From dfb80f772300dd2b6be2d28fe9b688953a90fd1d Mon Sep 17 00:00:00 2001 From: Steve Androulakis Date: Sat, 15 Mar 2025 03:47:29 -0700 Subject: [PATCH] Update README.md --- README.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/README.md b/README.md index fd070f2..64ad6cc 100644 --- a/README.md +++ b/README.md @@ -26,7 +26,7 @@ The agent can be configured to pursue different goals using the `AGENT_GOAL` env #### Goal: Find a Premier League match, book train tickets to it and invoice the user for the cost - `AGENT_GOAL=goal_match_train_invoice` - Focuses on Premier League match attendance with train booking and invoice generation - - This is a new goal that is part of an upcoming conference talk + - This goal was part of [Temporal's Replay 2025 conference keynote demo](https://www.youtube.com/watch?v=YDxAWrIBQNE) If not specified, the agent defaults to `goal_event_flight_invoice`. Each goal comes with its own set of tools and conversation flows designed for specific use cases. You can examine `tools/goal_registry.py` to see the detailed configuration of each goal. @@ -189,4 +189,4 @@ If you're running your train API above on a different host/port then change the - In a prod setting, I would need to ensure that payload data is stored separately (e.g. in S3 or a noSQL db - the claim-check pattern), or otherwise 'garbage collected'. Without these techniques, long conversations will fill up the workflow's conversation history, and start to breach Temporal event history payload limits. - Continue-as-new shouldn't be a big consideration for this use case (as it would take many conversational turns to trigger). Regardless, I should ensure that it's able to carry the agent state over to the new workflow execution. - Perhaps the UI should show when the LLM response is being retried (i.e. activity retry attempt because the LLM provided bad output) -- Tests would be nice! \ No newline at end of file +- Tests would be nice!