Every reply your agent writes comes from an AI model, and you choose how that model is picked on the agent's Agent screen under AI Model. For most agents the best choice is one of the two Auto settings: eChat picks the best model for you and keeps it current, so your agent gets better models as they arrive with nothing for you to change.
Auto (Smart) and Auto (Efficient)
What it is
The AI Model picker lists two Auto settings first, under Recommended:
- Auto (Smart) — the strongest answers. It's the default for new agents and the right choice for most.
- Auto (Efficient) — great answers at the lowest cost per response, for busy agents where cost matters more than the last bit of quality.
The credits each one costs per response are shown next to it in the AI Model card.
How it works
- eChat does the picking. Each Auto setting answers with the best model eChat has found for it, and when a better one proves itself, your agent moves to it automatically.
- You pay for the answer you got. Each response is billed at the credits of the model that wrote it, within the range shown in the card.
- Small talk costs less. On Auto (Smart), a quick hello, thanks, or goodbye costs just 1 credit.
Your credits are shared across all your agents, so a pricier setting on one agent leaves fewer for the others. See Plans, Credits & Usage.
Best practices
Start with the default, Auto (Smart). You get the strongest answers without following model releases yourself, and a baseline to compare against before you change anything.
Choosing between Smart and Efficient
What it's best for
- Auto (Smart) — most agents, and any agent where answer quality matters most, such as sales conversations or complex product questions
- Auto (Efficient) — high-volume agents answering routine, well-documented questions
How it works
Changing the setting takes effect on the agent's next replies. It doesn't change what the agent knows — training, Instructions, and Grounding strictness all stay the same. If answers are wrong because training is missing or outdated, a stronger model won't fix that; add or correct Q&A instead.
Best practices
- Estimate the cost before you switch: multiply your typical monthly reply count by the credits per response in the AI Model card, and compare it with your plan's allowance.
- Fix thin training first, then decide whether a stronger setting still helps.
- Revisit the choice after big changes in volume.
Picking a specific model
What it is
Below the Auto settings, the picker also lists specific models, each with its credit cost per response. Check the picker for the current options.
How it works
A specific model stays fixed until you change it; it doesn't move to newer models the way Auto does.
Best practices
Pick a specific model only when you have a clear reason, such as an Evaluate result showing it works better for your agent. Otherwise, Auto keeps you current with no upkeep.
Testing a switch before you commit
What it is
Before moving a live agent to a different setting, you can measure the difference instead of guessing.
How it works
Try a handful of real questions in Playground to get a feel for tone. Then run Evaluate with the setting you're considering — only that run uses it, and your agent keeps its own. Compare the scores side by side. Evaluation runs use credits too, so a comparison on a pricier setting costs more.
Best practices
Decide ahead of time how much of a score change you'd accept for a given saving, and check Chat Logs in the days after a switch to confirm real conversations still look right.