AI Agent usage is billed per token. The more tokens each execution uses, the faster costs add up - and the less room you have to scale. Until now, every AI Agent execution was carrying a lot of unnecessary weight - duplicate data, irrelevant fields, redundant metadata - all contributing to token usage without adding anything to the quality of the output.

That's been cleaned up.

The AI Agent action now uses significantly fewer tokens per execution with no impact on output quality. The same results, leaner execution, lower cost.

What Changed

Cleaner context Duplicate and internal data that was being sent to the model on every turn has been stripped out. Raw database internals, redundant contact data, and unnecessary workflow metadata are no longer included.

Smarter tool responses Tool outputs previously included dozens of irrelevant fields per record - for example, 30+ permission fields per user. Now only relevant fields like name, email, and phone are passed to the model.

Conversation memory management Long-running agents now automatically summarise older conversation steps while keeping recent ones in full detail, instead of sending the entire history every turn.

Structured output optimisation The final extraction step no longer duplicates the entire context, saving thousands of tokens per execution.

The Results

Tested on the same workflow and contact with zero quality loss:

• First LLM call: 36% token reduction

• Total execution: 20% token reduction

Same output. Fewer tokens. Lower cost.

Why It Matters

Every workflow execution is now leaner. If you're running AI Agent automations at volume - follow-ups, lead qualification, enrichment, routing - a 20% reduction in token usage across every run adds up fast. More automations, same spend. Or the same automations, meaningfully lower cost.

If you have any questions about AI Agent actions inside ESC Hub, the support team is here every day. Drop a message inside Escapepreneur Central.