster.
Use Fast mode in the following situations:
- You need quick answers to straightforward questions.
- You do not need brand or campaign context.
- You want lower credit consumption for high-volume usage.
Enriched
Enriched mode generates responses using the full set of available context, including your skills, knowledge retrieval (RAG), and memory. Opal considers your brand guidelines, campaign context, and other relevant information when forming a response. Because Enriched mode retrieves and processes additional context, it uses more credits per response than Fast mode.
Use Enriched mode in the following situations:
- You create or review content that must align with brand guidelines.
- You work on campaigns where accuracy and context matter.
- You want comprehensive, well-informed answers that draw on stored knowledge.
Compare chat modes
Chat mode affects credit usage, which counts toward your organization's Opal consumption. Auto mode optimizes this consumption automatically. The following table compares the three chat modes:
| Characteristic | Auto | Fast | Enriched |
|---|---|---|---|
| Skills | Included | Included | Included |
| Knowledge retrieval (RAG) | Included when needed | Not included | Included |
| Memory | Included when needed | Not included | Included |
| Credit consumption | Optimized per message | Lower | Higher |
| Best for | Most users and general use | Simple, high-volume requests | Brand-aligned content and complex tasks |
Switch modes
Change the chat mode at any time. The selection applies to your next message.
- Click the chat mode selector in the chat input bar.
- Select Auto, Fast, or Enriched.
The selector displays the mode you selected.
How Auto mode routes prompts
Before Auto mode generates a response, it runs a lightweight classification step. The step does the following:
- Creates a semantic embedding of your prompt.
- Extracts signals such as prompt length, the presence of code, and question structure.
- Uses specialized classifiers to decide which capabilities and model tier the prompt needs.
The routing decision happens in milliseconds and does not add noticeable latency to your response. Auto mode is deliberately cautious about skipping context. It needs strong confidence to skip a capability, but only moderate confidence to include one. This bias favors quality over cost savings.
For a deeper look at the design thinking behind Auto mode and prompt routing, see Not every question deserves a PhD.
Article is closed for comments.