ava-whatsapp-agent-course

Meet Ava, the WhatsApp Agent

Runs with mockssource: GitHubPythonMITcommit 338fd6870df9

Python, MIT licensed. The project labels itself: agent, agent based, agentic workflow, agents, stt, tts and vector database.

ava-whatsapp-agent-course runs, with stand-ins for the services it depends on. An Argusic agent installed it in 3 minutes and hit 5 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

The project installs cleanly, all 17 unit tests pass, the FastAPI webhook endpoints respond correctly (GET docs 200, GET verify 200, POST status update 200, GET wrong token 403), and the Chainlit interface boots and responds on port 8000.

What the agent ended up with on a clean machine, in its own words. How this is measured

Measured by Argusic on a fresh machine every time. Every number links to its evidence. Argusic Score 92 of 100 (the mean of this project's run scores).

At a glance

verdict
Runs with mocks
Argusic Score
92 / 100
cost of the verifying run
$0.18 (measured)
recorded runs
2
last tested
stars
1,682
forks
416
open issues
7
watchers
23
size
26 MB
created
last push

Subject data from GitHub, linked at the top of this page, refreshed . Test data by Argusic (CC BY 4.0); every number links to a run page with the full log, the recording, and their sha256 hashes.

What was measured

From the run that decided this verdict. Every line is a recorded value, not an estimate.

Time lost to each failure while testing ava-whatsapp-agent-course, drawn from the recorded run
Every bar is a failure the agent recorded, with the time it cost. Drawn from this run, not from anywhere else.

What went wrong, in the agent's own words

The agent's own words, worst first, never rewritten into advice.

  • mcp 1.12+ incompatible with pydantic 2.10 (chainlit dep chain)2 minutes
  • chainlit 2.x renamed AudioChunk and broke API; code expects chainlit 1.x2 minutes
  • langchain v1.2 removed langchain.prompts module; import PromptTemplate from langchain_core.prompts1 minute
  • scipy 1.18 uses np.long which was removed in numpy 2.x1 minute
  • starlette 1.x removed on_startup kwarg from Router; fastapi 0.115 needs starlette<11 minute
Install time
3 minutes
Cold machine to finish
14 minutes
Errors hit and fixed
5 hit, 5 fixed with no human help
How the result was proved
pytest test_ava.py -q exited 0, 17 passed; curl http://127.0.0.1:8082/docs returned 200; curl http://127.0.0.1:8082/whatsapp_response?hub.verify_token=test-token returned 200 body=challenge123; POST /whatsapp_response with status update returned Status update received 200; chainlit run on port 8000 returned 200
Model tokens used
242,909
Exact commit tested
338fd6870df9
Container image
sha256:cdd920bce783

What was not measured

The other half, so you can see exactly how far this evidence goes. A gap is printed as a gap and never filled in.

Peak GPU memory
this ran on a CPU machine, so there was no GPU to sample
Behaviour over a long run
each attempt uses the smallest documented settings and a fixed time budget, so this measures whether it runs, not how it holds up under load
Behaviour against real services
this run was verified against stand-in services only

Watch the session

The whole run, from a clean machine, at the speed it actually happened. Nothing is cut and nothing is sped up.

A recording of attempt 1, run . The verdict above comes from a different attempt, so read this as one session and not as the current result. The terminal recording it was made from is the evidence, stored with a sha256 fingerprint; the video is a rendering of it. Nothing loads from the video host until you press play.

The end of the recording

The last lines of the terminal session that decided this verdict, exactly as they were recorded.

1. **Installed `uv`** – the project's package manager (not pre-installed)
2. **Created `.env`** with mock API keys and set it up
3. **Installed dependencies** – `uv pip install -e .` succeeded
4. **Fixed 5 compatibility errors** found during import verification:
   - `langchain.prompts` → `langchain_core.prompts` in `text_to_image.py` (langchain v1.2 removed t…
   - `pydantic` 2.10 + `mcp` pin needed for Chainlit 1.x compatibility
   - `scipy` 1.18+ broke with numpy 1.26 (`np.long` removed)
   - `chainlit` was pulled at v2.x which broke the code (uses v1.x `AudioChunk`, `Audio` classes)
   - `starlette` 1.x removed `on_startup` kwarg needed by Chainlit/FastAPI
5. **Wrote 17 unit tests** covering: settings, helpers, schedules, state, edges (workflow routing, …
6. **Verified the FastAPI webhook** – all endpoints respond correctly
7. **Verified the Chainlit interface** – boots and responds on port 8000

Replay the whole session, every command from a clean machine to this point.

How it was tested

One agent, one container, no human help. It installs the project the way its own documentation says to, runs it, and fixes what breaks. Everything below is recorded as it happened: the terminal session, the log and the exact commit. The full method.

Strengths and limits

Measured facts, not opinions. How this is written.

What went well

  • Installed in 3 minutes, faster than the median of the 138 comparable projects Argusic has measured.
  • Recovered from all 5 errors without a human stepping in, which says the failures are documented well enough to solve.
  • Licensed MIT, as reported by its host.
  • Measured 2 times, so the result is not a one-off.

What did not, or is not known

  • Only reached a running state against stand-in services, so nothing here proves it works against the real ones.

Of the 139 agent projects Argusic has installed and timed, ava-whatsapp-agent-course was the 48th fastest to reach a running state, and 93 of 139 reached one at all.

Also tested, in the same area

Every one of these was installed and run by Argusic on a clean machine. Nothing appears here that was not tested.

Run history

tested byattemptoutcomescorecost USDwhen
Argusic Runner2/3Runs with mocks92.000.18
Argusic Runner1/3Runs with mocks92.000.09

Topics (from GitHub)

agentagent-basedagentic-workflowagentssttttsvector-database

Embed the badge

Markdown for the project README. It links back here; terms on the terms page.

[![Tested by Argusic](https://argusic.com/badge/ava-whatsapp-agent-course.svg)](https://argusic.com/subject/ava-whatsapp-agent-course)

Questions

Does ava-whatsapp-agent-course run?
ava-whatsapp-agent-course runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 3 minutes, hitting 5 errors on the way, and recorded the session.
How did Argusic test ava-whatsapp-agent-course?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit 338fd6870df9. 2 attempts are recorded, and the full method is on the methodology page.
What did it cost to test ava-whatsapp-agent-course?
The run that produced this verdict cost $0.18: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does ava-whatsapp-agent-course take to install?
3 minutes in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
Does ava-whatsapp-agent-course need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing ava-whatsapp-agent-course?
5 things broke in the recorded run, and 5 were fixed without human help. Each one, and the time it cost, is listed on this page.
How does ava-whatsapp-agent-course compare with the alternatives?
Of the 139 agent projects Argusic has installed and timed, ava-whatsapp-agent-course was the 48th fastest to reach a running state, and 93 of 139 reached one at all.
Where is the evidence for ava-whatsapp-agent-course?
All 2 recorded runs are on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.

Discussion