applied-ai examples on Programmer.ie: Modern AI programming

Keep the report, the observation and the effect apart

Mon, 01 Jan 0001 00:00:00 +0000

Four workers report the same thing — SUCCEEDED — and the record says four different things, none of them on the worker’s say-so. The chapter’s claim is that “the agent said done” is three questions, not one: what the actor said, what the runtime could read, and what a declared check against a bound target supports.

Run it

git clone https://github.com/ernanhughes/codeai.git
cd codeai
git checkout c1707f793abbd6042dce7d00b6dde34f2dbf33cc
PYTHONPATH=src python examples/applied_ai/ch19_effect_observation.py

git clone https://github.com/ernanhughes/codeai.git
cd codeai
git checkout c1707f793abbd6042dce7d00b6dde34f2dbf33cc
PYTHONPATH=src python examples/applied_ai/ch19_effect_observation.py

CodeAI has no runtime dependencies, so nothing needs installing; PYTHONPATH=src is enough. On PowerShell, set it first with $env:PYTHONPATH = "src". Python 3.11 or later. No model is called and nothing leaves the machine.

Resolve the grant from the record, not from the caller

Mon, 01 Jan 0001 00:00:00 +0000

The chapter’s claim is that the grant that authorized an effect is one the record establishes. A caller that supplies its own authority is not a source of permission: it is a claim, and the runtime decides the claim from the directive chain it has recorded.

Run it

git clone https://github.com/ernanhughes/codeai.git
cd codeai
git checkout c1707f793abbd6042dce7d00b6dde34f2dbf33cc
PYTHONPATH=src python examples/applied_ai/ch20_authority.py

git clone https://github.com/ernanhughes/codeai.git
cd codeai
git checkout c1707f793abbd6042dce7d00b6dde34f2dbf33cc
PYTHONPATH=src python examples/applied_ai/ch20_authority.py

CodeAI has no runtime dependencies, so nothing needs installing. Python 3.11 or later. No model is called and nothing leaves the machine.

Bind a check to the state it actually reached

Mon, 01 Jan 0001 00:00:00 +0000

A check that passes establishes one narrow thing: this declared command, against this bound target, exited 0. The chapter’s claim is that the interesting cases are the other three, and that INCONCLUSIVE and ERROR are not FAIL. A check that could not read its subject, and a check that measured the wrong state, need different repairs from a check that found a real problem.

Run it

git clone https://github.com/ernanhughes/codeai.git
cd codeai
git checkout c1707f793abbd6042dce7d00b6dde34f2dbf33cc
PYTHONPATH=src python examples/applied_ai/ch21_verification.py

git clone https://github.com/ernanhughes/codeai.git
cd codeai
git checkout c1707f793abbd6042dce7d00b6dde34f2dbf33cc
PYTHONPATH=src python examples/applied_ai/ch21_verification.py

CodeAI has no runtime dependencies, so nothing needs installing. Python 3.11 or later. No model is called and nothing leaves the machine.

A failed report is not an absent effect

Mon, 01 Jan 0001 00:00:00 +0000

The chapter’s hardest distinction is operation reported failed → effect did not happen. Those are two different facts, and a system that collapses them will retry an action that already took effect. The program’s fixture is a worker that appends a line to a file and then loses its connection.

Run it

git clone https://github.com/ernanhughes/codeai.git
cd codeai
git checkout c1707f793abbd6042dce7d00b6dde34f2dbf33cc
PYTHONPATH=src python examples/applied_ai/ch22_action_recovery.py

git clone https://github.com/ernanhughes/codeai.git
cd codeai
git checkout c1707f793abbd6042dce7d00b6dde34f2dbf33cc
PYTHONPATH=src python examples/applied_ai/ch22_action_recovery.py

CodeAI has no runtime dependencies, so nothing needs installing. Python 3.11 or later. No model is called and nothing leaves the machine.

Decide the next step, and replay the decision that was recorded

Mon, 01 Jan 0001 00:00:00 +0000

The chapter separates three things that often get merged: which operation comes next, whether to escalate to a person, and which selector answers. The scheduler here is a deterministic policy over an explicit state, and the run’s last part is the part that matters: the decision that was recorded is replayed, and the facts it rested on are shown.

Run it

git clone https://github.com/ernanhughes/codeai.git
cd codeai
git checkout c1707f793abbd6042dce7d00b6dde34f2dbf33cc
PYTHONPATH=src python examples/applied_ai/ch28_scheduler.py

git clone https://github.com/ernanhughes/codeai.git
cd codeai
git checkout c1707f793abbd6042dce7d00b6dde34f2dbf33cc
PYTHONPATH=src python examples/applied_ai/ch28_scheduler.py

CodeAI has no runtime dependencies, so nothing needs installing. Python 3.11 or later. No model is called and nothing leaves the machine.