I built a small Python prototype that converts runtime logs into four normalized signals:
- self-call ratio
- concurrency
- external admission rate
- recent-state diversity
It then evaluates the direction of change between time steps against a fixed table of symbolic patterns. For example, rising concurrency combined with falling external admission is labeled as a possible bottleneck.
I tested it on several synthetic traces. One early run produced a false positive because the entropy calculation compared a warmed-up window with an incomplete one. I changed the scanner so both windows must be fully initialized before pattern matching.
I am now exploring whether an LLM could explain these symbolic matches while remaining grounded in the measured values.
My questions:
- Has anyone used an OpenAI model to explain structured telemetry rather than raw logs?
- Would tool calling with a fixed schema be preferable to placing the pattern table directly in context?
- Are there useful evaluation methods for checking whether the model’s explanation stays faithful to the underlying measurements?
4.I would love any feedback.
Minimal code and sample traces:
The Operator Algebra paper ("An Operator Algebra Over Recursion, Scale, Flow, and Entropy") built twelve named operators (Onion, Apple, Gate, Stack, Mirror, Funnel, Hydra, Echo, Spiral, Ratchet, Lens, Compass) as explicit clamped-affine functions on a state space **𝒳 = [0,1]⁴**, and proved real, checkable theorems about that algebra
@DysTopia this is the algebra scanner. I’m self taught so it’s nothing fancy.
You do amazing things Mitchell!
Thank you Pi. It’s just a hobby. 
But it makes me happy you find value in it.
mitchell_d00:
just a hobby.
You are the only one that sees it as “just a hobby.”.
I’m just happy you dig it pi