Browse Source

README TODO update

Jeff Tang 4 months ago
parent
commit
2ecd6e0041
1 changed files with 6 additions and 6 deletions
  1. 6 6
      recipes/use_cases/gmail_agent/README.md

+ 6 - 6
recipes/use_cases/gmail_agent/README.md

@@ -304,11 +304,11 @@ Tool calling returned: [{'message_id': '1936ef72ad3f30e8', 'sender': 'gmagent_te
 2. Improve the search, reply, forward, create email draft, and query about attachments to cover all listed and other examples in `functions_prompt.py`.
 2. Improve the search, reply, forward, create email draft, and query about attachments to cover all listed and other examples in `functions_prompt.py`.
 3. Improve the fallback and error handling mechanism when the user asks don't lead to a correct function calling spec or the function calling fails. 
 3. Improve the fallback and error handling mechanism when the user asks don't lead to a correct function calling spec or the function calling fails. 
 4. Improve the user experience by showing progress when some Gmail search API calls take long (minutes) to complete.
 4. Improve the user experience by showing progress when some Gmail search API calls take long (minutes) to complete.
-5. Implement the agent planning - decomposing a complicated ask into sub-tasks, using ReAct and other methods.
-6. Implement the agent long-term memory - longer context and memory across sessions (consider using Llama Stack/MemGPT/Letta)
-7. Implement reflection - on the tool calling spec and results.
-8. Introduce multiple-agent collaboration.
-9. Support any and all types of asks a user may have to Gmagent.
+5. Implement the async behavior of Gmagent - schedule an email to be sent later.
+6. Implement the agent planning - decomposing a complicated ask into sub-tasks, using ReAct and other methods.
+7. Implement the agent long-term memory - longer context and memory across sessions (consider using Llama Stack/MemGPT/Letta)
+8. Implement reflection - on the tool calling spec and results.
+9. Introduce multiple-agent collaboration.
 10. Implement the agent observability. 
 10. Implement the agent observability. 
 11. Compare different agent frameworks using Gmagent as the case study.
 11. Compare different agent frameworks using Gmagent as the case study.
 12. Productionize Gmagent.
 12. Productionize Gmagent.
@@ -324,4 +324,4 @@ Tool calling returned: [{'message_id': '1936ef72ad3f30e8', 'sender': 'gmagent_te
 7. Amazon's [Multi-Agent Orchestrator framework](https://awslabs.github.io/multi-agent-orchestrator/)
 7. Amazon's [Multi-Agent Orchestrator framework](https://awslabs.github.io/multi-agent-orchestrator/)
 8. Deeplearning.ai's [agent related courses](https://www.deeplearning.ai/courses/?courses_date_desc%5Bquery%5D=agents) (Meta, AWS, Microsoft, LangChain, LlamaIndex, crewAI, AutoGen) and some [lessons ported to using Llama](https://github.com/meta-llama/llama-recipes/tree/main/recipes/quickstart/agents/DeepLearningai_Course_Notebooks). 
 8. Deeplearning.ai's [agent related courses](https://www.deeplearning.ai/courses/?courses_date_desc%5Bquery%5D=agents) (Meta, AWS, Microsoft, LangChain, LlamaIndex, crewAI, AutoGen) and some [lessons ported to using Llama](https://github.com/meta-llama/llama-recipes/tree/main/recipes/quickstart/agents/DeepLearningai_Course_Notebooks). 
 9. Felicis's [The Agentic Web](https://www.felicis.com/insight/the-agentic-web)
 9. Felicis's [The Agentic Web](https://www.felicis.com/insight/the-agentic-web)
-10. A pretty complete [list of AI agents](https://github.com/e2b-dev/awesome-ai-agents), not including [/dev/agents](https://sdsa.ai/), a very new startup building the next-gen OS for AI agents, though.
+10. A pretty complete [list of AI agents](https://github.com/e2b-dev/awesome-ai-agents), not including [/dev/agents](https://sdsa.ai/), a very new startup building the next-gen OS for AI agents, though.