Async agent execution in Agentic AI - Model Pipeline Trace

Model Pipeline - Async agent execution

This pipeline shows how an AI agent runs tasks asynchronously to work faster and handle many jobs at once. It splits tasks, runs them in parallel, and combines results smoothly.

Data Flow - 5 Stages

1Input Task Queue

100 tasks→Receive tasks to be processed asynchronously→100 tasks

Tasks: ['Analyze text A', 'Summarize report B', 'Translate sentence C', ...]

↓

2Task Splitting

100 tasks→Divide tasks into smaller subtasks for parallel execution→300 subtasks

Task 'Analyze text A' split into ['Tokenize', 'Extract keywords', 'Sentiment analysis']

↓

3Async Execution

300 subtasks→Run subtasks concurrently using async calls→300 subtasks with results

Subtask 'Tokenize' output: ['This', 'is', 'text', 'A']

↓

4Result Aggregation

300 subtasks with results→Combine subtask results back into full task results→100 task results

Task 'Analyze text A' result: {'tokens': [...], 'keywords': [...], 'sentiment': 'positive'}

↓

5Output Delivery

100 task results→Send completed task results to user or next system→100 task results delivered

Delivered results: [{'task': 'Analyze text A', 'result': {...}}, ...]

Training Trace - Epoch by Epoch

Loss
0.5 |**************
0.4 |**********
0.3 |*******
0.2 |****
0.1 |**
    +----------------
     1 2 3 4 5 Epochs

Epoch	Loss ↓	Accuracy ↑	Observation
1	0.45	0.60	Initial async scheduling causes some overhead, moderate accuracy
2	0.30	0.75	Improved concurrency reduces wait time, accuracy improves
3	0.20	0.85	Optimized async calls and aggregation stabilize performance
4	0.15	0.90	Fine-tuned task splitting and error handling boost accuracy
5	0.12	0.92	Converged with low loss and high accuracy, efficient async execution

Prediction Trace - 5 Layers

Layer 1: Receive Task

Layer 2: Split Task

Layer 3: Async Run Subtasks

Layer 4: Aggregate Results

Layer 5: Deliver Output

Model Quiz - 3 Questions

What is the main benefit of splitting tasks into subtasks in async agent execution?

A Prevents any errors from happening

B Allows running parts of the task at the same time

C Makes the task take longer to finish

D Reduces the number of tasks

Key Insight

Async agent execution speeds up processing by running many small parts of a task at once, then combining results. This approach improves efficiency and accuracy as shown by the training loss decreasing and accuracy increasing over time.

Practice

1. What is the main benefit of using async agent execution in AI systems?

easy

A. It makes the agents run slower but more accurately.

B. It allows multiple agents to run at the same time, speeding up processing.

C. It forces agents to run one after another in a fixed order.

D. It disables agents from communicating with each other.

Solution

1. Step 1: Understand async execution

   Async execution means running tasks without waiting for each to finish before starting the next.

2. Step 2: Apply to AI agents

   Running multiple AI agents at the same time speeds up overall processing by avoiding delays.

3. Final Answer:

   It allows multiple agents to run at the same time, speeding up processing. -> Option B

4. Quick Check:

   Async = concurrent execution = speed up [OK]

Hint: Async means agents run together, not one by one [OK]

Common Mistakes:

• Thinking async slows down agents
• Believing async forces sequential runs
• Confusing async with disabling communication

2. Which of the following is the correct syntax to run multiple async agents together in Python?

easy

A. await agent1() and agent2()

B. asyncio.run(agent1(), agent2())

C. await asyncio.gather(agent1(), agent2())

D. async gather(agent1, agent2)

Solution

1. Step 1: Recall asyncio syntax

   To run multiple async functions concurrently, use await asyncio.gather(...).

2. Step 2: Check options

   await asyncio.gather(agent1(), agent2()) uses correct syntax with await asyncio.gather(agent1(), agent2()). Others are invalid or incorrect.

3. Final Answer:

   await asyncio.gather(agent1(), agent2()) -> Option C

4. Quick Check:

   asyncio.gather + await = correct syntax [OK]

Hint: Use await with asyncio.gather to run agents together [OK]

Common Mistakes:

• Using asyncio.run with multiple args
• Missing await before asyncio.gather
• Wrong function call syntax without parentheses

3. Given the code below, what will be the output?

import asyncio

async def agent1():
    await asyncio.sleep(1)
    return 'Agent1 done'

async def agent2():
    await asyncio.sleep(2)
    return 'Agent2 done'

async def main():
    results = await asyncio.gather(agent1(), agent2())
    print(results)

asyncio.run(main())

medium

A. ['Agent1 done', 'Agent2 done'] after about 2 seconds

B. ['Agent2 done', 'Agent1 done'] after about 2 seconds

C. ['Agent1 done', 'Agent2 done'] after about 3 seconds

D. Error because agent2 takes longer

Solution

1. Step 1: Understand asyncio.gather timing

   asyncio.gather runs tasks concurrently, so total time is max of individual times.

2. Step 2: Analyze sleep durations

   agent1 sleeps 1s, agent2 sleeps 2s, so total time ~2 seconds, results in order of calls.

3. Final Answer:

   ['Agent1 done', 'Agent2 done'] after about 2 seconds -> Option A

4. Quick Check:

   Concurrent run time = max sleep = 2s [OK]

Hint: Total time = longest agent sleep with asyncio.gather [OK]

Common Mistakes:

• Adding sleep times instead of taking max
• Assuming output order changes by sleep time
• Expecting error due to different sleep durations

4. What is wrong with this async agent execution code?

import asyncio

async def agent():
    return 'done'

async def main():
    results = asyncio.gather(agent(), agent())
    print(results)

asyncio.run(main())

medium

A. Missing await before asyncio.gather, so results is a coroutine, not actual results.

B. agent() is not async, so cannot be awaited.

C. asyncio.run cannot be used with async functions.

D. print cannot be used inside async functions.

Solution

1. Step 1: Check asyncio.gather usage

   asyncio.gather returns a coroutine; it must be awaited to get results.

2. Step 2: Identify missing await

   Code misses await before asyncio.gather, so print shows coroutine object, not results.

3. Final Answer:

   Missing await before asyncio.gather, so results is a coroutine, not actual results. -> Option A

4. Quick Check:

   Always await asyncio.gather to get results [OK]

Hint: Always put await before asyncio.gather to get results [OK]

Common Mistakes:

• Forgetting await before asyncio.gather
• Thinking print can't be used in async
• Misunderstanding asyncio.run usage

5. You want to run three async agents where agent3 depends on the results of agent1 and agent2. Which approach correctly handles this dependency using async agent execution?

hard

A. Run all three agents sequentially without async to ensure order.

B. Run agent3 concurrently with agent1 and agent2 using asyncio.gather without waiting.

C. Run agent3 first, then run agent1 and agent2 concurrently after.

D. Run agent1 and agent2 concurrently with asyncio.gather, await their results, then run agent3 with those results.

Solution

1. Step 1: Identify dependency order

   agent3 needs results from agent1 and agent2, so it must run after they finish.

2. Step 2: Use asyncio.gather for parallelism

   Run agent1 and agent2 concurrently with asyncio.gather, await results, then pass to agent3.

3. Final Answer:

   Run agent1 and agent2 concurrently with asyncio.gather, await their results, then run agent3 with those results. -> Option D

4. Quick Check:

   Run dependencies first, then dependent agent [OK]

Hint: Await dependencies before running dependent agent [OK]

Common Mistakes:

• Running dependent agent before dependencies finish
• Running all agents concurrently ignoring dependencies
• Running sequentially losing async speed benefits